config-schema.json,config.example.yaml: Update examples and schema

config: support environment variable macros in apiKeys (#467 )
Add substituteEnvMacros support for apiKeys configuration field, allowing API keys to be loaded from environment variables using the ${env.VAR_NAME} syntax. - Apply env macro substitution before validation - Add tests for env macro substitution in apiKeys
2026-01-16 22:43:25 -08:00 · 2026-01-16 22:41:14 -08:00 · 2026-01-16 22:25:20 -08:00 · 2026-01-15 18:59:43 -08:00 · 2026-01-14 22:03:42 -08:00 · 2026-01-10 22:14:33 -08:00
32 changed files with 2858 additions and 299 deletions
@@ -8,8 +8,15 @@ reviews:
  poem: false
  review_status: true
  collapse_walkthrough: false
+  sequence_diagrams: false
+  finishing_touches:
+    docstrings:
+      enabled: false
  auto_review:
    enabled: true
    drafts: false
 chat:
  auto_reply: true
+issue_enrichment:
+  planning:
+    enabled: false
@@ -10,17 +10,36 @@ on:
  # Allows manual triggering of the workflow
  workflow_dispatch:

+  # Run on workflow file changes (without pushing)
+  push:
+    paths:
+      - '.github/workflows/containers.yml'
+      - 'docker/build-container.sh'
+
 jobs:
  build-and-push:
    runs-on: ubuntu-latest
    strategy:
      matrix:
-        platform: [intel, cuda, vulkan, cpu, musa]
+        platform: [intel, cuda, vulkan, cpu, musa, rocm]
      fail-fast: false
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

+      - name: Free up disk space
+        if: matrix.platform == 'rocm'
+        run: |
+          echo "Before cleanup:"
+          df -h
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /opt/ghc
+          sudo rm -rf /opt/hostedtoolcache/CodeQL
+          sudo docker system prune -af
+          echo "After cleanup:"
+          df -h
+
      - name: Log in to GitHub Container Registry
        uses: docker/login-action@v2
        with:
@@ -31,7 +50,7 @@ jobs:
      - name: Run build-container
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: ./docker/build-container.sh ${{ matrix.platform }} true
+        run: ./docker/build-container.sh ${{ matrix.platform }} ${{ github.event_name != 'push' }}

  # note make sure mostlygeek/llama-swap has admin rights to the llama-swap package
  # see: https://github.com/actions/delete-package-versions/issues/74
@@ -1,5 +1,3 @@
-# Project: llama-swap
-
 ## Project Description:

 llama-swap is a light weight, transparent proxy server that provides automatic model swapping to llama.cpp's server.
@@ -7,37 +5,45 @@ llama-swap is a light weight, transparent proxy server that provides automatic m
 ## Tech stack

 - golang
- typescript, vite and react for UI (ui/)
-
-## Testing
-
- `make test-dev` - Use this when making iterative changes. Runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
- `make test-all` - runs at the end before completing work. Includes long running concurrency tests.
+- typescript, vite and react for UI (located in ui/)

 ## Workflow Tasks

-### Plan Improvements
+- when summarizing changes only include details that require further action
+- just say "Done." when there is no further action
+- use `gh` to create PRs and load issues
+- do include Co-Authored-By or created by when committing changes or creating PRs
+- keep PR descriptions short and focused on changes.
+  - never include a test plan

-Work plans are located in ai-plans/. Plans written by the user may be incomplete, contain inconsistencies or errors.
+## Testing

-When the user asks to improve a plan follow these guidelines for expanding and improving it.
+- Follow test naming conventions like `TestProxyManager_<test name>`, `TestProcessGroup_<test name>`, etc.
+- Use `go test -v -run <name pattern for new tests>` to run any new tests you've written.
+- Use `make test-dev` after running new tests for a quick over all test run. This runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
+- Use `make test-all` before completing work. This includes long running concurrency tests.

- Identify any inconsistencies.
- Expand plans out to be detailed specification of requirements and changes to be made.
- Plans should have at least these sections:
-  - Title - very short, describes changes
-  - Overview: A more detailed summary of goal and outcomes desired
-  - Design Requirements: Detailed descriptions of what needs to be done
-  - Testing Plan: Tests to be implemented
-  - Checklist: A detailed list of changes to be made
+### Commit message example format:

-Look for "plan expansion" as explicit instructions to improve a plan.
+```
+proxy: add new feature

-### Implementation of plans
+Add new feature that implements functionality X and Y.

-When the user says "paint it", respond with "commencing automated assembly". Then implement the changes as described by the plan. Update the checklist as you complete items.
+- key change 1
+- key change 2
+- key change 3

-## General Rules
+fixes #123
+```

- when summarizing changes only include details that require further action (action items)
- when there are no action items, just say "Done."
+## Code Reviews
+
+- use three levels High, Medium, Low severity
+- label each discovered issue with a label like H1, M2, L3 respectively
+- High severity are must fix issues (security, race conditions, critical bugs)
+- Medium severity are recommended improvements (coding style, missing functionality, inconsistencies)
+- Low severity are nice to have changes and nits
+- Include a suggestion with each discovered item
+- Limit your code review to three items with the highest priority first
+- Double check your discovered items and recommended remediations
@@ -18,9 +18,13 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and
 - ✅ OpenAI API supported endpoints:
  - `v1/completions`
  - `v1/chat/completions`
+  - `v1/responses`
  - `v1/embeddings`
  - `v1/audio/speech` ([#36](https://github.com/mostlygeek/llama-swap/issues/36))
  - `v1/audio/transcriptions` ([docs](https://github.com/mostlygeek/llama-swap/issues/41#issuecomment-2722637867))
+  - `v1/audio/voices`
+  - `v1/images/generations`
+  - `v1/images/edits`
 - ✅ Anthropic API supported endpoints:
  - `v1/messages`
 - ✅ llama-server (llama.cpp) supported endpoints
@@ -34,6 +38,7 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and
  - `/running` - list currently running models ([#61](https://github.com/mostlygeek/llama-swap/issues/61))
  - `/log` - remote log monitoring
  - `/health` - just returns "OK"
+- ✅ API Key support - define keys to restrict access to API endpoints
 - ✅ Customizable
  - Run multiple models at once with `Groups` ([#107](https://github.com/mostlygeek/llama-swap/issues/107))
  - Automatic unloading of models after timeout by setting a `ttl`
@@ -188,11 +188,17 @@
                                "default": "",
                                "pattern": "^[a-zA-Z0-9_, ]*$",
                                "description": "Comma separated list of parameters to remove from the request. Used for server-side enforcement of sampling parameters."
+                            },
+                            "setParams": {
+                                "type": "object",
+                                "additionalProperties": true,
+                                "default": {},
+                                "description": "Dictionary of parameters to set/override in requests. Useful for enforcing specific parameter values. Protected params like 'model' cannot be overridden. Values can be strings, numbers, booleans, arrays, or objects."
                            }
                        },
                        "additionalProperties": false,
                        "default": {},
-                        "description": "Dictionary of filter settings. Only stripParams is supported."
+                        "description": "Dictionary of filter settings. Supports stripParams and setParams."
                    },
                    "metadata": {
                        "type": "object",
@@ -273,6 +279,78 @@
            },
            "additionalProperties": false,
            "description": "A dictionary of event triggers and actions. Only supported hook is on_startup."
+        },
+        "logToStdout": {
+            "type": "string",
+            "enum": [
+                "proxy",
+                "upstream",
+                "both",
+                "none"
+            ],
+            "default": "proxy",
+            "description": "Controls what is logged to stdout. 'proxy': logs generated by llama-swap, 'upstream': copy of upstream process stdout logs, 'both': both interleaved together, 'none': no logs written to stdout."
+        },
+        "apiKeys": {
+            "type": "array",
+            "items": {
+                "type": "string",
+                "minLength": 1
+            },
+            "default": [],
+            "description": "Require an API key when making requests to inference endpoints. When empty, authorization will not be checked. Each key is a non-empty string."
+        },
+        "peers": {
+            "type": "object",
+            "additionalProperties": {
+                "type": "object",
+                "required": [
+                    "proxy",
+                    "models"
+                ],
+                "properties": {
+                    "proxy": {
+                        "type": "string",
+                        "format": "uri",
+                        "description": "A valid base URL to proxy requests to. Requested path to llama-swap will be appended to the end of the proxy value."
+                    },
+                    "apiKey": {
+                        "type": "string",
+                        "default": "",
+                        "description": "A string key to be injected into the request. If blank, no key will be added. Key will be injected into headers: Authorization: Bearer <key> and x-api-key: <key>."
+                    },
+                    "models": {
+                        "type": "array",
+                        "items": {
+                            "type": "string",
+                            "minLength": 1
+                        },
+                        "description": "A list of models served by the peer."
+                    },
+                    "filters": {
+                        "type": "object",
+                        "properties": {
+                            "stripParams": {
+                                "type": "string",
+                                "default": "",
+                                "pattern": "^[a-zA-Z0-9_, ]*$",
+                                "description": "Comma separated list of parameters to remove from the request. Useful for removing parameters that the peer doesn't support."
+                            },
+                            "setParams": {
+                                "type": "object",
+                                "additionalProperties": true,
+                                "default": {},
+                                "description": "Dictionary of parameters to set/override in requests to this peer. Useful for injecting provider-specific settings. Protected params like 'model' cannot be overridden. Values can be strings, numbers, booleans, arrays, or objects."
+                            }
+                        },
+                        "additionalProperties": false,
+                        "default": {},
+                        "description": "Dictionary of filter settings for peer requests. Supports stripParams and setParams."
+                    }
+                }
+            },
+            "default": {},
+            "description": "A dictionary of remote peers and models they provide. Peers can be another llama-swap or any server that provides the /v1/ generative API endpoints supported by llama-swap."
        }
    }
 }
@@ -34,6 +34,16 @@ logLevel: info
 # - For more info, read: https://pkg.go.dev/time#pkg-constants
 logTimeFormat: ""

+# logToStdout: controls what is logged to stdout
+# - optional, default: "proxy"
+# - valid values:
+#   - "proxy": logs generated by llama-swap when swapping models,
+#      handling requests, etc.
+#   - "upstream": a copy of an upstream processes stdout logs
+#   - "both": both the proxy and upstream logs interleaved together
+#   - "none": no logs are ever written to stdout
+logToStdout: "proxy"
+
 # metricsMaxInMemory: maximum number of metrics to keep in memory
 # - optional, default: 1000
 # - controls how many metrics are stored in memory before older ones are discarded
@@ -70,6 +80,9 @@ includeAliasesInList: false
 # - macro names must not be a reserved name: PORT or MODEL_ID
 # - macro values can be numbers, bools, or strings
 # - macros can contain other macros, but they must be defined before they are used
+# - environment variables can be referenced with ${env.VAR_NAME} syntax
+#   - env macros are substituted first, before regular macros
+#   - if the env var is not set, config loading will fail with an error
 macros:
  # Example of a multi-line macro
  "latest-llama": >
@@ -82,6 +95,24 @@ macros:
  # but they must be previously declared.
  "default_args": "--ctx-size ${default_ctx}"

+  # Example of environment variable macros
+  # - ${env.VAR_NAME} pulls the value from the system environment
+  # - useful for paths, secrets, or machine-specific configuration
+  "models_dir": "${env.HOME}/models"
+
+# apiKeys: require an API key when making requests to inference endpoints
+# - optional, default: []
+# - when empty (the default) authorization will not be checked as llama-swap is default-allow
+# - each key is a non-empty string
+apiKeys:
+  - "sk-hunter2"
+  # tip, one liner: printf "sk-%s\n" "$(head -c 48 /dev/urandom | base64 )"
+  - "sk-gyCPiKUcIfPlaM4OSMZekkprgijPx6+OsmQs8Rsg0xZ9qpy6gKWsIKqHOk+cgXVx"
+
+  # use environment variable macros to keep secrets out of the config
+  - "${env.API_KEY_1}"
+  - "${env.API_KEY_2}"
+
 # models: a dictionary of model configurations
 # - required
 # - each key is the model's ID, used in API requests
@@ -165,7 +196,7 @@ models:

    # filters: a dictionary of filter settings
    # - optional, default: empty dictionary
-    # - only stripParams is currently supported
+    # - same capabilities as peer filters (stripParams, setParams)
    filters:
      # stripParams: a comma separated list of parameters to remove from the request
      # - optional, default: ""
@@ -175,6 +206,16 @@ models:
      # - recommended to stick to sampling parameters
      stripParams: "temperature, top_p, top_k"

+      # setParams: a dictionary of parameters to set/override in requests
+      # - optional, default: empty dictionary
+      # - useful for enforcing specific parameter values
+      # - protected params like "model" cannot be overridden
+      # - values can be strings, numbers, booleans, arrays, or objects
+      setParams:
+        # Example: enforce specific sampling parameters
+        temperature: 0.7
+        top_p: 0.9
+
    # metadata: a dictionary of arbitrary values that are included in /v1/models
    # - optional, default: empty dictionary
    # - while metadata can contains complex types it is recommended to keep it simple
@@ -321,3 +362,55 @@ hooks:
    #   otherwise models will be loaded and swapped out
    preload:
      - "llama"
+
+# peers: a dictionary of remote peers and models they provide
+# - optional, default empty dictionary
+# - peers can be another llama-swap
+# - peers can be any server that provides the /v1/ generative api endpoints supported by llama-swap
+peers:
+  # keys is the peer'd ID
+  llama-swap-peer:
+    # proxy: a valid base URL to proxy requests to
+    # - required
+    # - requested path to llama-swap will be appended to the end of the proxy value
+    proxy: http://192.168.1.23
+    # models: a list of models served by the peer
+    # - required
+    models:
+      - model_a
+      - model_b
+      - embeddings/model_c
+  openrouter:
+    proxy: https://openrouter.ai/api
+    # apiKey: a string key to be injected into the request
+    # - optional, default: ""
+    # - if blank, no key will be added to the request
+    # - key will be injected into headers: Authorization: Bearer <key> and x-api-key: <key>
+    apiKey: sk-your-openrouter-key
+    models:
+      - meta-llama/llama-3.1-8b-instruct
+      - qwen/qwen3-235b-a22b-2507
+      - deepseek/deepseek-v3.2
+      - z-ai/glm-4.7
+      - moonshotai/kimi-k2-0905
+      - minimax/minimax-m2.1
+    # filters: a dictionary of filter settings for peer requests
+    # - optional, default: empty dictionary
+    # - same capabilities as model filters (stripParams, setParams)
+    filters:
+      # stripParams: a comma separated list of parameters to remove from the request
+      # - optional, default: ""
+      # - useful for removing parameters that the peer doesn't support
+      # - the `model` parameter can never be removed
+      stripParams: "temperature, top_p"
+
+      # setParams: a dictionary of parameters to set/override in requests to this peer
+      # - optional, default: empty dictionary
+      # - useful for injecting provider-specific settings like data retention policies
+      # - protected params like "model" cannot be overridden
+      # - values can be strings, numbers, booleans, arrays, or objects
+      setParams:
+        # Example: enforce zero-data-retention for OpenRouter
+        provider:
+          data_collection: "deny"
+          allow_fallbacks: false
@@ -2,21 +2,37 @@

 cd $(dirname "$0")

+# use this to test locally, example:
+# GITHUB_TOKEN=$(gh auth token) LOG_DEBUG=1 DEBUG_ABORT_BUILD=1 ./docker/build-container.sh rocm
+# you need read:package scope on the token. Generate a personal access token with
+# the scopes: gist, read:org, repo, write:packages
+# then: gh auth login (and copy/paste the new token)
+
+log_debug() {
+    if [ "$LOG_DEBUG" = "1" ]; then
+        echo "[DEBUG] $*"
+    fi
+}
+
+log_info() {
+    echo "[INFO] $*"
+}
+
 ARCH=$1
 PUSH_IMAGES=${2:-false}

 # List of allowed architectures
-ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cpu")
+ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cpu" "rocm")

 # Check if ARCH is in the allowed list
 if [[ ! " ${ALLOWED_ARCHS[@]} " =~ " ${ARCH} " ]]; then
-  echo "Error: ARCH must be one of the following: ${ALLOWED_ARCHS[@]}"
+  log_info "Error: ARCH must be one of the following: ${ALLOWED_ARCHS[@]}"
  exit 1
 fi

 # Check if GITHUB_TOKEN is set and not empty
 if [[ -z "$GITHUB_TOKEN" ]]; then
-  echo "Error: GITHUB_TOKEN is not set or is empty."
+  log_info "Error: GITHUB_TOKEN is not set or is empty."
  exit 1
 fi

@@ -32,25 +48,74 @@ LS_REPO=${GITHUB_REPOSITORY:-mostlygeek/llama-swap}
 # have to strip out the 'v' due to .tar.gz file naming
 LS_VER=$(curl -s https://api.github.com/repos/${LS_REPO}/releases/latest | jq -r .tag_name | sed 's/v//')

+# Fetches the most recent llama.cpp tag matching the given prefix
+# Handles pagination to search beyond the first 100 results
+# $1 - tag_prefix (e.g., "server" or "server-vulkan")
+# Returns: the version number extracted from the tag
+fetch_llama_tag() {
+    local tag_prefix=$1
+    local page=1
+    local per_page=100
+
+    while true; do
+        log_debug "Fetching page $page for tag prefix: $tag_prefix"
+
+        local response=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
+            "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions?per_page=${per_page}&page=${page}")
+
+        # Check for API errors
+        if echo "$response" | jq -e '.message' > /dev/null 2>&1; then
+            local error_msg=$(echo "$response" | jq -r '.message')
+            log_info "GitHub API error: $error_msg"
+            return 1
+        fi
+
+        # Check if response is empty array (no more pages)
+        if [ "$(echo "$response" | jq 'length')" -eq 0 ]; then
+            log_debug "No more pages (empty response)"
+            return 1
+        fi
+
+        # Extract matching tag from this page
+        local found_tag=$(echo "$response" | jq -r \
+            ".[] | select(.metadata.container.tags[]? | startswith(\"$tag_prefix\")) | .metadata.container.tags[] | select(startswith(\"$tag_prefix\"))" \
+            | sort -r | head -n1)
+
+        if [ -n "$found_tag" ]; then
+            log_debug "Found tag: $found_tag on page $page"
+            echo "$found_tag" | awk -F '-' '{print $NF}'
+            return 0
+        fi
+
+        page=$((page + 1))
+
+        # Safety limit to prevent infinite loops
+        if [ $page -gt 50 ]; then
+            log_info "Reached pagination safety limit (50 pages)"
+            return 1
+        fi
+    done
+}
+
 if [ "$ARCH" == "cpu" ]; then
-    # cpu only containers just use the server tag
-    LCPP_TAG=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
-        "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions" \
-        | jq -r '.[] | select(.metadata.container.tags[] | startswith("server")) | .metadata.container.tags[]' \
-        | sort -r | head -n1 | awk -F '-' '{print $3}')
+    LCPP_TAG=$(fetch_llama_tag "server")
    BASE_TAG=server-${LCPP_TAG}
 else
-    LCPP_TAG=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
-        "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions" \
-        | jq -r --arg arch "$ARCH" '.[] | select(.metadata.container.tags[] | startswith("server-\($arch)")) | .metadata.container.tags[]' \
-        | sort -r | head -n1 | awk -F '-' '{print $3}')
+    LCPP_TAG=$(fetch_llama_tag "server-${ARCH}")
    BASE_TAG=server-${ARCH}-${LCPP_TAG}
 fi

 # Abort if LCPP_TAG is empty.
 if [[ -z "$LCPP_TAG" ]]; then
-    echo "Abort: Could not find llama-server container for arch: $ARCH"
+    log_info "Abort: Could not find llama-server container for arch: $ARCH"
    exit 1
+else
+    log_info "LCPP_TAG: $LCPP_TAG"
+fi
+
+if [[ ! -z "$DEBUG_ABORT_BUILD" ]]; then
+    log_info "Abort: DEBUG_ABORT_BUILD set"
+    exit 0
 fi

 for CONTAINER_TYPE in non-root root; do
@@ -68,7 +133,7 @@ for CONTAINER_TYPE in non-root root; do
    USER_HOME=/app
  fi

-  echo "Building $CONTAINER_TYPE $CONTAINER_TAG $LS_VER"
+  log_info "Building $CONTAINER_TYPE $CONTAINER_TAG $LS_VER"
  docker build -f llama-swap.Containerfile --build-arg BASE_TAG=${BASE_TAG} --build-arg LS_VER=${LS_VER} --build-arg UID=${USER_UID} \
    --build-arg LS_REPO=${LS_REPO} --build-arg GID=${USER_GID} --build-arg USER_HOME=${USER_HOME} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} \
    --build-arg BASE_IMAGE=${BASE_IMAGE} .
@@ -86,9 +86,12 @@ llama-swap supports many more features to customize how you want to manage your
 ## Full Configuration Example

 > [!NOTE]
-> This is a copy of `config.example.yaml`. Always check that for the most up to date examples.
+> Always check [config.example.yaml](https://github.com/mostlygeek/llama-swap/blob/main/config.example.yaml) for the most up to date reference for all example configurations.

 ```yaml
+# add this modeline for validation in vscode
+# yaml-language-server: $schema=https://raw.githubusercontent.com/mostlygeek/llama-swap/refs/heads/main/config-schema.json
+#
 # llama-swap YAML configuration example
 # -------------------------------------
 #
@@ -114,6 +117,24 @@ healthCheckTimeout: 500
 # - Valid log levels: debug, info, warn, error
 logLevel: info

+# logTimeFormat: enables and sets the logging timestamp format
+# - optional, default (disabled): ""
+# - Valid values: "", "ansic", "unixdate", "rubydate", "rfc822", "rfc822z",
+#   "rfc850", "rfc1123", "rfc1123z", "rfc3339", "rfc3339nano", "kitchen",
+#   "stamp", "stampmilli", "stampmicro", and "stampnano".
+# - For more info, read: https://pkg.go.dev/time#pkg-constants
+logTimeFormat: ""
+
+# logToStdout: controls what is logged to stdout
+# - optional, default: "proxy"
+# - valid values:
+#   - "proxy": logs generated by llama-swap when swapping models,
+#      handling requests, etc.
+#   - "upstream": a copy of an upstream processes stdout logs
+#   - "both": both the proxy and upstream logs interleaved together
+#   - "none": no logs are ever written to stdout
+logToStdout: "proxy"
+
 # metricsMaxInMemory: maximum number of metrics to keep in memory
 # - optional, default: 1000
 # - controls how many metrics are stored in memory before older ones are discarded
@@ -126,6 +147,30 @@ metricsMaxInMemory: 1000
 # - it is automatically incremented for every model that uses it
 startPort: 10001

+# sendLoadingState: inject loading status updates into the reasoning (thinking)
+# field
+# - optional, default: false
+# - when true, a stream of loading messages will be sent to the client in the
+#   reasoning field so chat UIs can show that loading is in progress.
+# - see #366 for more details
+sendLoadingState: true
+
+# includeAliasesInList: present aliases within the /v1/models OpenAI API listing
+# - optional, default: false
+# - when true, model aliases will be output to the API model listing duplicating
+#   all fields except for Id so chat UIs can use the alias equivalent to the original.
+includeAliasesInList: false
+
+# apiKeys: require an API key when making requests to inference endpoints
+# - optional, default: []
+# - when empty (the default) authorization will not be checked as llama-swap is default-allow
+# - each key is a non-empty string
+apiKeys:
+  - "sk-hunter2"
+  # hint, one liner: printf "sk-%s\n" "$(head -c 48 /dev/urandom | base64 )"
+  - "sk-gyCPiKUcIfPlaM4OSMZekkprgijPx6+OsmQs8Rsg0xZ9qpy6gKWsIKqHOk+cgXVx"
+  - "sk-+QtIn0Zjj4UHjiaZYiZEnru4mrwKM9RzhmJeK5SobNXLl8QMFXxGz1/2lEuvQpkb"
+
 # macros: a dictionary of string substitutions
 # - optional, default: empty dictionary
 # - macros are reusable snippets
@@ -274,6 +319,10 @@ models:
    # - recommended to be omitted and the default used
    concurrencyLimit: 0

+    # sendLoadingState: overrides the global sendLoadingState setting for this model
+    # - optional, default: undefined (use global setting)
+    sendLoadingState: false
+
  # Unlisted model example:
  "qwen-unlisted":
    # unlisted: boolean, true or false
@@ -383,4 +432,36 @@ hooks:
    #   otherwise models will be loaded and swapped out
    preload:
      - "llama"
+
+# peers: a dictionary of remote peers and models they provide
+# - optional, default empty dictionary
+# - peers can be another llama-swap
+# - peers can be any server that provides the /v1/ generative api endpoints supported by llama-swap
+peers:
+  # keys is the peer'd ID
+  llama-swap-peer:
+    # proxy: a valid base URL to proxy requests to
+    # - required
+    # - requested path to llama-swap will be appended to the end of the proxy value
+    proxy: http://192.168.1.23
+    # models: a list of models served by the peer
+    # - required
+    models:
+      - model_a
+      - model_b
+      - embeddings/model_c
+  openrouter:
+    proxy: https://openrouter.ai/api
+    # apiKey: a string key to be injected into the request
+    # - optional, default: ""
+    # - if blank, no key will be added to the request
+    # - key will be injected into headers: Authorization: Bearer <key> and x-api-key: <key>
+    apiKey: sk-your-openrouter-key
+    models:
+      - meta-llama/llama-3.1-8b-instruct
+      - qwen/qwen3-235b-a22b-2507
+      - deepseek/deepseek-v3.2
+      - z-ai/glm-4.7
+      - moonshotai/kimi-k2-0905
+      - minimax/minimax-m2.1
 ```
@@ -15,6 +15,12 @@ import (
 )

 const DEFAULT_GROUP_ID = "(default)"
+const (
+	LogToStdoutProxy    = "proxy"
+	LogToStdoutUpstream = "upstream"
+	LogToStdoutBoth     = "both"
+	LogToStdoutNone     = "none"
+)

 type MacroEntry struct {
 	Name  string
@@ -81,6 +87,7 @@ type GroupConfig struct {
 var (
 	macroNameRegex    = regexp.MustCompile(`^[a-zA-Z0-9_-]+$`)
 	macroPatternRegex = regexp.MustCompile(`\$\{([a-zA-Z0-9_-]+)\}`)
+	envMacroRegex     = regexp.MustCompile(`\$\{env\.([a-zA-Z_][a-zA-Z0-9_]*)\}`)
 )

 // set default values for GroupConfig
@@ -114,6 +121,7 @@ type Config struct {
 	LogRequests        bool                   `yaml:"logRequests"`
 	LogLevel           string                 `yaml:"logLevel"`
 	LogTimeFormat      string                 `yaml:"logTimeFormat"`
+	LogToStdout        string                 `yaml:"logToStdout"`
 	MetricsMaxInMemory int                    `yaml:"metricsMaxInMemory"`
 	Models             map[string]ModelConfig `yaml:"models"` /* key is model ID */
 	Profiles           map[string][]string    `yaml:"profiles"`
@@ -136,6 +144,12 @@ type Config struct {

 	// present aliases to /v1/models OpenAI API listing
 	IncludeAliasesInList bool `yaml:"includeAliasesInList"`
+
+	// support API keys, see issue #433, #50, #251
+	RequiredAPIKeys []string `yaml:"apiKeys"`
+
+	// support remote peers, see issue #433, #296
+	Peers PeerDictionaryConfig `yaml:"peers"`
 }

 func (c *Config) RealModelName(search string) (string, bool) {
@@ -177,6 +191,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		StartPort:          5800,
 		LogLevel:           "info",
 		LogTimeFormat:      "",
+		LogToStdout:        LogToStdoutProxy,
 		MetricsMaxInMemory: 1000,
 	}
 	err = yaml.Unmarshal(data, &config)
@@ -193,6 +208,12 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		return Config{}, fmt.Errorf("startPort must be greater than 1")
 	}

+	switch config.LogToStdout {
+	case LogToStdoutProxy, LogToStdoutUpstream, LogToStdoutBoth, LogToStdoutNone:
+	default:
+		return Config{}, fmt.Errorf("logToStdout must be one of: proxy, upstream, both, none")
+	}
+
 	// Populate the aliases map
 	config.aliases = make(map[string]string)
 	for modelName, modelConfig := range config.Models {
@@ -217,6 +238,17 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		}
 	}

+	// Process environment variable macros in global macro values first
+	for i, macro := range config.Macros {
+		if strVal, ok := macro.Value.(string); ok {
+			newVal, err := substituteEnvMacros(strVal)
+			if err != nil {
+				return Config{}, fmt.Errorf("global macro '%s': %w", macro.Name, err)
+			}
+			config.Macros[i].Value = newVal
+		}
+	}
+
 	// Get and sort all model IDs first, makes testing more consistent
 	modelIds := make([]string, 0, len(config.Models))
 	for modelId := range config.Models {
@@ -232,6 +264,48 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		modelConfig.Cmd = StripComments(modelConfig.Cmd)
 		modelConfig.CmdStop = StripComments(modelConfig.CmdStop)

+		// Substitute environment variable macros in model fields
+		modelConfig.Cmd, err = substituteEnvMacros(modelConfig.Cmd)
+		if err != nil {
+			return Config{}, fmt.Errorf("model %s cmd: %w", modelId, err)
+		}
+		modelConfig.CmdStop, err = substituteEnvMacros(modelConfig.CmdStop)
+		if err != nil {
+			return Config{}, fmt.Errorf("model %s cmdStop: %w", modelId, err)
+		}
+		modelConfig.Proxy, err = substituteEnvMacros(modelConfig.Proxy)
+		if err != nil {
+			return Config{}, fmt.Errorf("model %s proxy: %w", modelId, err)
+		}
+		modelConfig.CheckEndpoint, err = substituteEnvMacros(modelConfig.CheckEndpoint)
+		if err != nil {
+			return Config{}, fmt.Errorf("model %s checkEndpoint: %w", modelId, err)
+		}
+		modelConfig.Filters.StripParams, err = substituteEnvMacros(modelConfig.Filters.StripParams)
+		if err != nil {
+			return Config{}, fmt.Errorf("model %s filters.stripParams: %w", modelId, err)
+		}
+
+		// Substitute env macros in model-level macro values
+		for i, macro := range modelConfig.Macros {
+			if strVal, ok := macro.Value.(string); ok {
+				newVal, err := substituteEnvMacros(strVal)
+				if err != nil {
+					return Config{}, fmt.Errorf("model %s macro '%s': %w", modelId, macro.Name, err)
+				}
+				modelConfig.Macros[i].Value = newVal
+			}
+		}
+
+		// Substitute env macros in metadata
+		if len(modelConfig.Metadata) > 0 {
+			result, err := substituteEnvMacrosInValue(modelConfig.Metadata)
+			if err != nil {
+				return Config{}, fmt.Errorf("model %s metadata: %w", modelId, err)
+			}
+			modelConfig.Metadata = result.(map[string]any)
+		}
+
 		// validate model macros
 		for _, macro := range modelConfig.Macros {
 			if err = validateMacro(macro.Name, macro.Value); err != nil {
@@ -342,6 +416,13 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 				// Any other macro is unknown
 				return Config{}, fmt.Errorf("unknown macro '${%s}' found in %s.%s", macroName, modelId, fieldName)
 			}
+
+			// Check for unsubstituted env macros
+			envMatches := envMacroRegex.FindAllStringSubmatch(fieldValue, -1)
+			for _, match := range envMatches {
+				varName := match[1]
+				return Config{}, fmt.Errorf("environment variable '%s' not set (found in %s.%s)", varName, modelId, fieldName)
+			}
 		}

 		// Check for unknown macros in metadata
@@ -404,6 +485,23 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		config.Hooks.OnStartup.Preload = toPreload
 	}

+	// check api keys validity and substitute env macros
+	for i, apikey := range config.RequiredAPIKeys {
+		apikey, err = substituteEnvMacros(apikey)
+		if err != nil {
+			return Config{}, fmt.Errorf("apiKeys[%d]: %w", i, err)
+		}
+		config.RequiredAPIKeys[i] = apikey
+
+		if apikey == "" {
+			return Config{}, fmt.Errorf("empty api key found in apiKeys")
+		}
+
+		if strings.Contains(apikey, " ") {
+			return Config{}, fmt.Errorf("api key cannot contain spaces: `%s`", apikey)
+		}
+	}
+
 	return config, nil
 }

@@ -543,6 +641,12 @@ func validateMetadataForUnknownMacros(value any, modelId string) error {
 			macroName := match[1]
 			return fmt.Errorf("model %s metadata: unknown macro '${%s}'", modelId, macroName)
 		}
+		// Check for unsubstituted env macros
+		envMatches := envMacroRegex.FindAllStringSubmatch(v, -1)
+		for _, match := range envMatches {
+			varName := match[1]
+			return fmt.Errorf("model %s metadata: environment variable '%s' not set", modelId, varName)
+		}
 		return nil

 	case map[string]any:
@@ -614,3 +718,54 @@ func substituteMacroInValue(value any, macroName string, macroValue any) (any, e
 		return value, nil
 	}
 }
+
+// substituteEnvMacros replaces ${env.VAR_NAME} with environment variable values
+// Returns error if any env var is not set
+func substituteEnvMacros(s string) (string, error) {
+	result := s
+	matches := envMacroRegex.FindAllStringSubmatch(s, -1)
+	for _, match := range matches {
+		fullMatch := match[0] // ${env.VAR_NAME}
+		varName := match[1]   // VAR_NAME
+
+		value, exists := os.LookupEnv(varName)
+		if !exists {
+			return "", fmt.Errorf("environment variable '%s' is not set", varName)
+		}
+		result = strings.ReplaceAll(result, fullMatch, value)
+	}
+	return result, nil
+}
+
+// substituteEnvMacrosInValue recursively substitutes env macros in nested structures
+func substituteEnvMacrosInValue(value any) (any, error) {
+	switch v := value.(type) {
+	case string:
+		return substituteEnvMacros(v)
+
+	case map[string]any:
+		newMap := make(map[string]any)
+		for key, val := range v {
+			newVal, err := substituteEnvMacrosInValue(val)
+			if err != nil {
+				return nil, err
+			}
+			newMap[key] = newVal
+		}
+		return newMap, nil
+
+	case []any:
+		newSlice := make([]any, len(v))
+		for i, val := range v {
+			newVal, err := substituteEnvMacrosInValue(val)
+			if err != nil {
+				return nil, err
+			}
+			newSlice[i] = newVal
+		}
+		return newSlice, nil
+
+	default:
+		return value, nil
+	}
+}
@@ -166,6 +166,7 @@ groups:
 	expected := Config{
 		LogLevel:      "info",
 		LogTimeFormat: "",
+		LogToStdout:   LogToStdoutProxy,
 		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
@@ -761,3 +761,299 @@ models:
 		})
 	}
 }
+
+func TestConfig_APIKeys_Invalid(t *testing.T) {
+	tests := []struct {
+		name        string
+		content     string
+		expectedErr string
+	}{
+		{
+			name:        "empty string",
+			content:     `apiKeys: [""]`,
+			expectedErr: "empty api key found in apiKeys",
+		},
+		{
+			name:        "blank spaces only",
+			content:     `apiKeys: ["   "]`,
+			expectedErr: "api key cannot contain spaces: `   `",
+		},
+		{
+			name:        "contains leading space",
+			content:     `apiKeys: [" key123"]`,
+			expectedErr: "api key cannot contain spaces: ` key123`",
+		},
+		{
+			name:        "contains trailing space",
+			content:     `apiKeys: ["key123 "]`,
+			expectedErr: "api key cannot contain spaces: `key123 `",
+		},
+		{
+			name:        "contains middle space",
+			content:     `apiKeys: ["key 123"]`,
+			expectedErr: "api key cannot contain spaces: `key 123`",
+		},
+		{
+			name:        "empty in list with valid keys",
+			content:     `apiKeys: ["valid-key", "", "another-key"]`,
+			expectedErr: "empty api key found in apiKeys",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			_, err := LoadConfigFromReader(strings.NewReader(tt.content))
+			if assert.Error(t, err) {
+				assert.Equal(t, tt.expectedErr, err.Error())
+			}
+		})
+	}
+}
+
+func TestConfig_APIKeys_EnvMacros(t *testing.T) {
+	t.Run("env substitution in apiKeys", func(t *testing.T) {
+		t.Setenv("TEST_API_KEY", "secret-key-123")
+
+		content := `apiKeys: ["${env.TEST_API_KEY}"]`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, []string{"secret-key-123"}, config.RequiredAPIKeys)
+	})
+
+	t.Run("multiple env substitutions in apiKeys", func(t *testing.T) {
+		t.Setenv("TEST_API_KEY_1", "key-one")
+		t.Setenv("TEST_API_KEY_2", "key-two")
+
+		content := `apiKeys: ["${env.TEST_API_KEY_1}", "${env.TEST_API_KEY_2}", "static-key"]`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, []string{"key-one", "key-two", "static-key"}, config.RequiredAPIKeys)
+	})
+
+	t.Run("missing env var in apiKeys", func(t *testing.T) {
+		content := `apiKeys: ["${env.NONEXISTENT_API_KEY}"]`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Error(t, err)
+		assert.Contains(t, err.Error(), "apiKeys[0]")
+		assert.Contains(t, err.Error(), "NONEXISTENT_API_KEY")
+	})
+
+	t.Run("env substitution results in empty key", func(t *testing.T) {
+		t.Setenv("TEST_EMPTY_KEY", "")
+
+		content := `apiKeys: ["${env.TEST_EMPTY_KEY}"]`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Error(t, err)
+		assert.Equal(t, "empty api key found in apiKeys", err.Error())
+	})
+}
+
+func TestConfig_EnvMacros(t *testing.T) {
+	t.Run("basic env substitution in cmd", func(t *testing.T) {
+		t.Setenv("TEST_MODEL_PATH", "/opt/models")
+
+		content := `
+models:
+  test:
+    cmd: "${env.TEST_MODEL_PATH}/llama-server"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "/opt/models/llama-server", config.Models["test"].Cmd)
+	})
+
+	t.Run("env substitution in multiple fields", func(t *testing.T) {
+		t.Setenv("TEST_HOST", "myserver")
+		t.Setenv("TEST_PORT", "9999")
+
+		content := `
+models:
+  test:
+    cmd: "server --host ${env.TEST_HOST}"
+    proxy: "http://${env.TEST_HOST}:${env.TEST_PORT}"
+    checkEndpoint: "http://${env.TEST_HOST}/health"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "server --host myserver", config.Models["test"].Cmd)
+		assert.Equal(t, "http://myserver:9999", config.Models["test"].Proxy)
+		assert.Equal(t, "http://myserver/health", config.Models["test"].CheckEndpoint)
+	})
+
+	t.Run("env in global macro value", func(t *testing.T) {
+		t.Setenv("TEST_BASE_PATH", "/usr/local")
+
+		content := `
+macros:
+  SERVER_PATH: "${env.TEST_BASE_PATH}/bin/server"
+models:
+  test:
+    cmd: "${SERVER_PATH} --port 8080"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "/usr/local/bin/server --port 8080", config.Models["test"].Cmd)
+	})
+
+	t.Run("env in model-level macro value", func(t *testing.T) {
+		t.Setenv("TEST_MODEL_DIR", "/models/llama")
+
+		content := `
+models:
+  test:
+    macros:
+      MODEL_FILE: "${env.TEST_MODEL_DIR}/model.gguf"
+    cmd: "server --model ${MODEL_FILE}"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "server --model /models/llama/model.gguf", config.Models["test"].Cmd)
+	})
+
+	t.Run("env in metadata", func(t *testing.T) {
+		t.Setenv("TEST_API_KEY", "secret123")
+
+		content := `
+models:
+  test:
+    cmd: "server"
+    proxy: "http://localhost:8080"
+    metadata:
+      api_key: "${env.TEST_API_KEY}"
+      nested:
+        key: "${env.TEST_API_KEY}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "secret123", config.Models["test"].Metadata["api_key"])
+		nested := config.Models["test"].Metadata["nested"].(map[string]any)
+		assert.Equal(t, "secret123", nested["key"])
+	})
+
+	t.Run("env in filters.stripParams", func(t *testing.T) {
+		t.Setenv("TEST_STRIP_PARAMS", "temperature,top_p")
+
+		content := `
+models:
+  test:
+    cmd: "server"
+    proxy: "http://localhost:8080"
+    filters:
+      stripParams: "${env.TEST_STRIP_PARAMS}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "temperature,top_p", config.Models["test"].Filters.StripParams)
+	})
+
+	t.Run("env in cmdStop", func(t *testing.T) {
+		t.Setenv("TEST_KILL_SIGNAL", "SIGTERM")
+
+		content := `
+models:
+  test:
+    cmd: "server --port ${PORT}"
+    cmdStop: "kill -${env.TEST_KILL_SIGNAL} ${PID}"
+    proxy: "http://localhost:${PORT}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Contains(t, config.Models["test"].CmdStop, "-SIGTERM")
+	})
+
+	t.Run("missing env var returns error", func(t *testing.T) {
+		content := `
+models:
+  test:
+    cmd: "${env.UNDEFINED_VAR_12345}/server"
+    proxy: "http://localhost:8080"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "UNDEFINED_VAR_12345")
+			assert.Contains(t, err.Error(), "not set")
+		}
+	})
+
+	t.Run("missing env var in global macro", func(t *testing.T) {
+		content := `
+macros:
+  PATH: "${env.UNDEFINED_GLOBAL_VAR}"
+models:
+  test:
+    cmd: "server"
+    proxy: "http://localhost:8080"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "UNDEFINED_GLOBAL_VAR")
+			assert.Contains(t, err.Error(), "not set")
+		}
+	})
+
+	t.Run("missing env var in model macro", func(t *testing.T) {
+		content := `
+models:
+  test:
+    macros:
+      MY_PATH: "${env.UNDEFINED_MODEL_VAR}"
+    cmd: "server"
+    proxy: "http://localhost:8080"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "UNDEFINED_MODEL_VAR")
+			assert.Contains(t, err.Error(), "not set")
+		}
+	})
+
+	t.Run("missing env var in metadata", func(t *testing.T) {
+		content := `
+models:
+  test:
+    cmd: "server"
+    proxy: "http://localhost:8080"
+    metadata:
+      key: "${env.UNDEFINED_META_VAR}"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "UNDEFINED_META_VAR")
+			assert.Contains(t, err.Error(), "not set")
+		}
+	})
+
+	t.Run("env combined with regular macros", func(t *testing.T) {
+		t.Setenv("TEST_ROOT", "/data")
+
+		content := `
+macros:
+  MODEL_BASE: "${env.TEST_ROOT}/models"
+models:
+  test:
+    cmd: "server --model ${MODEL_BASE}/${MODEL_ID}.gguf"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "server --model /data/models/test.gguf", config.Models["test"].Cmd)
+	})
+
+	t.Run("multiple env vars in same string", func(t *testing.T) {
+		t.Setenv("TEST_USER", "admin")
+		t.Setenv("TEST_PASS", "secret")
+
+		content := `
+models:
+  test:
+    cmd: "server --auth ${env.TEST_USER}:${env.TEST_PASS}"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "server --auth admin:secret", config.Models["test"].Cmd)
+	})
+}
@@ -158,6 +158,7 @@ groups:
 	expected := Config{
 		LogLevel:      "info",
 		LogTimeFormat: "",
+		LogToStdout:   LogToStdoutProxy,
 		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
@@ -0,0 +1,81 @@
+package config
+
+import (
+	"slices"
+	"sort"
+	"strings"
+)
+
+// ProtectedParams is a list of parameters that cannot be set or stripped via filters
+// These are protected to prevent breaking the proxy's ability to route requests correctly
+var ProtectedParams = []string{"model"}
+
+// Filters contains filter settings for modifying request parameters
+// Used by both models and peers
+type Filters struct {
+	// StripParams is a comma-separated list of parameters to remove from requests
+	// The "model" parameter can never be removed
+	StripParams string `yaml:"stripParams"`
+
+	// SetParams is a dictionary of parameters to set/override in requests
+	// Protected params (like "model") cannot be set
+	SetParams map[string]any `yaml:"setParams"`
+}
+
+// SanitizedStripParams returns a sorted list of parameters to strip,
+// with duplicates, empty strings, and protected params removed
+func (f Filters) SanitizedStripParams() []string {
+	if f.StripParams == "" {
+		return nil
+	}
+
+	params := strings.Split(f.StripParams, ",")
+	cleaned := make([]string, 0, len(params))
+	seen := make(map[string]bool)
+
+	for _, param := range params {
+		trimmed := strings.TrimSpace(param)
+		// Skip protected params, empty strings, and duplicates
+		if slices.Contains(ProtectedParams, trimmed) || trimmed == "" || seen[trimmed] {
+			continue
+		}
+		seen[trimmed] = true
+		cleaned = append(cleaned, trimmed)
+	}
+
+	if len(cleaned) == 0 {
+		return nil
+	}
+
+	slices.Sort(cleaned)
+	return cleaned
+}
+
+// SanitizedSetParams returns a copy of SetParams with protected params removed
+// and keys sorted for consistent iteration order
+func (f Filters) SanitizedSetParams() (map[string]any, []string) {
+	if len(f.SetParams) == 0 {
+		return nil, nil
+	}
+
+	result := make(map[string]any, len(f.SetParams))
+	keys := make([]string, 0, len(f.SetParams))
+
+	for key, value := range f.SetParams {
+		// Skip protected params
+		if slices.Contains(ProtectedParams, key) {
+			continue
+		}
+		result[key] = value
+		keys = append(keys, key)
+	}
+
+	// Sort keys for consistent ordering
+	sort.Strings(keys)
+
+	if len(result) == 0 {
+		return nil, nil
+	}
+
+	return result, keys
+}
@@ -0,0 +1,168 @@
+package config
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestFilters_SanitizedStripParams(t *testing.T) {
+	tests := []struct {
+		name        string
+		stripParams string
+		want        []string
+	}{
+		{
+			name:        "empty string",
+			stripParams: "",
+			want:        nil,
+		},
+		{
+			name:        "single param",
+			stripParams: "temperature",
+			want:        []string{"temperature"},
+		},
+		{
+			name:        "multiple params",
+			stripParams: "temperature, top_p, top_k",
+			want:        []string{"temperature", "top_k", "top_p"}, // sorted
+		},
+		{
+			name:        "model param filtered",
+			stripParams: "model, temperature, top_p",
+			want:        []string{"temperature", "top_p"},
+		},
+		{
+			name:        "only model param",
+			stripParams: "model",
+			want:        nil,
+		},
+		{
+			name:        "duplicates removed",
+			stripParams: "temperature, top_p, temperature",
+			want:        []string{"temperature", "top_p"},
+		},
+		{
+			name:        "extra whitespace",
+			stripParams: "  temperature  ,  top_p  ",
+			want:        []string{"temperature", "top_p"},
+		},
+		{
+			name:        "empty values filtered",
+			stripParams: "temperature,,top_p,",
+			want:        []string{"temperature", "top_p"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			f := Filters{StripParams: tt.stripParams}
+			got := f.SanitizedStripParams()
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func TestFilters_SanitizedSetParams(t *testing.T) {
+	tests := []struct {
+		name       string
+		setParams  map[string]any
+		wantParams map[string]any
+		wantKeys   []string
+	}{
+		{
+			name:       "empty setParams",
+			setParams:  nil,
+			wantParams: nil,
+			wantKeys:   nil,
+		},
+		{
+			name:       "empty map",
+			setParams:  map[string]any{},
+			wantParams: nil,
+			wantKeys:   nil,
+		},
+		{
+			name: "normal params",
+			setParams: map[string]any{
+				"temperature": 0.7,
+				"top_p":       0.9,
+			},
+			wantParams: map[string]any{
+				"temperature": 0.7,
+				"top_p":       0.9,
+			},
+			wantKeys: []string{"temperature", "top_p"},
+		},
+		{
+			name: "protected model param filtered",
+			setParams: map[string]any{
+				"model":       "should-be-filtered",
+				"temperature": 0.7,
+			},
+			wantParams: map[string]any{
+				"temperature": 0.7,
+			},
+			wantKeys: []string{"temperature"},
+		},
+		{
+			name: "only protected param",
+			setParams: map[string]any{
+				"model": "should-be-filtered",
+			},
+			wantParams: nil,
+			wantKeys:   nil,
+		},
+		{
+			name: "complex nested values",
+			setParams: map[string]any{
+				"provider": map[string]any{
+					"data_collection": "deny",
+					"allow_fallbacks": false,
+				},
+				"transforms": []string{"middle-out"},
+			},
+			wantParams: map[string]any{
+				"provider": map[string]any{
+					"data_collection": "deny",
+					"allow_fallbacks": false,
+				},
+				"transforms": []string{"middle-out"},
+			},
+			wantKeys: []string{"provider", "transforms"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			f := Filters{SetParams: tt.setParams}
+			gotParams, gotKeys := f.SanitizedSetParams()
+
+			assert.Equal(t, len(tt.wantKeys), len(gotKeys), "keys length mismatch")
+			for i, key := range gotKeys {
+				assert.Equal(t, tt.wantKeys[i], key, "key mismatch at %d", i)
+			}
+
+			if tt.wantParams == nil {
+				assert.Nil(t, gotParams, "expected nil params")
+				return
+			}
+
+			assert.Equal(t, len(tt.wantParams), len(gotParams), "params length mismatch")
+			for key, wantValue := range tt.wantParams {
+				gotValue, exists := gotParams[key]
+				assert.True(t, exists, "missing key: %s", key)
+				// Simple comparison for basic types
+				switch v := wantValue.(type) {
+				case string, int, float64, bool:
+					assert.Equal(t, v, gotValue, "value mismatch for key %s", key)
+				}
+			}
+		})
+	}
+}
+
+func TestProtectedParams(t *testing.T) {
+	// Verify that "model" is protected
+	assert.Contains(t, ProtectedParams, "model")
+}
@@ -3,8 +3,6 @@ package config
 import (
 	"errors"
 	"runtime"
-	"slices"
-	"strings"
 )

 type ModelConfig struct {
@@ -74,16 +72,15 @@ func (m *ModelConfig) SanitizedCommand() ([]string, error) {
 	return SanitizeCommand(m.Cmd)
 }

-// ModelFilters see issue #174
+// ModelFilters embeds Filters and adds legacy support for strip_params field
+// See issue #174
 type ModelFilters struct {
-	StripParams string `yaml:"stripParams"`
+	Filters `yaml:",inline"`
 }

 func (m *ModelFilters) UnmarshalYAML(unmarshal func(interface{}) error) error {
 	type rawModelFilters ModelFilters
-	defaults := rawModelFilters{
-		StripParams: "",
-	}
+	defaults := rawModelFilters{}

 	if err := unmarshal(&defaults); err != nil {
 		return err
@@ -104,25 +101,8 @@ func (m *ModelFilters) UnmarshalYAML(unmarshal func(interface{}) error) error {
 	return nil
 }

+// SanitizedStripParams wraps Filters.SanitizedStripParams for backwards compatibility
+// Returns ([]string, error) to match existing API
 func (f ModelFilters) SanitizedStripParams() ([]string, error) {
-	if f.StripParams == "" {
-		return nil, nil
-	}
-
-	params := strings.Split(f.StripParams, ",")
-	cleaned := make([]string, 0, len(params))
-	seen := make(map[string]bool)
-
-	for _, param := range params {
-		trimmed := strings.TrimSpace(param)
-		if trimmed == "model" || trimmed == "" || seen[trimmed] {
-			continue
-		}
-		seen[trimmed] = true
-		cleaned = append(cleaned, trimmed)
-	}
-
-	// sort cleaned
-	slices.Sort(cleaned)
-	return cleaned, nil
+	return f.Filters.SanitizedStripParams(), nil
 }
@@ -72,3 +72,35 @@ models:
 		assert.True(t, *config.Models["model2"].SendLoadingState)
 	}
 }
+
+func TestConfig_ModelFiltersWithSetParams(t *testing.T) {
+	content := `
+models:
+  model1:
+    cmd: path/to/cmd --port ${PORT}
+    filters:
+      stripParams: "top_k"
+      setParams:
+        temperature: 0.7
+        top_p: 0.9
+        stop:
+          - "<|end|>"
+          - "<|stop|>"
+`
+	config, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.NoError(t, err)
+
+	modelConfig := config.Models["model1"]
+
+	// Check stripParams
+	stripParams, err := modelConfig.Filters.SanitizedStripParams()
+	assert.NoError(t, err)
+	assert.Equal(t, []string{"top_k"}, stripParams)
+
+	// Check setParams
+	setParams, keys := modelConfig.Filters.SanitizedSetParams()
+	assert.NotNil(t, setParams)
+	assert.Equal(t, []string{"stop", "temperature", "top_p"}, keys)
+	assert.Equal(t, 0.7, setParams["temperature"])
+	assert.Equal(t, 0.9, setParams["top_p"])
+}
@@ -0,0 +1,49 @@
+package config
+
+import (
+	"fmt"
+	"net/url"
+)
+
+type PeerDictionaryConfig map[string]PeerConfig
+type PeerConfig struct {
+	Proxy    string   `yaml:"proxy"`
+	ProxyURL *url.URL `yaml:"-"`
+	ApiKey   string   `yaml:"apiKey"`
+	Models   []string `yaml:"models"`
+	Filters  Filters  `yaml:"filters"`
+}
+
+func (c *PeerConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	type rawPeerConfig PeerConfig
+	defaults := rawPeerConfig{
+		Proxy:   "",
+		ApiKey:  "",
+		Models:  []string{},
+		Filters: Filters{},
+	}
+
+	if err := unmarshal(&defaults); err != nil {
+		return err
+	}
+
+	// Validate proxy is not empty
+	if defaults.Proxy == "" {
+		return fmt.Errorf("proxy is required")
+	}
+
+	// Validate proxy is a valid URL and store the parsed value
+	parsedURL, err := url.Parse(defaults.Proxy)
+	if err != nil {
+		return fmt.Errorf("invalid peer proxy URL (%s): %w", defaults.Proxy, err)
+	}
+	defaults.ProxyURL = parsedURL
+
+	// Validate models is not empty
+	if len(defaults.Models) == 0 {
+		return fmt.Errorf("peer models can not be empty")
+	}
+
+	*c = PeerConfig(defaults)
+	return nil
+}
@@ -0,0 +1,209 @@
+package config
+
+import (
+	"testing"
+
+	"gopkg.in/yaml.v3"
+)
+
+func TestPeerConfig_UnmarshalYAML(t *testing.T) {
+	tests := []struct {
+		name    string
+		yaml    string
+		wantErr string
+	}{
+		{
+			name: "valid config",
+			yaml: `
+proxy: http://192.168.1.23
+models:
+  - model_a
+  - model_b
+`,
+			wantErr: "",
+		},
+		{
+			name: "valid config with apiKey",
+			yaml: `
+proxy: https://openrouter.ai/api
+apiKey: sk-test-key
+models:
+  - meta-llama/llama-3.1-8b-instruct
+`,
+			wantErr: "",
+		},
+		{
+			name: "missing proxy",
+			yaml: `
+models:
+  - model_a
+`,
+			wantErr: "proxy is required",
+		},
+		{
+			name: "empty proxy",
+			yaml: `
+proxy: ""
+models:
+  - model_a
+`,
+			wantErr: "proxy is required",
+		},
+		{
+			name: "invalid proxy URL",
+			yaml: `
+proxy: "://invalid"
+models:
+  - model_a
+`,
+			wantErr: "invalid peer proxy URL",
+		},
+		{
+			name: "missing models",
+			yaml: `
+proxy: http://localhost:8080
+`,
+			wantErr: "peer models can not be empty",
+		},
+		{
+			name: "empty models",
+			yaml: `
+proxy: http://localhost:8080
+models: []
+`,
+			wantErr: "peer models can not be empty",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			var config PeerConfig
+			err := yaml.Unmarshal([]byte(tt.yaml), &config)
+
+			if tt.wantErr == "" {
+				if err != nil {
+					t.Errorf("unexpected error: %v", err)
+				}
+			} else {
+				if err == nil {
+					t.Errorf("expected error containing %q, got nil", tt.wantErr)
+				} else if !contains(err.Error(), tt.wantErr) {
+					t.Errorf("expected error containing %q, got %q", tt.wantErr, err.Error())
+				}
+			}
+		})
+	}
+}
+
+func TestPeerConfig_ProxyURL(t *testing.T) {
+	yamlData := `
+proxy: http://192.168.1.23:8080/api
+apiKey: sk-test
+models:
+  - model_a
+`
+	var config PeerConfig
+	err := yaml.Unmarshal([]byte(yamlData), &config)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+
+	if config.ProxyURL == nil {
+		t.Fatal("ProxyURL should not be nil")
+	}
+
+	if config.ProxyURL.Host != "192.168.1.23:8080" {
+		t.Errorf("expected host %q, got %q", "192.168.1.23:8080", config.ProxyURL.Host)
+	}
+
+	if config.ProxyURL.Scheme != "http" {
+		t.Errorf("expected scheme %q, got %q", "http", config.ProxyURL.Scheme)
+	}
+
+	if config.ProxyURL.Path != "/api" {
+		t.Errorf("expected path %q, got %q", "/api", config.ProxyURL.Path)
+	}
+}
+
+func contains(s, substr string) bool {
+	return len(s) >= len(substr) && searchSubstring(s, substr)
+}
+
+func searchSubstring(s, substr string) bool {
+	for i := 0; i <= len(s)-len(substr); i++ {
+		if s[i:i+len(substr)] == substr {
+			return true
+		}
+	}
+	return false
+}
+
+func TestPeerConfig_WithFilters(t *testing.T) {
+	yamlData := `
+proxy: https://openrouter.ai/api
+apiKey: sk-test
+models:
+  - model_a
+filters:
+  setParams:
+    temperature: 0.7
+    provider:
+      data_collection: deny
+`
+	var config PeerConfig
+	err := yaml.Unmarshal([]byte(yamlData), &config)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+
+	if config.Filters.SetParams == nil {
+		t.Fatal("Filters.SetParams should not be nil")
+	}
+
+	if config.Filters.SetParams["temperature"] != 0.7 {
+		t.Errorf("expected temperature 0.7, got %v", config.Filters.SetParams["temperature"])
+	}
+
+	provider, ok := config.Filters.SetParams["provider"].(map[string]any)
+	if !ok {
+		t.Fatal("provider should be a map")
+	}
+	if provider["data_collection"] != "deny" {
+		t.Errorf("expected data_collection deny, got %v", provider["data_collection"])
+	}
+}
+
+func TestPeerConfig_WithBothFilters(t *testing.T) {
+	yamlData := `
+proxy: https://openrouter.ai/api
+apiKey: sk-test
+models:
+  - model_a
+filters:
+  stripParams: "temperature, top_p"
+  setParams:
+    max_tokens: 1000
+`
+	var config PeerConfig
+	err := yaml.Unmarshal([]byte(yamlData), &config)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+
+	// Check stripParams
+	stripParams := config.Filters.SanitizedStripParams()
+	if len(stripParams) != 2 {
+		t.Errorf("expected 2 strip params, got %d", len(stripParams))
+	}
+	if stripParams[0] != "temperature" || stripParams[1] != "top_p" {
+		t.Errorf("unexpected strip params: %v", stripParams)
+	}
+
+	// Check setParams
+	if config.Filters.SetParams == nil {
+		t.Fatal("Filters.SetParams should not be nil")
+	}
+	if config.Filters.SetParams["max_tokens"] != 1000 {
+		t.Errorf("expected max_tokens 1000, got %v", config.Filters.SetParams["max_tokens"])
+	}
+}
@@ -2,6 +2,8 @@ package proxy

 import (
 	"bytes"
+	"compress/flate"
+	"compress/gzip"
 	"encoding/json"
 	"fmt"
 	"io"
@@ -96,6 +98,12 @@ func (mp *metricsMonitor) wrapHandler(
 	next func(modelID string, w http.ResponseWriter, r *http.Request) error,
 ) error {
 	recorder := newBodyCopier(writer)
+
+	// Filter Accept-Encoding to only include encodings we can decompress for metrics
+	if ae := request.Header.Get("Accept-Encoding"); ae != "" {
+		request.Header.Set("Accept-Encoding", filterAcceptEncoding(ae))
+	}
+
 	if err := next(modelID, recorder, request); err != nil {
 		return err
 	}
@@ -108,17 +116,36 @@ func (mp *metricsMonitor) wrapHandler(
 		return nil
 	}

+	// Initialize default metrics - these will always be recorded
+	tm := TokenMetrics{
+		Timestamp:  time.Now(),
+		Model:      modelID,
+		DurationMs: int(time.Since(recorder.StartTime()).Milliseconds()),
+	}
+
 	body := recorder.body.Bytes()
 	if len(body) == 0 {
-		mp.logger.Warn("metrics skipped, empty body")
+		mp.logger.Warn("metrics: empty body, recording minimal metrics")
+		mp.addMetrics(tm)
 		return nil
 	}

-	if strings.Contains(recorder.Header().Get("Content-Type"), "text/event-stream") {
-		if tm, err := processStreamingResponse(modelID, recorder.StartTime(), body); err != nil {
-			mp.logger.Warnf("error processing streaming response: %v, path=%s", err, request.URL.Path)
-		} else {
+	// Decompress if needed
+	if encoding := recorder.Header().Get("Content-Encoding"); encoding != "" {
+		var err error
+		body, err = decompressBody(body, encoding)
+		if err != nil {
+			mp.logger.Warnf("metrics: decompression failed: %v, path=%s, recording minimal metrics", err, request.URL.Path)
 			mp.addMetrics(tm)
+			return nil
+		}
+	}
+
+	if strings.Contains(recorder.Header().Get("Content-Type"), "text/event-stream") {
+		if parsed, err := processStreamingResponse(modelID, recorder.StartTime(), body); err != nil {
+			mp.logger.Warnf("error processing streaming response: %v, path=%s, recording minimal metrics", err, request.URL.Path)
+		} else {
+			tm = parsed
 		}
 	} else {
 		if gjson.ValidBytes(body) {
@@ -127,18 +154,18 @@ func (mp *metricsMonitor) wrapHandler(
 			timings := parsed.Get("timings")

 			if usage.Exists() || timings.Exists() {
-				if tm, err := parseMetrics(modelID, recorder.StartTime(), usage, timings); err != nil {
-					mp.logger.Warnf("error parsing metrics: %v, path=%s", err, request.URL.Path)
+				if parsedMetrics, err := parseMetrics(modelID, recorder.StartTime(), usage, timings); err != nil {
+					mp.logger.Warnf("error parsing metrics: %v, path=%s, recording minimal metrics", err, request.URL.Path)
 				} else {
-					mp.addMetrics(tm)
+					tm = parsedMetrics
 				}
 			}
-
 		} else {
-			mp.logger.Warnf("metrics skipped, invalid JSON in response body path=%s", request.URL.Path)
+			mp.logger.Warnf("metrics: invalid JSON in response body path=%s, recording minimal metrics", request.URL.Path)
 		}
 	}

+	mp.addMetrics(tm)
 	return nil
 }

@@ -251,6 +278,25 @@ func parseMetrics(modelID string, start time.Time, usage, timings gjson.Result)
 	}, nil
 }

+// decompressBody decompresses the body based on Content-Encoding header
+func decompressBody(body []byte, encoding string) ([]byte, error) {
+	switch strings.ToLower(strings.TrimSpace(encoding)) {
+	case "gzip":
+		reader, err := gzip.NewReader(bytes.NewReader(body))
+		if err != nil {
+			return nil, err
+		}
+		defer reader.Close()
+		return io.ReadAll(reader)
+	case "deflate":
+		reader := flate.NewReader(bytes.NewReader(body))
+		defer reader.Close()
+		return io.ReadAll(reader)
+	default:
+		return body, nil // Return as-is for unknown/no encoding
+	}
+}
+
 // responseBodyCopier records the response body and writes to the original response writer
 // while also capturing it in a buffer for later processing
 type responseBodyCopier struct {
@@ -289,3 +335,25 @@ func (w *responseBodyCopier) Header() http.Header {
 func (w *responseBodyCopier) StartTime() time.Time {
 	return w.start
 }
+
+// filterAcceptEncoding filters the Accept-Encoding header to only include
+// encodings we can decompress (gzip, deflate). This respects the client's
+// preferences while ensuring we can parse response bodies for metrics.
+func filterAcceptEncoding(acceptEncoding string) string {
+	if acceptEncoding == "" {
+		return ""
+	}
+
+	supported := map[string]bool{"gzip": true, "deflate": true}
+	var filtered []string
+
+	for _, part := range strings.Split(acceptEncoding, ",") {
+		// Parse encoding and optional quality value (e.g., "gzip;q=1.0")
+		encoding := strings.TrimSpace(strings.Split(part, ";")[0])
+		if supported[strings.ToLower(encoding)] {
+			filtered = append(filtered, strings.TrimSpace(part))
+		}
+	}
+
+	return strings.Join(filtered, ", ")
+}
@@ -1,6 +1,9 @@
 package proxy

 import (
+	"bytes"
+	"compress/flate"
+	"compress/gzip"
 	"encoding/json"
 	"net/http"
 	"net/http/httptest"
@@ -291,7 +294,7 @@ data: [DONE]
 		assert.Equal(t, 0, len(metrics))
 	})

-	t.Run("empty response body does not record metrics", func(t *testing.T) {
+	t.Run("empty response body records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)

 		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
@@ -307,10 +310,13 @@ data: [DONE]
 		assert.NoError(t, err)

 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})

-	t.Run("invalid JSON does not record metrics", func(t *testing.T) {
+	t.Run("invalid JSON records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)

 		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
@@ -328,7 +334,10 @@ data: [DONE]
 		assert.NoError(t, err) // Errors after response is sent are logged, not returned

 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})

 	t.Run("next handler error is propagated", func(t *testing.T) {
@@ -350,7 +359,7 @@ data: [DONE]
 		assert.Equal(t, 0, len(metrics))
 	})

-	t.Run("response without usage or timings does not record metrics", func(t *testing.T) {
+	t.Run("response without usage or timings records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)

 		responseBody := `{"result": "ok"}`
@@ -367,10 +376,13 @@ data: [DONE]
 		ginCtx, _ := gin.CreateTestContext(rec)

 		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
-		assert.NoError(t, err) // Errors after response is sent are logged, not returned
+		assert.NoError(t, err)

 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})
 }

@@ -598,7 +610,7 @@ data: [DONE]
 		assert.Equal(t, 50, metrics[0].OutputTokens)
 	})

-	t.Run("handles streaming with no valid JSON", func(t *testing.T) {
+	t.Run("handles streaming with no valid JSON records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)

 		responseBody := `data: not json
@@ -619,13 +631,16 @@ data: [DONE]
 		ginCtx, _ := gin.CreateTestContext(rec)

 		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
-		assert.NoError(t, err) // Errors after response is sent are logged, not returned
+		assert.NoError(t, err)

 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})

-	t.Run("handles empty streaming response", func(t *testing.T) {
+	t.Run("handles empty streaming response records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)

 		responseBody := ``
@@ -642,11 +657,13 @@ data: [DONE]
 		ginCtx, _ := gin.CreateTestContext(rec)

 		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
-		// Empty body should not trigger WrapHandler processing
 		assert.NoError(t, err)

 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})
 }

@@ -691,3 +708,127 @@ func BenchmarkMetricsMonitor_AddMetrics_SmallBuffer(b *testing.B) {
 		mm.addMetrics(metric)
 	}
 }
+
+func TestMetricsMonitor_WrapHandler_Compression(t *testing.T) {
+	t.Run("gzip encoded response", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{"usage": {"prompt_tokens": 100, "completion_tokens": 50}}`
+
+		// Compress with gzip
+		var buf bytes.Buffer
+		gzWriter := gzip.NewWriter(&buf)
+		gzWriter.Write([]byte(responseBody))
+		gzWriter.Close()
+		compressedBody := buf.Bytes()
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.Header().Set("Content-Encoding", "gzip")
+			w.WriteHeader(http.StatusOK)
+			w.Write(compressedBody)
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 100, metrics[0].InputTokens)
+		assert.Equal(t, 50, metrics[0].OutputTokens)
+	})
+
+	t.Run("deflate encoded response", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{"usage": {"prompt_tokens": 200, "completion_tokens": 75}}`
+
+		// Compress with deflate
+		var buf bytes.Buffer
+		flateWriter, _ := flate.NewWriter(&buf, flate.DefaultCompression)
+		flateWriter.Write([]byte(responseBody))
+		flateWriter.Close()
+		compressedBody := buf.Bytes()
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.Header().Set("Content-Encoding", "deflate")
+			w.WriteHeader(http.StatusOK)
+			w.Write(compressedBody)
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 200, metrics[0].InputTokens)
+		assert.Equal(t, 75, metrics[0].OutputTokens)
+	})
+
+	t.Run("invalid gzip data records minimal metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		// Invalid compressed data
+		invalidData := []byte("this is not gzip data")
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.Header().Set("Content-Encoding", "gzip")
+			w.WriteHeader(http.StatusOK)
+			w.Write(invalidData)
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err) // Should not return error, just log warning
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
+	})
+
+	t.Run("unknown encoding treated as uncompressed", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{"usage": {"prompt_tokens": 300, "completion_tokens": 100}}`
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.Header().Set("Content-Encoding", "unknown-encoding")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(responseBody))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, 300, metrics[0].InputTokens)
+		assert.Equal(t, 100, metrics[0].OutputTokens)
+	})
+}
@@ -0,0 +1,141 @@
+package proxy
+
+import (
+	"fmt"
+	"net"
+	"net/http"
+	"net/http/httputil"
+	"runtime"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/mostlygeek/llama-swap/proxy/config"
+)
+
+type peerProxyMember struct {
+	peerID       string
+	reverseProxy *httputil.ReverseProxy
+	apiKey       string
+}
+
+type PeerProxy struct {
+	peers    config.PeerDictionaryConfig
+	proxyMap map[string]*peerProxyMember
+}
+
+func NewPeerProxy(peers config.PeerDictionaryConfig, proxyLogger *LogMonitor) (*PeerProxy, error) {
+	proxyMap := make(map[string]*peerProxyMember)
+
+	// Sort peer IDs for consistent iteration order
+	peerIDs := make([]string, 0, len(peers))
+	for peerID := range peers {
+		peerIDs = append(peerIDs, peerID)
+	}
+	sort.Strings(peerIDs)
+
+	// Create a shared transport with reasonable timeouts for peer connections
+	// these can be tuned with feedback later
+	peerTransport := &http.Transport{
+		DialContext: (&net.Dialer{
+			Timeout:   30 * time.Second, // Connection timeout
+			KeepAlive: 30 * time.Second,
+		}).DialContext,
+		TLSHandshakeTimeout:   10 * time.Second,
+		ResponseHeaderTimeout: 60 * time.Second, // Time to wait for response headers
+		ExpectContinueTimeout: 1 * time.Second,
+		MaxIdleConns:          100,
+		MaxIdleConnsPerHost:   10,
+		IdleConnTimeout:       90 * time.Second,
+	}
+
+	for _, peerID := range peerIDs {
+		peer := peers[peerID]
+		// Create reverse proxy for this peer
+		reverseProxy := httputil.NewSingleHostReverseProxy(peer.ProxyURL)
+		reverseProxy.Transport = peerTransport
+
+		// Wrap Director to set Host header for remote hosts (not localhost)
+		originalDirector := reverseProxy.Director
+		reverseProxy.Director = func(req *http.Request) {
+			originalDirector(req)
+			// Ensure Host header matches target URL for remote proxying
+			req.Host = req.URL.Host
+		}
+
+		reverseProxy.ModifyResponse = func(resp *http.Response) error {
+			if strings.Contains(strings.ToLower(resp.Header.Get("Content-Type")), "text/event-stream") {
+				resp.Header.Set("X-Accel-Buffering", "no")
+			}
+			return nil
+		}
+
+		reverseProxy.ErrorHandler = func(w http.ResponseWriter, r *http.Request, err error) {
+			proxyLogger.Warnf("peer %s: proxy error: %v", peerID, err)
+			errMsg := fmt.Sprintf("peer proxy error: %v", err)
+			if runtime.GOOS == "darwin" && strings.Contains(err.Error(), "connect: no route to host") {
+				errMsg += " (hint: on macOS, check System Settings > Privacy & Security > Local Network permissions)"
+			}
+			http.Error(w, errMsg, http.StatusBadGateway)
+		}
+
+		pp := &peerProxyMember{
+			peerID:       peerID,
+			reverseProxy: reverseProxy,
+			apiKey:       peer.ApiKey,
+		}
+
+		// Map each model to this peer's proxy
+		for _, modelID := range peer.Models {
+			if _, found := proxyMap[modelID]; found {
+				proxyLogger.Warnf("peer %s: model %s already mapped to another peer, skipping", peerID, modelID)
+				continue
+			}
+			proxyMap[modelID] = pp
+		}
+	}
+
+	return &PeerProxy{
+		peers:    peers,
+		proxyMap: proxyMap,
+	}, nil
+}
+
+func (p *PeerProxy) HasPeerModel(modelID string) bool {
+	_, found := p.proxyMap[modelID]
+	return found
+}
+
+// GetPeerFilters returns the filters for a peer model, or empty filters if not found
+func (p *PeerProxy) GetPeerFilters(modelID string) config.Filters {
+	pp, found := p.proxyMap[modelID]
+	if !found {
+		return config.Filters{}
+	}
+	// Get the peer config using the peerID
+	peer, found := p.peers[pp.peerID]
+	if !found {
+		return config.Filters{}
+	}
+	return peer.Filters
+}
+
+func (p *PeerProxy) ListPeers() config.PeerDictionaryConfig {
+	return p.peers
+}
+
+func (p *PeerProxy) ProxyRequest(model_id string, writer http.ResponseWriter, request *http.Request) error {
+	pp, found := p.proxyMap[model_id]
+	if !found {
+		return fmt.Errorf("no peer proxy found for model %s", model_id)
+	}
+
+	// Inject API key if configured for this peer
+	if pp.apiKey != "" {
+		request.Header.Set("Authorization", "Bearer "+pp.apiKey)
+		request.Header.Set("x-api-key", pp.apiKey)
+	}
+
+	pp.reverseProxy.ServeHTTP(writer, request)
+	return nil
+}
@@ -0,0 +1,268 @@
+package proxy
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"strings"
+	"testing"
+
+	"github.com/mostlygeek/llama-swap/proxy/config"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestNewPeerProxy_EmptyPeers(t *testing.T) {
+	peers := config.PeerDictionaryConfig{}
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+	assert.NotNil(t, pm)
+	assert.Empty(t, pm.proxyMap)
+}
+
+func TestNewPeerProxy_SinglePeer(t *testing.T) {
+	proxyURL, _ := url.Parse("http://peer1.example.com:8080")
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    "http://peer1.example.com:8080",
+			ProxyURL: proxyURL,
+			ApiKey:   "test-key",
+			Models:   []string{"model-a", "model-b"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+	assert.Len(t, pm.proxyMap, 2)
+	assert.True(t, pm.HasPeerModel("model-a"))
+	assert.True(t, pm.HasPeerModel("model-b"))
+	assert.False(t, pm.HasPeerModel("model-c"))
+}
+
+func TestNewPeerProxy_MultiplePeers(t *testing.T) {
+	proxyURL1, _ := url.Parse("http://peer1.example.com:8080")
+	proxyURL2, _ := url.Parse("http://peer2.example.com:8080")
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    "http://peer1.example.com:8080",
+			ProxyURL: proxyURL1,
+			Models:   []string{"model-a", "model-b"},
+		},
+		"peer2": config.PeerConfig{
+			Proxy:    "http://peer2.example.com:8080",
+			ProxyURL: proxyURL2,
+			Models:   []string{"model-c", "model-d"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+	assert.Len(t, pm.proxyMap, 4)
+	assert.True(t, pm.HasPeerModel("model-a"))
+	assert.True(t, pm.HasPeerModel("model-b"))
+	assert.True(t, pm.HasPeerModel("model-c"))
+	assert.True(t, pm.HasPeerModel("model-d"))
+}
+
+func TestNewPeerProxy_DuplicateModelWarning(t *testing.T) {
+	// When the same model is in multiple peers, only the first (lexicographically by peer ID)
+	// should be mapped, and a warning should be logged
+	proxyURL1, _ := url.Parse("http://peer1.example.com:8080")
+	proxyURL2, _ := url.Parse("http://peer2.example.com:8080")
+	peers := config.PeerDictionaryConfig{
+		"alpha-peer": config.PeerConfig{
+			Proxy:    "http://peer1.example.com:8080",
+			ProxyURL: proxyURL1,
+			Models:   []string{"duplicate-model"},
+		},
+		"beta-peer": config.PeerConfig{
+			Proxy:    "http://peer2.example.com:8080",
+			ProxyURL: proxyURL2,
+			Models:   []string{"duplicate-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+	// Should only have one entry for the duplicate model
+	assert.Len(t, pm.proxyMap, 1)
+	assert.True(t, pm.HasPeerModel("duplicate-model"))
+}
+
+func TestHasPeerModel(t *testing.T) {
+	proxyURL, _ := url.Parse("http://peer1.example.com:8080")
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    "http://peer1.example.com:8080",
+			ProxyURL: proxyURL,
+			Models:   []string{"existing-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	assert.True(t, pm.HasPeerModel("existing-model"))
+	assert.False(t, pm.HasPeerModel("non-existing-model"))
+}
+
+func TestProxyRequest_ModelNotFound(t *testing.T) {
+	peers := config.PeerDictionaryConfig{}
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("non-existing-model", w, req)
+	assert.Error(t, err)
+	assert.Contains(t, err.Error(), "no peer proxy found for model non-existing-model")
+}
+
+func TestProxyRequest_Success(t *testing.T) {
+	// Create a test server to act as the peer
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusOK)
+		w.Write([]byte("response from peer"))
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	assert.Equal(t, http.StatusOK, w.Code)
+	assert.Equal(t, "response from peer", w.Body.String())
+}
+
+func TestProxyRequest_ApiKeyInjection(t *testing.T) {
+	// Create a test server that checks for the Authorization header
+	var receivedAuthHeader string
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		receivedAuthHeader = r.Header.Get("Authorization")
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			ApiKey:   "secret-api-key",
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	assert.Equal(t, "Bearer secret-api-key", receivedAuthHeader)
+}
+
+func TestProxyRequest_NoApiKey(t *testing.T) {
+	// Create a test server that checks for the Authorization header
+	var receivedAuthHeader string
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		receivedAuthHeader = r.Header.Get("Authorization")
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			ApiKey:   "", // No API key
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	assert.Empty(t, receivedAuthHeader)
+}
+
+func TestProxyRequest_HostHeaderSet(t *testing.T) {
+	// Create a test server that checks the Host header
+	var receivedHost string
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		receivedHost = r.Host
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	// The Host header should be set to the target URL's host
+	assert.True(t, strings.HasPrefix(receivedHost, "127.0.0.1:"))
+}
+
+func TestProxyRequest_SSEHeaderModification(t *testing.T) {
+	// Create a test server that returns SSE content type
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "text/event-stream")
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	// The X-Accel-Buffering header should be set to "no" for SSE
+	assert.Equal(t, "no", w.Header().Get("X-Accel-Buffering"))
+}
@@ -395,6 +395,10 @@ func TestProcess_StopImmediately(t *testing.T) {
 // Test that SIGKILL is sent when gracefulStopTimeout is reached and properly terminates
 // the upstream command
 func TestProcess_ForceStopWithKill(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping slow test")
+	}
+
 	if runtime.GOOS == "windows" {
 		t.Skip("skipping SIGTERM test on Windows ")
 	}
@@ -49,6 +49,10 @@ func TestProcessGroup_HasMember(t *testing.T) {
 // TestProcessGroup_ProxyRequestSwapIsTrueParallel tests that when swap is true
 // and multiple requests are made in parallel, only one process is running at a time.
 func TestProcessGroup_ProxyRequestSwapIsTrueParallel(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping slow test")
+	}
+
 	var processGroupTestConfig = config.AddDefaultGroupToConfig(config.Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]config.ModelConfig{
@@ -3,6 +3,7 @@ package proxy
 import (
 	"bytes"
 	"context"
+	"encoding/base64"
 	"fmt"
 	"io"
 	"mime/multipart"
@@ -50,19 +51,42 @@ type ProxyManager struct {
 	buildDate string
 	commit    string
 	version   string
+
+	// peer proxy see: #296, #433
+	peerProxy *PeerProxy
 }

-func New(config config.Config) *ProxyManager {
+func New(proxyConfig config.Config) *ProxyManager {
 	// set up loggers
-	stdoutLogger := NewLogMonitorWriter(os.Stdout)
-	upstreamLogger := NewLogMonitorWriter(stdoutLogger)
-	proxyLogger := NewLogMonitorWriter(stdoutLogger)

-	if config.LogRequests {
+	var muxLogger, upstreamLogger, proxyLogger *LogMonitor
+	switch proxyConfig.LogToStdout {
+	case config.LogToStdoutNone:
+		muxLogger = NewLogMonitorWriter(io.Discard)
+		upstreamLogger = NewLogMonitorWriter(io.Discard)
+		proxyLogger = NewLogMonitorWriter(io.Discard)
+	case config.LogToStdoutBoth:
+		muxLogger = NewLogMonitorWriter(os.Stdout)
+		upstreamLogger = NewLogMonitorWriter(muxLogger)
+		proxyLogger = NewLogMonitorWriter(muxLogger)
+	case config.LogToStdoutUpstream:
+		muxLogger = NewLogMonitorWriter(os.Stdout)
+		upstreamLogger = NewLogMonitorWriter(muxLogger)
+		proxyLogger = NewLogMonitorWriter(io.Discard)
+	default:
+		// same as config.LogToStdoutProxy
+		// helpful because some old tests create a config.Config directly and it
+		// may not have LogToStdout set explicitly
+		muxLogger = NewLogMonitorWriter(os.Stdout)
+		upstreamLogger = NewLogMonitorWriter(io.Discard)
+		proxyLogger = NewLogMonitorWriter(muxLogger)
+	}
+
+	if proxyConfig.LogRequests {
 		proxyLogger.Warn("LogRequests configuration is deprecated. Use logLevel instead.")
 	}

-	switch strings.ToLower(strings.TrimSpace(config.LogLevel)) {
+	switch strings.ToLower(strings.TrimSpace(proxyConfig.LogLevel)) {
 	case "debug":
 		proxyLogger.SetLogLevel(LevelDebug)
 		upstreamLogger.SetLogLevel(LevelDebug)
@@ -99,7 +123,7 @@ func New(config config.Config) *ProxyManager {
 		"stampnano":   time.StampNano,
 	}

-	if timeFormat, ok := timeFormats[strings.ToLower(strings.TrimSpace(config.LogTimeFormat))]; ok {
+	if timeFormat, ok := timeFormats[strings.ToLower(strings.TrimSpace(proxyConfig.LogTimeFormat))]; ok {
 		proxyLogger.SetLogTimeFormat(timeFormat)
 		upstreamLogger.SetLogTimeFormat(timeFormat)
 	}
@@ -107,18 +131,24 @@ func New(config config.Config) *ProxyManager {
 	shutdownCtx, shutdownCancel := context.WithCancel(context.Background())

 	var maxMetrics int
-	if config.MetricsMaxInMemory <= 0 {
+	if proxyConfig.MetricsMaxInMemory <= 0 {
 		maxMetrics = 1000 // Default fallback
 	} else {
-		maxMetrics = config.MetricsMaxInMemory
+		maxMetrics = proxyConfig.MetricsMaxInMemory
+	}
+
+	peerProxy, err := NewPeerProxy(proxyConfig.Peers, proxyLogger)
+	if err != nil {
+		proxyLogger.Errorf("Disabling Peering. Failed to create proxy peers: %v", err)
+		peerProxy = nil
 	}

 	pm := &ProxyManager{
-		config:    config,
+		config:    proxyConfig,
 		ginEngine: gin.New(),

 		proxyLogger:    proxyLogger,
-		muxLogger:      stdoutLogger,
+		muxLogger:      muxLogger,
 		upstreamLogger: upstreamLogger,

 		metricsMonitor: newMetricsMonitor(proxyLogger, maxMetrics),
@@ -131,37 +161,46 @@ func New(config config.Config) *ProxyManager {
 		buildDate: "unknown",
 		commit:    "abcd1234",
 		version:   "0",
+
+		peerProxy: peerProxy,
 	}

 	// create the process groups
-	for groupID := range config.Groups {
-		processGroup := NewProcessGroup(groupID, config, proxyLogger, upstreamLogger)
+	for groupID := range proxyConfig.Groups {
+		processGroup := NewProcessGroup(groupID, proxyConfig, proxyLogger, upstreamLogger)
 		pm.processGroups[groupID] = processGroup
 	}

 	pm.setupGinEngine()

 	// run any startup hooks
-	if len(config.Hooks.OnStartup.Preload) > 0 {
+	if len(proxyConfig.Hooks.OnStartup.Preload) > 0 {
 		// do it in the background, don't block startup -- not sure if good idea yet
 		go func() {
 			discardWriter := &DiscardWriter{}
-			for _, realModelName := range config.Hooks.OnStartup.Preload {
-				proxyLogger.Infof("Preloading model: %s", realModelName)
-				processGroup, _, err := pm.swapProcessGroup(realModelName)
+			for _, preloadModelName := range proxyConfig.Hooks.OnStartup.Preload {
+				modelID, ok := proxyConfig.RealModelName(preloadModelName)
+
+				if !ok {
+					proxyLogger.Warnf("Preload model %s not found in config", preloadModelName)
+					continue
+				}
+
+				proxyLogger.Infof("Preloading model: %s", modelID)
+				processGroup, err := pm.swapProcessGroup(modelID)

 				if err != nil {
 					event.Emit(ModelPreloadedEvent{
-						ModelName: realModelName,
+						ModelName: modelID,
 						Success:   false,
 					})
-					proxyLogger.Errorf("Failed to preload model %s: %v", realModelName, err)
+					proxyLogger.Errorf("Failed to preload model %s: %v", modelID, err)
 					continue
 				} else {
 					req, _ := http.NewRequest("GET", "/", nil)
-					processGroup.ProxyRequest(realModelName, discardWriter, req)
+					processGroup.ProxyRequest(modelID, discardWriter, req)
 					event.Emit(ModelPreloadedEvent{
-						ModelName: realModelName,
+						ModelName: modelID,
 						Success:   true,
 					})
 				}
@@ -236,37 +275,42 @@ func (pm *ProxyManager) setupGinEngine() {
 	})

 	// Set up routes using the Gin engine
-	pm.ginEngine.POST("/v1/chat/completions", pm.proxyInferenceHandler)
+	// Protected routes use pm.apiKeyAuth() middleware
+	pm.ginEngine.POST("/v1/chat/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/responses", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 	// Support legacy /v1/completions api, see issue #12
-	pm.ginEngine.POST("/v1/completions", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 	// Support anthropic /v1/messages (added https://github.com/ggml-org/llama.cpp/pull/17570)
-	pm.ginEngine.POST("/v1/messages", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/messages", pm.apiKeyAuth(), pm.proxyInferenceHandler)

 	// Support embeddings and reranking
-	pm.ginEngine.POST("/v1/embeddings", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/embeddings", pm.apiKeyAuth(), pm.proxyInferenceHandler)

 	// llama-server's /reranking endpoint + aliases
-	pm.ginEngine.POST("/reranking", pm.proxyInferenceHandler)
-	pm.ginEngine.POST("/rerank", pm.proxyInferenceHandler)
-	pm.ginEngine.POST("/v1/rerank", pm.proxyInferenceHandler)
-	pm.ginEngine.POST("/v1/reranking", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/reranking", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/rerank", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/rerank", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/reranking", pm.apiKeyAuth(), pm.proxyInferenceHandler)

 	// llama-server's /infill endpoint for code infilling
-	pm.ginEngine.POST("/infill", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/infill", pm.apiKeyAuth(), pm.proxyInferenceHandler)

 	// llama-server's /completion endpoint
-	pm.ginEngine.POST("/completion", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/completion", pm.apiKeyAuth(), pm.proxyInferenceHandler)

 	// Support audio/speech endpoint
-	pm.ginEngine.POST("/v1/audio/speech", pm.proxyInferenceHandler)
-	pm.ginEngine.POST("/v1/audio/transcriptions", pm.proxyOAIPostFormHandler)
+	pm.ginEngine.POST("/v1/audio/speech", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/audio/voices", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/audio/transcriptions", pm.apiKeyAuth(), pm.proxyOAIPostFormHandler)
+	pm.ginEngine.POST("/v1/images/generations", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/images/edits", pm.apiKeyAuth(), pm.proxyOAIPostFormHandler)

-	pm.ginEngine.GET("/v1/models", pm.listModelsHandler)
+	pm.ginEngine.GET("/v1/models", pm.apiKeyAuth(), pm.listModelsHandler)

 	// in proxymanager_loghandlers.go
-	pm.ginEngine.GET("/logs", pm.sendLogsHandlers)
-	pm.ginEngine.GET("/logs/stream", pm.streamLogsHandler)
-	pm.ginEngine.GET("/logs/stream/:logMonitorID", pm.streamLogsHandler)
+	pm.ginEngine.GET("/logs", pm.apiKeyAuth(), pm.sendLogsHandlers)
+	pm.ginEngine.GET("/logs/stream", pm.apiKeyAuth(), pm.streamLogsHandler)
+	pm.ginEngine.GET("/logs/stream/*logMonitorID", pm.apiKeyAuth(), pm.streamLogsHandler)

 	/**
 	 * User Interface Endpoints
@@ -278,9 +322,9 @@ func (pm *ProxyManager) setupGinEngine() {
 	pm.ginEngine.GET("/upstream", func(c *gin.Context) {
 		c.Redirect(http.StatusFound, "/ui/models")
 	})
-	pm.ginEngine.Any("/upstream/*upstreamPath", pm.proxyToUpstream)
-	pm.ginEngine.GET("/unload", pm.unloadAllModelsHandler)
-	pm.ginEngine.GET("/running", pm.listRunningProcessesHandler)
+	pm.ginEngine.Any("/upstream/*upstreamPath", pm.apiKeyAuth(), pm.proxyToUpstream)
+	pm.ginEngine.GET("/unload", pm.apiKeyAuth(), pm.unloadAllModelsHandler)
+	pm.ginEngine.GET("/running", pm.apiKeyAuth(), pm.listRunningProcessesHandler)
 	pm.ginEngine.GET("/health", func(c *gin.Context) {
 		c.String(http.StatusOK, "OK")
 	})
@@ -378,16 +422,10 @@ func (pm *ProxyManager) Shutdown() {
 	pm.shutdownCancel()
 }

-func (pm *ProxyManager) swapProcessGroup(requestedModel string) (*ProcessGroup, string, error) {
-	// de-alias the real model name and get a real one
-	realModelName, found := pm.config.RealModelName(requestedModel)
-	if !found {
-		return nil, realModelName, fmt.Errorf("could not find real modelID for %s", requestedModel)
-	}
-
+func (pm *ProxyManager) swapProcessGroup(realModelName string) (*ProcessGroup, error) {
 	processGroup := pm.findGroupByModelName(realModelName)
 	if processGroup == nil {
-		return nil, realModelName, fmt.Errorf("could not find process group for model %s", requestedModel)
+		return nil, fmt.Errorf("could not find process group for model %s", realModelName)
 	}

 	if processGroup.exclusive {
@@ -399,54 +437,71 @@ func (pm *ProxyManager) swapProcessGroup(requestedModel string) (*ProcessGroup,
 		}
 	}

-	return processGroup, realModelName, nil
+	return processGroup, nil
 }

 func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	data := make([]gin.H, 0, len(pm.config.Models))
 	createdTime := time.Now().Unix()

+	newRecord := func(modelId string, modelConfig config.ModelConfig) gin.H {
+		record := gin.H{
+			"id":       modelId,
+			"object":   "model",
+			"created":  createdTime,
+			"owned_by": "llama-swap",
+		}
+
+		if name := strings.TrimSpace(modelConfig.Name); name != "" {
+			record["name"] = name
+		}
+		if desc := strings.TrimSpace(modelConfig.Description); desc != "" {
+			record["description"] = desc
+		}
+
+		// Add metadata if present
+		if len(modelConfig.Metadata) > 0 {
+			record["meta"] = gin.H{
+				"llamaswap": modelConfig.Metadata,
+			}
+		}
+		return record
+	}
+
 	for id, modelConfig := range pm.config.Models {
 		if modelConfig.Unlisted {
 			continue
 		}

-		newRecord := func(modelId string) gin.H {
-			record := gin.H{
-				"id":       modelId,
-				"object":   "model",
-				"created":  createdTime,
-				"owned_by": "llama-swap",
-			}
-
-			if name := strings.TrimSpace(modelConfig.Name); name != "" {
-				record["name"] = name
-			}
-			if desc := strings.TrimSpace(modelConfig.Description); desc != "" {
-				record["description"] = desc
-			}
-
-			// Add metadata if present
-			if len(modelConfig.Metadata) > 0 {
-				record["meta"] = gin.H{
-					"llamaswap": modelConfig.Metadata,
-				}
-			}
-			return record
-		}
-
-		data = append(data, newRecord(id))
+		data = append(data, newRecord(id, modelConfig))

 		// Include aliases
 		if pm.config.IncludeAliasesInList {
 			for _, alias := range modelConfig.Aliases {
 				if alias := strings.TrimSpace(alias); alias != "" {
-					data = append(data, newRecord(alias))
+					data = append(data, newRecord(alias, modelConfig))
 				}
 			}
 		}
 	}

+	if pm.peerProxy != nil {
+		for peerID, peer := range pm.peerProxy.ListPeers() {
+			// add peer models
+			for _, modelID := range peer.Models {
+				// Skip unlisted models if not showing them
+				record := newRecord(modelID, config.ModelConfig{
+					Name: fmt.Sprintf("%s: %s", peerID, modelID),
+					Metadata: map[string]any{
+						"peerID": peerID,
+					},
+				})
+
+				data = append(data, record)
+			}
+		}
+	}
+
 	// Sort by the "id" key
 	sort.Slice(data, func(i, j int) bool {
 		si, _ := data[i]["id"].(string)
@@ -466,62 +521,61 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	})
 }

-func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
-	upstreamPath := c.Param("upstreamPath")
-
-	// split the upstream path by / and search for the model name
-	parts := strings.Split(strings.TrimSpace(upstreamPath), "/")
-	if len(parts) == 0 {
-		pm.sendErrorResponse(c, http.StatusBadRequest, "model id required in path")
-		return
-	}
-
-	modelFound := false
+// findModelInPath searches for a valid model name in a path with slashes.
+// It iteratively builds up path segments until it finds a matching model.
+// Returns: (searchModelName, realModelName, remainingPath, found)
+// Example: "/author/model/endpoint" with model "author/model" -> ("author/model", "author/model", "/endpoint", true)
+func (pm *ProxyManager) findModelInPath(path string) (searchName string, realName string, remainingPath string, found bool) {
+	parts := strings.Split(strings.TrimSpace(path), "/")
 	searchModelName := ""
-	var modelName, remainingPath string
+
 	for i, part := range parts {
-		if parts[i] == "" {
+		if part == "" {
 			continue
 		}

 		if searchModelName == "" {
 			searchModelName = part
 		} else {
-			searchModelName = searchModelName + "/" + parts[i]
+			searchModelName = searchModelName + "/" + part
 		}

-		if real, ok := pm.config.RealModelName(searchModelName); ok {
-			modelName = real
-			remainingPath = "/" + strings.Join(parts[i+1:], "/")
-			modelFound = true
-
-			// Check if this is exactly a model name with no additional path
-			// and doesn't end with a trailing slash
-			if remainingPath == "/" && !strings.HasSuffix(upstreamPath, "/") {
-				// Build new URL with query parameters preserved
-				newPath := "/upstream/" + searchModelName + "/"
-				if c.Request.URL.RawQuery != "" {
-					newPath += "?" + c.Request.URL.RawQuery
-				}
-
-				// Use 308 for non-GET/HEAD requests to preserve method
-				if c.Request.Method == http.MethodGet || c.Request.Method == http.MethodHead {
-					c.Redirect(http.StatusMovedPermanently, newPath)
-				} else {
-					c.Redirect(http.StatusPermanentRedirect, newPath)
-				}
-				return
-			}
-			break
+		if modelID, ok := pm.config.RealModelName(searchModelName); ok {
+			return searchModelName, modelID, "/" + strings.Join(parts[i+1:], "/"), true
 		}
 	}

+	return "", "", "", false
+}
+
+func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
+	upstreamPath := c.Param("upstreamPath")
+
+	searchModelName, modelID, remainingPath, modelFound := pm.findModelInPath(upstreamPath)
+
 	if !modelFound {
 		pm.sendErrorResponse(c, http.StatusBadRequest, "model id required in path")
 		return
 	}

-	processGroup, realModelName, err := pm.swapProcessGroup(modelName)
+	// Redirect /upstream/modelname to /upstream/modelname/ for URL consistency.
+	// This ensures relative URLs in upstream responses resolve correctly and
+	// provides canonical URL form. Uses 308 for POST/PUT/etc to preserve the
+	// HTTP method (301 would downgrade to GET).
+	if remainingPath == "/" && !strings.HasSuffix(upstreamPath, "/") {
+		newPath := "/upstream/" + searchModelName + "/"
+		if c.Request.URL.RawQuery != "" {
+			newPath += "?" + c.Request.URL.RawQuery
+		}
+		if c.Request.Method == http.MethodGet || c.Request.Method == http.MethodHead {
+			c.Redirect(http.StatusMovedPermanently, newPath)
+		} else {
+			c.Redirect(http.StatusPermanentRedirect, newPath)
+		}
+		return
+	}
+
+	processGroup, err := pm.swapProcessGroup(modelID)
 	if err != nil {
 		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
 		return
@@ -533,15 +587,15 @@ func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {

 	// attempt to record metrics if it is a POST request
 	if pm.metricsMonitor != nil && c.Request.Method == "POST" {
-		if err := pm.metricsMonitor.wrapHandler(realModelName, c.Writer, c.Request, processGroup.ProxyRequest); err != nil {
+		if err := pm.metricsMonitor.wrapHandler(modelID, c.Writer, c.Request, processGroup.ProxyRequest); err != nil {
 			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying metrics wrapped request: %s", err.Error()))
-			pm.proxyLogger.Errorf("Error proxying wrapped upstream request for model %s, path=%s", realModelName, originalPath)
+			pm.proxyLogger.Errorf("Error proxying wrapped upstream request for model %s, path=%s", modelID, originalPath)
 			return
 		}
 	} else {
-		if err := processGroup.ProxyRequest(realModelName, c.Writer, c.Request); err != nil {
+		if err := processGroup.ProxyRequest(modelID, c.Writer, c.Request); err != nil {
 			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying request: %s", err.Error()))
-			pm.proxyLogger.Errorf("Error proxying upstream request for model %s, path=%s", realModelName, originalPath)
+			pm.proxyLogger.Errorf("Error proxying upstream request for model %s, path=%s", modelID, originalPath)
 			return
 		}
 	}
@@ -560,41 +614,90 @@ func (pm *ProxyManager) proxyInferenceHandler(c *gin.Context) {
 		return
 	}

-	realModelName, found := pm.config.RealModelName(requestedModel)
-	if !found {
-		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("could not find real modelID for %s", requestedModel))
-		return
-	}
+	// Look for a matching local model first
+	var nextHandler func(modelID string, w http.ResponseWriter, r *http.Request) error

-	processGroup, _, err := pm.swapProcessGroup(realModelName)
-	if err != nil {
-		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
-		return
-	}
-
-	// issue #69 allow custom model names to be sent to upstream
-	useModelName := pm.config.Models[realModelName].UseModelName
-	if useModelName != "" {
-		bodyBytes, err = sjson.SetBytes(bodyBytes, "model", useModelName)
+	modelID, found := pm.config.RealModelName(requestedModel)
+	if found {
+		processGroup, err := pm.swapProcessGroup(modelID)
 		if err != nil {
-			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error rewriting model name in JSON: %s", err.Error()))
+			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
 			return
 		}
-	}

-	// issue #174 strip parameters from the JSON body
-	stripParams, err := pm.config.Models[realModelName].Filters.SanitizedStripParams()
-	if err != nil { // just log it and continue
-		pm.proxyLogger.Errorf("Error sanitizing strip params string: %s, %s", pm.config.Models[realModelName].Filters.StripParams, err.Error())
-	} else {
-		for _, param := range stripParams {
-			pm.proxyLogger.Debugf("<%s> stripping param: %s", realModelName, param)
-			bodyBytes, err = sjson.DeleteBytes(bodyBytes, param)
+		// issue #69 allow custom model names to be sent to upstream
+		useModelName := pm.config.Models[modelID].UseModelName
+		if useModelName != "" {
+			bodyBytes, err = sjson.SetBytes(bodyBytes, "model", useModelName)
 			if err != nil {
-				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error deleting parameter %s from request", param))
+				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error rewriting model name in JSON: %s", err.Error()))
 				return
 			}
 		}
+
+		// issue #174 strip parameters from the JSON body
+		stripParams, err := pm.config.Models[modelID].Filters.SanitizedStripParams()
+		if err != nil { // just log it and continue
+			pm.proxyLogger.Errorf("Error sanitizing strip params string: %s, %s", pm.config.Models[modelID].Filters.StripParams, err.Error())
+		} else {
+			for _, param := range stripParams {
+				pm.proxyLogger.Debugf("<%s> stripping param: %s", modelID, param)
+				bodyBytes, err = sjson.DeleteBytes(bodyBytes, param)
+				if err != nil {
+					pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error deleting parameter %s from request", param))
+					return
+				}
+			}
+		}
+
+		// issue #453 set/override parameters in the JSON body
+		setParams, setParamKeys := pm.config.Models[modelID].Filters.SanitizedSetParams()
+		for _, key := range setParamKeys {
+			pm.proxyLogger.Debugf("<%s> setting param: %s", modelID, key)
+			bodyBytes, err = sjson.SetBytes(bodyBytes, key, setParams[key])
+			if err != nil {
+				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error setting parameter %s in request", key))
+				return
+			}
+		}
+
+		pm.proxyLogger.Debugf("ProxyManager using local Process for model: %s", requestedModel)
+		nextHandler = processGroup.ProxyRequest
+	} else if pm.peerProxy != nil && pm.peerProxy.HasPeerModel(requestedModel) {
+		pm.proxyLogger.Debugf("ProxyManager using ProxyPeer for model: %s", requestedModel)
+		modelID = requestedModel
+
+		// issue #453 apply filters for peer requests
+		peerFilters := pm.peerProxy.GetPeerFilters(requestedModel)
+
+		// Apply stripParams - remove specified parameters from request
+		stripParams := peerFilters.SanitizedStripParams()
+		for _, param := range stripParams {
+			pm.proxyLogger.Debugf("<%s> stripping param: %s", requestedModel, param)
+			bodyBytes, err = sjson.DeleteBytes(bodyBytes, param)
+			if err != nil {
+				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error stripping parameter %s from request", param))
+				return
+			}
+		}
+
+		// Apply setParams - set/override specified parameters in request
+		setParams, setParamKeys := peerFilters.SanitizedSetParams()
+		for _, key := range setParamKeys {
+			pm.proxyLogger.Debugf("<%s> setting param: %s", requestedModel, key)
+			bodyBytes, err = sjson.SetBytes(bodyBytes, key, setParams[key])
+			if err != nil {
+				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error setting parameter %s in request", key))
+				return
+			}
+		}
+
+		nextHandler = pm.peerProxy.ProxyRequest
+	}
+
+	if nextHandler == nil {
+		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("could not find suitable inference handler for %s", requestedModel))
+		return
 	}

 	c.Request.Body = io.NopCloser(bytes.NewBuffer(bodyBytes))
@@ -607,19 +710,19 @@ func (pm *ProxyManager) proxyInferenceHandler(c *gin.Context) {
 	// issue #366 extract values that downstream handlers may need
 	isStreaming := gjson.GetBytes(bodyBytes, "stream").Bool()
 	ctx := context.WithValue(c.Request.Context(), proxyCtxKey("streaming"), isStreaming)
-	ctx = context.WithValue(ctx, proxyCtxKey("model"), realModelName)
+	ctx = context.WithValue(ctx, proxyCtxKey("model"), modelID)
 	c.Request = c.Request.WithContext(ctx)

 	if pm.metricsMonitor != nil && c.Request.Method == "POST" {
-		if err := pm.metricsMonitor.wrapHandler(realModelName, c.Writer, c.Request, processGroup.ProxyRequest); err != nil {
+		if err := pm.metricsMonitor.wrapHandler(modelID, c.Writer, c.Request, nextHandler); err != nil {
 			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying metrics wrapped request: %s", err.Error()))
-			pm.proxyLogger.Errorf("Error Proxying Metrics Wrapped Request for processGroup %s and model %s", processGroup.id, realModelName)
+			pm.proxyLogger.Errorf("Error Proxying Metrics Wrapped Request model %s", modelID)
 			return
 		}
 	} else {
-		if err := processGroup.ProxyRequest(realModelName, c.Writer, c.Request); err != nil {
+		if err := nextHandler(modelID, c.Writer, c.Request); err != nil {
 			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying request: %s", err.Error()))
-			pm.proxyLogger.Errorf("Error Proxying Request for processGroup %s and model %s", processGroup.id, realModelName)
+			pm.proxyLogger.Errorf("Error Proxying Request for model %s", modelID)
 			return
 		}
 	}
@@ -639,7 +742,13 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 		return
 	}

-	processGroup, realModelName, err := pm.swapProcessGroup(requestedModel)
+	modelID, found := pm.config.RealModelName(requestedModel)
+	if !found {
+		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("could not find real modelID for %s", requestedModel))
+		return
+	}
+
+	processGroup, err := pm.swapProcessGroup(modelID)
 	if err != nil {
 		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
 		return
@@ -657,7 +766,7 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 			// If this is the model field and we have a profile, use just the model name
 			if key == "model" {
 				// # issue #69 allow custom model names to be sent to upstream
-				useModelName := pm.config.Models[realModelName].UseModelName
+				useModelName := pm.config.Models[modelID].UseModelName

 				if useModelName != "" {
 					fieldValue = useModelName
@@ -728,9 +837,9 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 	modifiedReq.ContentLength = int64(requestBuffer.Len())

 	// Use the modified request for proxying
-	if err := processGroup.ProxyRequest(realModelName, c.Writer, modifiedReq); err != nil {
+	if err := processGroup.ProxyRequest(modelID, c.Writer, modifiedReq); err != nil {
 		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying request: %s", err.Error()))
-		pm.proxyLogger.Errorf("Error Proxying Request for processGroup %s and model %s", processGroup.id, realModelName)
+		pm.proxyLogger.Errorf("Error Proxying Request for processGroup %s and model %s", processGroup.id, modelID)
 		return
 	}
 }
@@ -745,6 +854,67 @@ func (pm *ProxyManager) sendErrorResponse(c *gin.Context, statusCode int, messag
 	}
 }

+// apiKeyAuth returns a middleware that validates API keys if configured.
+// Returns a pass-through handler if no API keys are configured.
+func (pm *ProxyManager) apiKeyAuth() gin.HandlerFunc {
+	if len(pm.config.RequiredAPIKeys) == 0 {
+		return func(c *gin.Context) { c.Next() }
+	}
+
+	return func(c *gin.Context) {
+		xApiKey := c.GetHeader("x-api-key")
+
+		var bearerKey string
+		var basicKey string
+		if auth := c.GetHeader("Authorization"); auth != "" {
+			if strings.HasPrefix(auth, "Bearer ") {
+				bearerKey = strings.TrimPrefix(auth, "Bearer ")
+			} else if strings.HasPrefix(auth, "Basic ") {
+				// Basic Auth: base64(username:password), password is the API key
+				encoded := strings.TrimPrefix(auth, "Basic ")
+				if decoded, err := base64.StdEncoding.DecodeString(encoded); err == nil {
+					parts := strings.SplitN(string(decoded), ":", 2)
+					if len(parts) == 2 {
+						basicKey = parts[1] // password is the API key
+					}
+				}
+			}
+		}
+
+		// Use first key found: Basic, then Bearer, then x-api-key
+		var providedKey string
+		if basicKey != "" {
+			providedKey = basicKey
+		} else if bearerKey != "" {
+			providedKey = bearerKey
+		} else {
+			providedKey = xApiKey
+		}
+
+		// Validate key
+		valid := false
+		for _, key := range pm.config.RequiredAPIKeys {
+			if providedKey == key {
+				valid = true
+				break
+			}
+		}
+
+		if !valid {
+			c.Header("WWW-Authenticate", `Basic realm="llama-swap"`)
+			pm.sendErrorResponse(c, http.StatusUnauthorized, "unauthorized: invalid or missing API key")
+			c.Abort()
+			return
+		}
+
+		// Strip auth headers to prevent leakage to upstream
+		c.Request.Header.Del("Authorization")
+		c.Request.Header.Del("x-api-key")
+
+		c.Next()
+	}
+}
+
 func (pm *ProxyManager) unloadAllModelsHandler(c *gin.Context) {
 	pm.StopProcesses(StopImmediately)
 	c.String(http.StatusOK, "OK")
@@ -18,11 +18,13 @@ type Model struct {
 	Description string `json:"description"`
 	State       string `json:"state"`
 	Unlisted    bool   `json:"unlisted"`
+	PeerID      string `json:"peerID"`
 }

 func addApiHandlers(pm *ProxyManager) {
 	// Add API endpoints for React to consume
-	apiGroup := pm.ginEngine.Group("/api")
+	// Protected with API key authentication
+	apiGroup := pm.ginEngine.Group("/api", pm.apiKeyAuth())
 	{
 		apiGroup.POST("/models/unload", pm.apiUnloadAllModels)
 		apiGroup.POST("/models/unload/*model", pm.apiUnloadSingleModelHandler)
@@ -82,6 +84,18 @@ func (pm *ProxyManager) getModelStatus() []Model {
 		})
 	}

+	// Iterate over the peer models
+	if pm.peerProxy != nil {
+		for peerID, peer := range pm.peerProxy.ListPeers() {
+			for _, modelID := range peer.Models {
+				models = append(models, Model{
+					Id:     modelID,
+					PeerID: peerID,
+				})
+			}
+		}
+	}
+
 	return models
 }

@@ -31,7 +31,7 @@ func (pm *ProxyManager) streamLogsHandler(c *gin.Context) {
 	// prevent nginx from buffering streamed logs
 	c.Header("X-Accel-Buffering", "no")

-	logMonitorId := c.Param("logMonitorID")
+	logMonitorId := strings.TrimPrefix(c.Param("logMonitorID"), "/")
 	logger, err := pm.getLogger(logMonitorId)
 	if err != nil {
 		c.String(http.StatusBadRequest, err.Error())
@@ -92,8 +92,9 @@ func (pm *ProxyManager) getLogger(logMonitorId string) (*LogMonitor, error) {
 	case "upstream":
 		return pm.upstreamLogger, nil
 	default:
-		// search for a models specific logger
-		if name, found := pm.config.RealModelName(logMonitorId); found {
+		// search for a models specific logger using findModelInPath
+		// to handle model names with slashes (e.g., "author/model")
+		if _, name, _, found := pm.findModelInPath("/" + logMonitorId); found {
 			for _, group := range pm.processGroups {
 				if process, found := group.GetMember(name); found {
 					return process.Logger(), nil
@@ -101,6 +102,6 @@ func (pm *ProxyManager) getLogger(logMonitorId string) (*LogMonitor, error) {
 			}
 		}

-		return nil, fmt.Errorf("invalid logger. Use 'proxy' or 'upstream'")
+		return nil, fmt.Errorf("invalid logger. Use 'proxy', 'upstream' or a model's ID")
 	}
 }
@@ -3,6 +3,7 @@ package proxy
 import (
 	"bytes"
 	"context"
+	"encoding/base64"
 	"encoding/json"
 	"fmt"
 	"math/rand"
@@ -36,10 +37,6 @@ func (r *TestResponseRecorder) CloseNotify() <-chan bool {
 	return r.closeChannel
 }

-func (r *TestResponseRecorder) closeClient() {
-	r.closeChannel <- true
-}
-
 func CreateTestResponseRecorder() *TestResponseRecorder {
 	return &TestResponseRecorder{
 		httptest.NewRecorder(),
@@ -223,17 +220,23 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 	model2Config.Name = "     " // empty whitespace only strings will get ignored
 	model2Config.Description = "  "

-	config := config.Config{
+	cfg := config.Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]config.ModelConfig{
 			"model1": model1Config,
 			"model2": model2Config,
 			"model3": getTestSimpleResponderConfig("model3"),
 		},
+		Peers: map[string]config.PeerConfig{
+			"peer1": {
+				Proxy:  "http://peer1:8080",
+				Models: []string{"peer-model-a", "peer-model-b"},
+			},
+		},
 		LogLevel: "error",
 	}

-	proxy := New(config)
+	proxy := New(cfg)

 	// Create a test request
 	req := httptest.NewRequest("GET", "/v1/models", nil)
@@ -258,14 +261,16 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 		t.Fatalf("Failed to parse JSON response: %v", err)
 	}

-	// Check the number of models returned
-	assert.Len(t, response.Data, 3)
+	// Check the number of models returned (3 local + 2 peer models)
+	assert.Len(t, response.Data, 5)

 	// Check the details of each model
 	expectedModels := map[string]struct{}{
-		"model1": {},
-		"model2": {},
-		"model3": {},
+		"model1":       {},
+		"model2":       {},
+		"model3":       {},
+		"peer-model-a": {},
+		"peer-model-b": {},
 	}

 	// make all models
@@ -296,6 +301,19 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 			description, ok := model["description"].(string)
 			assert.True(t, ok, "description should be a string")
 			assert.Equal(t, "Model 1 description is used for testing", description)
+		} else if modelID == "peer-model-a" || modelID == "peer-model-b" {
+			// Peer models should have meta.llamaswap.peerID
+			meta, exists := model["meta"]
+			assert.True(t, exists, "peer model should have meta field")
+			metaMap, ok := meta.(map[string]interface{})
+			assert.True(t, ok, "meta should be a map")
+			llamaswap, exists := metaMap["llamaswap"]
+			assert.True(t, exists, "meta should have llamaswap field")
+			llamaswapMap, ok := llamaswap.(map[string]interface{})
+			assert.True(t, ok, "llamaswap should be a map")
+			peerID, exists := llamaswapMap["peerID"]
+			assert.True(t, exists, "llamaswap should have peerID field")
+			assert.Equal(t, "peer1", peerID)
 		} else {
 			_, exists := model["name"]
 			assert.False(t, exists, "unexpected name field for model: %s", modelID)
@@ -502,6 +520,10 @@ func TestProxyManager_ListModelsHandler_IncludeAliasesInList(t *testing.T) {
 }

 func TestProxyManager_Shutdown(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping slow test")
+	}
+
 	// make broken model configurations
 	model1Config := getTestSimpleResponderConfigPort("model1", 9991)
 	model1Config.Proxy = "http://localhost:10001/"
@@ -944,7 +966,9 @@ func TestProxyManager_ChatContentLength(t *testing.T) {
 func TestProxyManager_FiltersStripParams(t *testing.T) {
 	modelConfig := getTestSimpleResponderConfig("model1")
 	modelConfig.Filters = config.ModelFilters{
-		StripParams: "temperature, model, stream",
+		Filters: config.Filters{
+			StripParams: "temperature, model, stream",
+		},
 	}

 	config := config.AddDefaultGroupToConfig(config.Config{
@@ -1078,7 +1102,8 @@ func TestProxyManager_StreamingEndpointsReturnNoBufferingHeader(t *testing.T) {
 	config := config.AddDefaultGroupToConfig(config.Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]config.ModelConfig{
-			"model1": getTestSimpleResponderConfig("model1"),
+			"model1":       getTestSimpleResponderConfig("model1"),
+			"author/model": getTestSimpleResponderConfig("author/model"),
 		},
 		LogLevel: "error",
 	})
@@ -1091,6 +1116,7 @@ func TestProxyManager_StreamingEndpointsReturnNoBufferingHeader(t *testing.T) {
 		"/logs/stream",
 		"/logs/stream/proxy",
 		"/logs/stream/upstream",
+		"/logs/stream/author/model",
 	}

 	for _, endpoint := range endpoints {
@@ -1185,3 +1211,349 @@ func TestProxyManager_ApiGetVersion(t *testing.T) {
 		assert.Equal(t, value, response[key], "%s value %s should match response %s", key, value, response[key])
 	}
 }
+
+func TestProxyManager_APIKeyAuth(t *testing.T) {
+	testConfig := config.AddDefaultGroupToConfig(config.Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]config.ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		RequiredAPIKeys: []string{"valid-key-1", "valid-key-2"},
+		LogLevel:        "error",
+	})
+
+	proxy := New(testConfig)
+	defer proxy.StopProcesses(StopImmediately)
+
+	t.Run("valid key in x-api-key header", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("x-api-key", "valid-key-1")
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("valid key in Authorization Bearer header", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("Authorization", "Bearer valid-key-2")
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("both headers with matching keys", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("x-api-key", "valid-key-1")
+		req.Header.Set("Authorization", "Bearer valid-key-1")
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("invalid key returns 401", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("x-api-key", "invalid-key")
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusUnauthorized, w.Code)
+		assert.Contains(t, w.Body.String(), "unauthorized")
+	})
+
+	t.Run("missing key returns 401", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusUnauthorized, w.Code)
+	})
+
+	t.Run("valid key in Basic Auth header", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		// Basic Auth: base64("anyuser:valid-key-1")
+		credentials := base64.StdEncoding.EncodeToString([]byte("anyuser:valid-key-1"))
+		req.Header.Set("Authorization", "Basic "+credentials)
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("invalid key in Basic Auth header returns 401", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		credentials := base64.StdEncoding.EncodeToString([]byte("anyuser:wrong-key"))
+		req.Header.Set("Authorization", "Basic "+credentials)
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusUnauthorized, w.Code)
+		assert.Contains(t, w.Body.String(), "unauthorized")
+	})
+
+	t.Run("x-api-key and Basic Auth with matching keys", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("x-api-key", "valid-key-1")
+		credentials := base64.StdEncoding.EncodeToString([]byte("user:valid-key-1"))
+		req.Header.Set("Authorization", "Basic "+credentials)
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("401 response includes WWW-Authenticate header", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusUnauthorized, w.Code)
+		assert.Equal(t, `Basic realm="llama-swap"`, w.Header().Get("WWW-Authenticate"))
+	})
+}
+
+func TestProxyManager_APIKeyAuth_Disabled(t *testing.T) {
+	// Config without RequiredAPIKeys - auth should be disabled
+	testConfig := config.AddDefaultGroupToConfig(config.Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]config.ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(testConfig)
+	defer proxy.StopProcesses(StopImmediately)
+
+	t.Run("requests pass without API key when not configured", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+}
+
+// TestProxyManager_PeerProxy_InferenceHandler tests the peerProxy integration
+// in proxyInferenceHandler for issue #433
+func TestProxyManager_PeerProxy_InferenceHandler(t *testing.T) {
+	t.Run("requests to peer models are proxied", func(t *testing.T) {
+		// Create a test server to act as the peer
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(`{"response":"from-peer","model":"peer-model"}`))
+		}))
+		defer peerServer.Close()
+
+		// Create config with peers but no local model for "peer-model"
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    models:
+      - peer-model
+models:
+  local-model:
+    cmd: %s -port ${PORT} -silent -respond local-model
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"peer-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), "from-peer")
+	})
+
+	t.Run("local models take precedence over peer models", func(t *testing.T) {
+		// Create a test server to act as the peer - should NOT be called
+		peerCalled := false
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			peerCalled = true
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(`{"response":"from-peer"}`))
+		}))
+		defer peerServer.Close()
+
+		// Create config where "shared-model" exists both locally and on peer
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    models:
+      - shared-model
+models:
+  shared-model:
+    cmd: %s -port ${PORT} -silent -respond local-response
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"shared-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), "local-response")
+		assert.False(t, peerCalled, "peer should not be called when local model exists")
+	})
+
+	t.Run("unknown model returns error", func(t *testing.T) {
+		// Create a test server to act as the peer
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.WriteHeader(http.StatusOK)
+		}))
+		defer peerServer.Close()
+
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    models:
+      - peer-model
+models:
+  local-model:
+    cmd: %s -port ${PORT} -silent -respond local-model
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"unknown-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusBadRequest, w.Code)
+		assert.Contains(t, w.Body.String(), "could not find suitable inference handler")
+	})
+
+	t.Run("peer API key is injected into request", func(t *testing.T) {
+		var receivedAuthHeader string
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			receivedAuthHeader = r.Header.Get("Authorization")
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(`{"response":"ok"}`))
+		}))
+		defer peerServer.Close()
+
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    apiKey: secret-peer-key
+    models:
+      - peer-model
+models:
+  local-model:
+    cmd: %s -port ${PORT} -silent -respond local-model
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"peer-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Equal(t, "Bearer secret-peer-key", receivedAuthHeader)
+	})
+
+	t.Run("no peers configured - unknown model returns error", func(t *testing.T) {
+		testConfig := config.AddDefaultGroupToConfig(config.Config{
+			HealthCheckTimeout: 15,
+			Models: map[string]config.ModelConfig{
+				"local-model": getTestSimpleResponderConfig("local-model"),
+			},
+			LogLevel: "error",
+		})
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		// peerProxy exists but has no peer models configured
+		assert.False(t, proxy.peerProxy.HasPeerModel("unknown-model"))
+
+		reqBody := `{"model":"unknown-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusBadRequest, w.Code)
+		assert.Contains(t, w.Body.String(), "could not find suitable inference handler")
+	})
+
+	t.Run("peer streaming response sets X-Accel-Buffering header", func(t *testing.T) {
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.Header().Set("Content-Type", "text/event-stream")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte("data: test\n\n"))
+		}))
+		defer peerServer.Close()
+
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    models:
+      - peer-model
+models:
+  local-model:
+    cmd: %s -port ${PORT} -silent -respond local-model
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"peer-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Equal(t, "no", w.Header().Get("X-Accel-Buffering"))
+	})
+}
@@ -12,7 +12,7 @@
        "react-dom": "^19.1.0",
        "react-icons": "^5.5.0",
        "react-resizable-panels": "^3.0.4",
-        "react-router-dom": "^7.6.2"
+        "react-router-dom": "^7.12.0"
      },
      "devDependencies": {
        "@eslint/js": "^9.25.0",
@@ -2232,12 +2232,16 @@
      "license": "MIT"
    },
    "node_modules/cookie": {
-      "version": "1.0.2",
-      "resolved": "https://registry.npmjs.org/cookie/-/cookie-1.0.2.tgz",
-      "integrity": "sha512-9Kr/j4O16ISv8zBBhJoi4bXOYNTkFLOqSL3UDB0njXxCXNezjeyVrJyGOWtgfs/q2km1gwBcfH8q1yEGoMYunA==",
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/cookie/-/cookie-1.1.1.tgz",
+      "integrity": "sha512-ei8Aos7ja0weRpFzJnEA9UHJ/7XQmqglbRwnf2ATjcB9Wq874VKH9kfjjirM6UhU2/E5fFYadylyhFldcqSidQ==",
      "license": "MIT",
      "engines": {
        "node": ">=18"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/express"
      }
    },
    "node_modules/cross-spawn": {
@@ -3559,9 +3563,9 @@
      }
    },
    "node_modules/react-router": {
-      "version": "7.6.2",
-      "resolved": "https://registry.npmjs.org/react-router/-/react-router-7.6.2.tgz",
-      "integrity": "sha512-U7Nv3y+bMimgWjhlT5CRdzHPu2/KVmqPwKUCChW8en5P3znxUqwlYFlbmyj8Rgp1SF6zs5X4+77kBVknkg6a0w==",
+      "version": "7.12.0",
+      "resolved": "https://registry.npmjs.org/react-router/-/react-router-7.12.0.tgz",
+      "integrity": "sha512-kTPDYPFzDVGIIGNLS5VJykK0HfHLY5MF3b+xj0/tTyNYL1gF1qs7u67Z9jEhQk2sQ98SUaHxlG31g1JtF7IfVw==",
      "license": "MIT",
      "dependencies": {
        "cookie": "^1.0.1",
@@ -3581,12 +3585,12 @@
      }
    },
    "node_modules/react-router-dom": {
-      "version": "7.6.2",
-      "resolved": "https://registry.npmjs.org/react-router-dom/-/react-router-dom-7.6.2.tgz",
-      "integrity": "sha512-Q8zb6VlTbdYKK5JJBLQEN06oTUa/RAbG/oQS1auK1I0TbJOXktqm+QENEVJU6QvWynlXPRBXI3fiOQcSEA78rA==",
+      "version": "7.12.0",
+      "resolved": "https://registry.npmjs.org/react-router-dom/-/react-router-dom-7.12.0.tgz",
+      "integrity": "sha512-pfO9fiBcpEfX4Tx+iTYKDtPbrSLLCbwJ5EqP+SPYQu1VYCXdy79GSj0wttR0U4cikVdlImZuEZ/9ZNCgoaxwBA==",
      "license": "MIT",
      "dependencies": {
-        "react-router": "7.6.2"
+        "react-router": "7.12.0"
      },
      "engines": {
        "node": ">=20.0.0"
@@ -3705,9 +3709,9 @@
      }
    },
    "node_modules/set-cookie-parser": {
-      "version": "2.7.1",
-      "resolved": "https://registry.npmjs.org/set-cookie-parser/-/set-cookie-parser-2.7.1.tgz",
-      "integrity": "sha512-IOc8uWeOZgnb3ptbCURJWNjWUPcO3ZnTTdzsurqERrP6nPyv+paC55vJM0LpOlT2ne+Ix+9+CRG1MNLlyZ4GjQ==",
+      "version": "2.7.2",
+      "resolved": "https://registry.npmjs.org/set-cookie-parser/-/set-cookie-parser-2.7.2.tgz",
+      "integrity": "sha512-oeM1lpU/UvhTxw+g3cIfxXHyJRc/uidd3yK1P242gzHds0udQBYzs3y8j4gCCW+ZJ7ad0yctld8RYO+bdurlvw==",
      "license": "MIT"
    },
    "node_modules/shebang-command": {
@@ -14,7 +14,7 @@
    "react-dom": "^19.1.0",
    "react-icons": "^5.5.0",
    "react-resizable-panels": "^3.0.4",
-    "react-router-dom": "^7.6.2"
+    "react-router-dom": "^7.12.0"
  },
  "devDependencies": {
    "@eslint/js": "^9.25.0",
@@ -10,6 +10,7 @@ export interface Model {
  name: string;
  description: string;
  unlisted: boolean;
+  peerID: string;
 }

 interface APIProviderType {
@@ -70,7 +71,7 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
  const [versionInfo, setVersionInfo] = useState<VersionInfo>({
    build_date: "unknown",
    commit: "unknown",
-    version: "unknown"
+    version: "unknown",
  });
  //const apiEventSource = useRef<EventSource | null>(null);

@@ -166,7 +167,7 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
  }, []);

  useEffect(() => {
-    // fetch version 
+    // fetch version
    const fetchVersion = async () => {
      try {
        const response = await fetch("/api/version");
@@ -180,7 +181,7 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
      }
    };

-    if (connectionStatus === 'connected') {
+    if (connectionStatus === "connected") {
      fetchVersion();
    }
  }, [connectionStatus]);
@@ -265,7 +266,19 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
      connectionStatus,
      versionInfo,
    }),
-    [models, listModels, unloadAllModels, unloadSingleModel, loadModel, enableAPIEvents, proxyLogs, upstreamLogs, metrics, connectionStatus, versionInfo]
+    [
+      models,
+      listModels,
+      unloadAllModels,
+      unloadSingleModel,
+      loadModel,
+      enableAPIEvents,
+      proxyLogs,
+      upstreamLogs,
+      metrics,
+      connectionStatus,
+      versionInfo,
+    ]
  );

  return <APIContext.Provider value={value}>{children}</APIContext.Provider>;
@@ -44,8 +44,24 @@ function ModelsPanel() {
  const [showIdorName, setShowIdorName] = usePersistentState<"id" | "name">("showIdorName", "id"); // true = show ID, false = show name
  const [menuOpen, setMenuOpen] = useState(false);

-  const filteredModels = useMemo(() => {
-    return models.filter((model) => showUnlisted || !model.unlisted);
+  const { regularModels, peerModelsByPeerId } = useMemo(() => {
+    const filtered = models.filter((model) => showUnlisted || !model.unlisted);
+    const peerModels = filtered.filter((m) => m.peerID);
+
+    // Group peer models by peerID
+    const grouped = peerModels.reduce((acc, model) => {
+      const peerId = model.peerID || "unknown";
+      if (!acc[peerId]) {
+        acc[peerId] = [];
+      }
+      acc[peerId].push(model);
+      return acc;
+    }, {} as Record<string, typeof peerModels>);
+
+    return {
+      regularModels: filtered.filter((m) => !m.peerID),
+      peerModelsByPeerId: grouped,
+    };
  }, [models, showUnlisted]);

  const handleUnloadAllModels = useCallback(async () => {
@@ -151,7 +167,7 @@ function ModelsPanel() {
            </tr>
          </thead>
          <tbody>
-            {filteredModels.map((model) => (
+            {regularModels.map((model) => (
              <tr key={model.id} className="border-b hover:bg-secondary-hover border-gray-200">
                <td className={`${model.unlisted ? "text-txtsecondary" : ""}`}>
                  <a href={`/upstream/${model.id}/`} className="font-semibold" target="_blank">
@@ -186,6 +202,34 @@ function ModelsPanel() {
            ))}
          </tbody>
        </table>
+
+        {Object.keys(peerModelsByPeerId).length > 0 && (
+          <>
+            <h3 className="mt-8 mb-2">Peer Models</h3>
+            {Object.entries(peerModelsByPeerId)
+              .sort(([a], [b]) => a.localeCompare(b))
+              .map(([peerId, models]) => (
+                <div key={peerId} className="mb-4">
+                  <table className="w-full">
+                    <thead className="sticky top-0 bg-card z-10">
+                      <tr className="text-left border-b border-gray-200 dark:border-white/10 bg-surface">
+                        <th className="font-semibold">{peerId}</th>
+                      </tr>
+                    </thead>
+                    <tbody>
+                      {models.map((model) => (
+                        <tr key={model.id} className="border-b hover:bg-secondary-hover border-gray-200">
+                          <td className={`pl-8 ${model.unlisted ? "text-txtsecondary" : ""}`}>
+                            <span>{model.id}</span>
+                          </td>
+                        </tr>
+                      ))}
+                    </tbody>
+                  </table>
+                </div>
+              ))}
+          </>
+        )}
      </div>
    </div>
  );
@@ -223,11 +267,7 @@ function TokenHistogram({ data }: { data: HistogramData }) {

  return (
    <div className="mt-2 w-full">
-      <svg
-        viewBox={`0 0 ${viewBoxWidth} ${height}`}
-        className="w-full h-auto"
-        preserveAspectRatio="xMidYMid meet"
-      >
+      <svg viewBox={`0 0 ${viewBoxWidth} ${height}`} className="w-full h-auto" preserveAspectRatio="xMidYMid meet">
        {/* Y-axis */}
        <line
          x1={padding.left}
@@ -312,14 +352,7 @@ function TokenHistogram({ data }: { data: HistogramData }) {
        />

        {/* X-axis labels */}
-        <text
-          x={padding.left}
-          y={height - 5}
-          fontSize="10"
-          fill="currentColor"
-          opacity="0.6"
-          textAnchor="start"
-        >
+        <text x={padding.left} y={height - 5} fontSize="10" fill="currentColor" opacity="0.6" textAnchor="start">
          {min.toFixed(1)}
        </text>
Author	SHA1	Message	Date
Benson Wong	b73f367f22	config-schema.json,config.example.yaml: Update examples and schema	2026-01-16 22:43:25 -08:00
Benson Wong	8f2137c72b	config: support environment variable macros in apiKeys (#467 ) Add substituteEnvMacros support for apiKeys configuration field, allowing API keys to be loaded from environment variables using the ${env.VAR_NAME} syntax. - Apply env macro substitution before validation - Add tests for env macro substitution in apiKeys	2026-01-16 22:41:14 -08:00
Benson Wong	124007cc98	config: add environment variable macros (#466 ) * config: add environment variable macros Add support for ${env.VAR_NAME} syntax to pull values from system environment variables during config loading. - env macros processed before regular macros (allows macros to reference env vars) - works in cmd, cmdStop, proxy, checkEndpoint, filters.stripParams, metadata - returns error if env var is not set - add comprehensive tests fixes #462 * docs: add env macro example to config.example.yaml	2026-01-16 22:25:20 -08:00
Benson Wong	eb5bfff0b0	proxy: unify filtering for local models and peers This unifies the filtering capabilities for models and peers - stripParams: removes params in the request - setParams: sets params in the request fixes #453	2026-01-15 18:59:43 -08:00
Benson Wong	3edb180c08	ci: free up disk space before ROCm container build (#460 )	2026-01-14 22:03:42 -08:00
Benson Wong	66d555e625	Improve container build reliability (#457 ) * docker: add .env usage in build-container.sh * .github,docker: add rocm, improve logging * .github,CLAUDE.md: fix workflow and update guidelines Update containers workflow to only push images when triggered manually or on schedule, not on workflow file changes. - add push trigger for workflow file changes in containers.yml - update push condition to skip on regular push events - update CLAUDE.md commit message guidelines * docker: remove comma in build-container.sh * .github,docker: improve container build workflow Add pagination support for fetching llama.cpp tags and improve debugging. - add build-container.sh to workflow trigger paths - implement fetch_llama_tag() with pagination support - replace .env with local testing instructions - add DEBUG_ABORT_BUILD flag for testing	2026-01-10 22:14:33 -08:00
Benson Wong	4f863fd9fc	CLAUDE.md: tweak instructions	2026-01-09 21:42:06 -08:00
Benson Wong	267c030457	ui: update react-router-dom to 7.12.0 (#456 ) Update react-router-dom from 7.6.2 to 7.12.0 to address security vulnerability. - Updated dependency in package.json - Regenerated package-lock.json - Verified build passes successfully - Confirmed 0 vulnerabilities with npm audit Co-authored-by: Claude <noreply@anthropic.com>	2026-01-08 16:13:09 -08:00
Benson Wong	c19309fe7e	CLAUDE.md: small instruction tweaks	2026-01-07 21:34:23 -08:00
Benson Wong	4413881b2d	proxy: actually add /v1/responses endpoint (#449 ) ref: #448	2026-01-01 13:35:45 -08:00
Benson Wong	8df5e8563b	proxy: add /v1/responses and /v1/audio/voices endpoints (#448 ) Updates #433 Fixes #442 #226	2026-01-01 12:52:12 -08:00
Benson Wong	7931212d3e	proxy: add v1/images/edits API endpoint (#447 ) Updates #433	2026-01-01 12:43:06 -08:00
Benson Wong	3dc36032fb	proxy: skip very slow tests in -short test mode (#446 ) * proxy: skip very slow tests in -short test mode * CLAUDE.md: update testing instructions	2025-12-31 14:08:56 -08:00
Benson Wong	addb98646f	proxy: add support for basic authorization (#445 ) Fixes #444 where the UI with api keys did not work. The choice to use http basic authorization is for simple, automatic browser support. No changes to the UI were necessary. Just use an API key as the password, no user name is required.	2025-12-31 13:42:35 -08:00
Benson Wong	37d74efc2d	proxy: add /v1/images/generations (#443 ) Add support for the /v1/images/generations endpoint Updates #433 Closes #191	2025-12-30 21:04:58 -08:00
Benson Wong	22e098ac8b	Add Peer Model Support (#438 ) This PR allows a single llama-swap to be the central proxy for models served by other inference servers. The peer servers can be another llama-swap or any API that supports the /v1/* inference endpoint. Updates: #433, #299 Closes: #296	2025-12-27 20:18:06 -08:00
Benson Wong	9864f9f517	.coderabbit.yaml: disable annoying features	2025-12-23 23:53:06 -08:00
Benson Wong	53b32f3601	proxy: add API key support (#436 ) Add configuration support for api keys that are enforced by llama-swap. Keys are stripped before sending them to upstream servers. Updates: #433, #50 and #251	2025-12-23 23:39:33 -08:00
Benson Wong	565c44766d	config,proxy: add new configuration logToStdout (#432 ) The new logToStdout option controls what is logged to stdout. The default has been changed to just the proxy logs, which contain swap and http request logs. There are four supported settings: none, proxy, upstream, both. The "both" setting is the legacy setting where everything was spewed to stdout.	2025-12-21 22:23:31 -08:00
Benson Wong	e6a9e210ba	proxy: fix path bug in /logs/stream/{model_id} (#431 ) A {model_id} containing a forward slash trips up gin's path param parsing. This updates /logs/stream to work like /upstream where the model_id is built up in parts and searched for in the configuration. Updates #421	2025-12-21 21:47:14 -08:00