feat(providers): add Chutes AI support

config/config.example.yaml

@@ -380,6 +380,12 @@ providers:
     # models:
     #   - id: "accounts/fireworks/models/gpt-oss-120b"
 
+  chutes:
+    type: chutes
+    api_key: "${CHUTES_API_KEY}"
+    # base_url defaults to "https://llm.chutes.ai/v1".
+    # Set base_url when using a different compatible endpoint.
+
   meta:
     type: meta
     api_key: "..."

docs/advanced/configuration.mdx

@@ -276,14 +276,15 @@ Set these to automatically register providers. No YAML configuration required.
 | `ZAI_API_KEY`        | Z.ai                                               |
 | `XAI_API_KEY`        | xAI (Grok)                                         |
 | `GROQ_API_KEY`       | Groq                                               |
+| `CHUTES_API_KEY`     | Chutes AI (`CHUTES_BASE_URL` optional)             |
 | `AZURE_API_KEY`      | Azure OpenAI (`AZURE_BASE_URL` also required)     |
 | `ORACLE_API_KEY`     | Oracle GenAI (`ORACLE_BASE_URL` also required)    |
 | `OLLAMA_BASE_URL`    | Ollama (no API key needed)                        |
 | `SGLANG_BASE_URL`    | SGLang (no API key needed unless upstream requires) |
 | `VLLM_BASE_URL`      | vLLM (no API key needed unless upstream requires) |
 | `LLMD_BASE_URL`      | llm-d Router/EPP (no API key needed unless its Gateway requires one) |
 
-Most providers can use a custom base URL via `<PROVIDER>_BASE_URL` (for example `OPENAI_BASE_URL`). DeepSeek defaults to `https://api.deepseek.com`; set `DEEPSEEK_BASE_URL` only for a compatible proxy or alternate DeepSeek endpoint. OpenRouter defaults to `https://openrouter.ai/api/v1` and can be overridden with `OPENROUTER_BASE_URL`. Kilo AI defaults to `https://api.kilo.ai/api/gateway` and can be overridden with `KILO_BASE_URL`. Z.ai defaults to `https://api.z.ai/api/paas/v4`; set `ZAI_BASE_URL=https://api.z.ai/api/coding/paas/v4` for the GLM Coding Plan endpoint. SGLang defaults to `http://localhost:30000/v1` when `SGLANG_API_KEY` is set, but keyless deployments should set `SGLANG_BASE_URL` explicitly to register the provider. vLLM follows the same pattern at `http://localhost:8000/v1`. llm-d has no universal endpoint, so `LLMD_BASE_URL` is always required; `LLMD_API_KEY` is optional. Azure uses `AZURE_BASE_URL` for its deployment base URL and accepts an optional `AZURE_API_VERSION` override; otherwise it defaults to `2024-10-21`. Oracle requires `ORACLE_BASE_URL` because its OpenAI-compatible endpoint is region-specific.
+Most providers can use a custom base URL via `<PROVIDER>_BASE_URL` (for example `OPENAI_BASE_URL`). Chutes AI defaults to `https://llm.chutes.ai/v1` and can be overridden with `CHUTES_BASE_URL`. DeepSeek defaults to `https://api.deepseek.com`; set `DEEPSEEK_BASE_URL` only for a compatible proxy or alternate DeepSeek endpoint. OpenRouter defaults to `https://openrouter.ai/api/v1` and can be overridden with `OPENROUTER_BASE_URL`. Kilo AI defaults to `https://api.kilo.ai/api/gateway` and can be overridden with `KILO_BASE_URL`. Z.ai defaults to `https://api.z.ai/api/paas/v4`; set `ZAI_BASE_URL=https://api.z.ai/api/coding/paas/v4` for the GLM Coding Plan endpoint. SGLang defaults to `http://localhost:30000/v1` when `SGLANG_API_KEY` is set, but keyless deployments should set `SGLANG_BASE_URL` explicitly to register the provider. vLLM follows the same pattern at `http://localhost:8000/v1`. llm-d has no universal endpoint, so `LLMD_BASE_URL` is always required; `LLMD_API_KEY` is optional. Azure uses `AZURE_BASE_URL` for its deployment base URL and accepts an optional `AZURE_API_VERSION` override; otherwise it defaults to `2024-10-21`. Oracle requires `ORACLE_BASE_URL` because its OpenAI-compatible endpoint is region-specific.
 
 Every provider type also accepts a comma-separated configured model list via
 `<PROVIDER>_MODELS`, for example `OPENROUTER_MODELS`, `ORACLE_MODELS`,
@@ -409,6 +410,7 @@ export GEMINI_API_KEY="..."          # Registers "gemini" provider
 export DEEPSEEK_API_KEY="..."        # Registers "deepseek" provider
 export XAI_API_KEY="..."             # Registers "xai" provider
 export GROQ_API_KEY="gsk_..."        # Registers "groq" provider
+export CHUTES_API_KEY="cpk_..."      # Registers "chutes" provider
 export OPENROUTER_API_KEY="sk-or-..." # Registers "openrouter" provider
 export KILO_API_KEY="..."            # Registers "kilo" provider
 export ZAI_API_KEY="..."             # Registers "zai" provider

docs/features/passthrough-api.mdx

@@ -133,6 +133,10 @@ Passthrough is intentionally narrow while the API is in beta.
 
 - `openai`, `anthropic`, `openrouter`, `kilo`, `zai`, `sglang`, `vllm`, `llmd`, and `deepseek` are enabled by
   default.
+- Chutes supports passthrough but requires explicit operator opt-in because
+  passthrough can forward provider-native routes that do not identify a model.
+  Add `chutes` to `ENABLED_PASSTHROUGH_PROVIDERS` only when you intend to expose
+  that surface.
 - GoModel does not translate passthrough request bodies or response bodies.
 - Provider-native error bodies and status codes are proxied instead of converted
   into OpenAI-compatible responses.

docs/providers/overview.mdx

@@ -48,6 +48,7 @@ support, not every individual model capability exposed by an upstream provider.
 | DeepSeek | `DEEPSEEK_API_KEY` | `deepseek-v4-pro` | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | [DeepSeek](/providers/deepseek) |
 | Groq | `GROQ_API_KEY` | `llama-3.3-70b-versatile` | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | — |
 | Fireworks AI | `FIREWORKS_API_KEY` (`FIREWORKS_BASE_URL` optional) | `accounts/fireworks/models/gpt-oss-120b` | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | — |
+| Chutes AI | `CHUTES_API_KEY` (`CHUTES_BASE_URL` optional) | `Qwen/Qwen3-32B-TEE` | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | — |
 | Meta (Muse Spark) | `META_API_KEY` (`META_BASE_URL` optional) | `muse-spark-1.1` | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | — |
 | OpenRouter | `OPENROUTER_API_KEY` | `google/gemini-2.5-flash` | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — |
 | Kilo AI | `KILO_API_KEY` (`KILO_BASE_URL` optional) | `anthropic/claude-sonnet-4.5` | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | — |
@@ -90,6 +91,12 @@ support, not every individual model capability exposed by an upstream provider.
 - **Fireworks AI** — model IDs are account-scoped paths such as
   `accounts/fireworks/models/gpt-oss-120b`; use them verbatim in requests and
   in `FIREWORKS_MODELS`.
+- **Chutes AI** — defaults to `https://llm.chutes.ai/v1` and discovers its
+  current model IDs, context limits, capabilities, and pricing from the live
+  catalog. GoModel translates `/v1/responses` requests to chat completions;
+  Chutes' shared LLM endpoint does not expose embeddings. Passthrough support
+  requires explicit operator opt-in by adding `chutes` to
+  `ENABLED_PASSTHROUGH_PROVIDERS`.
 - **Meta (Muse Spark)** — the Meta Model API is OpenAI-compatible; set
   `META_API_KEY` and route to `muse-spark-1.1`. Muse Spark models are not in
   the upstream model catalog yet, so declare `context_window` and `pricing`

internal/providers/chutes/chutes.go

@@ -0,0 +1,99 @@
+// Package chutes provides Chutes AI integration for the LLM gateway.
+package chutes
+
+import (
+	"context"
+	"io"
+	"net/http"
+
+	"github.com/enterpilot/gomodel/internal/core"
+	"github.com/enterpilot/gomodel/internal/llmclient"
+	"github.com/enterpilot/gomodel/internal/providers"
+	"github.com/enterpilot/gomodel/internal/providers/openai"
+)
+
+const defaultBaseURL = "https://llm.chutes.ai/v1"
+
+// Registration provides factory registration for the Chutes AI provider.
+var Registration = providers.Registration{
+	Type: "chutes",
+	New:  New,
+	Discovery: providers.DiscoveryConfig{
+		DefaultBaseURL: defaultBaseURL,
+	},
+}
+
+// Provider implements Chutes' OpenAI-compatible chat surface. Chutes does not
+// expose native Responses or embeddings endpoints, so Responses requests are
+// translated through chat completions and embeddings fail locally.
+type Provider struct {
+	compat *openai.CompatibleProvider
+}
+
+var _ core.Provider = (*Provider)(nil)
+var _ core.PassthroughProvider = (*Provider)(nil)
+
+// New creates a new Chutes AI provider.
+func New(cfg providers.ProviderConfig, opts providers.ProviderOptions) core.Provider {
+	return &Provider{compat: openai.NewCompatibleProvider(cfg.APIKey, opts, compatibleConfig(
+		providers.ResolveBaseURL(cfg.BaseURL, defaultBaseURL),
+	))}
+}
+
+// NewWithHTTPClient creates a new Chutes AI provider with a custom HTTP client.
+// If httpClient is nil, http.DefaultClient is used.
+func NewWithHTTPClient(apiKey string, baseURL string, httpClient *http.Client, hooks llmclient.Hooks) *Provider {
+	return &Provider{compat: openai.NewCompatibleProviderWithHTTPClient(apiKey, httpClient, hooks, compatibleConfig(
+		providers.ResolveBaseURL(baseURL, defaultBaseURL),
+	))}
+}
+
+// compatibleConfig returns the shared OpenAI-compatible transport settings for Chutes.
+func compatibleConfig(baseURL string) openai.CompatibleProviderConfig {
+	return openai.CompatibleProviderConfig{
+		ProviderName: "chutes",
+		BaseURL:      baseURL,
+		SetHeaders:   setHeaders,
+	}
+}
+
+// setHeaders applies Chutes' bearer-token authentication.
+func setHeaders(req *http.Request, apiKey string) {
+	providers.SetAuthHeaders(req, apiKey, providers.AuthHeaderConfig{AuthScheme: "Bearer "})
+}
+
+// SetBaseURL changes the Chutes API base URL.
+func (p *Provider) SetBaseURL(baseURL string) {
+	p.compat.SetBaseURL(baseURL)
+}
+
+// ChatCompletion sends a chat completion request to Chutes.
+func (p *Provider) ChatCompletion(ctx context.Context, req *core.ChatRequest) (*core.ChatResponse, error) {
+	return p.compat.ChatCompletion(ctx, req)
+}
+
+// StreamChatCompletion sends a streaming chat completion request to Chutes.
+func (p *Provider) StreamChatCompletion(ctx context.Context, req *core.ChatRequest) (io.ReadCloser, error) {
+	return p.compat.StreamChatCompletion(ctx, req)
+}
+
+// Responses translates an OpenAI Responses request through Chutes chat completions.
+func (p *Provider) Responses(ctx context.Context, req *core.ResponsesRequest) (*core.ResponsesResponse, error) {
+	return providers.ResponsesViaChat(ctx, p, req)
+}
+
+// StreamResponses translates a streaming Responses request through Chutes chat completions.
+func (p *Provider) StreamResponses(ctx context.Context, req *core.ResponsesRequest) (io.ReadCloser, error) {
+	return providers.StreamResponsesViaChat(ctx, p, req, "chutes")
+}
+
+// Embeddings returns an error because the shared Chutes LLM endpoint does not
+// expose an OpenAI-compatible embeddings route.
+func (p *Provider) Embeddings(_ context.Context, _ *core.EmbeddingRequest) (*core.EmbeddingResponse, error) {
+	return nil, core.NewInvalidRequestError("chutes does not support embeddings", nil)
+}
+
+// Passthrough forwards an opaque request to Chutes.
+func (p *Provider) Passthrough(ctx context.Context, req *core.PassthroughRequest) (*core.PassthroughResponse, error) {
+	return p.compat.Passthrough(ctx, req)
+}