feat: Add support for OpenRouter (#92)

* Add support for OpenRouter as a new model provider

- Introduced `ProviderOpenRouter` in the `models` package.
- Added OpenRouter-specific models, including `GPT41`, `GPT41Mini`, `GPT4o`, and others, with their configurations and costs.
- Updated `generateSchema` to include OpenRouter as a provider.
- Added OpenRouter-specific environment variable handling (`OPENROUTER_API_KEY`) in `config.go`.
- Implemented default model settings for OpenRouter agents in `setDefaultModelForAgent`.
- Updated `getProviderAPIKey` to retrieve the OpenRouter API key.
- Extended `SupportedModels` to include OpenRouter models.
- Added OpenRouter client initialization in the `provider` package.
- Modified `processGeneration` to handle `FinishReasonUnknown` in addition to `FinishReasonToolUse`.

* [feature/openrouter-provider] Add new models and provider to schema

- Added "deepseek-chat-free" and "deepseek-r1-free" to the list of supported models in `opencode-schema.json`.

* [feature/openrouter-provider] Add OpenRouter provider support and integrate new models

- Updated README.md to include OpenRouter as a supported provider and its configuration details.
- Added `OPENROUTER_API_KEY` to environment variable configuration.
- Introduced OpenRouter-specific models in `internal/llm/models/openrouter.go` with mappings to existing cost and token configurations.
- Updated `internal/config/config.go` to set default models for OpenRouter agents.
- Extended `opencode-schema.json` to include OpenRouter models in the schema definitions.
- Refactored model IDs and names to align with OpenRouter naming conventions.

* [feature/openrouter-provider] Refactor finish reason handling and tool call logic in agent and OpenAI provider

- Simplified finish reason check in `agent.go` by removing redundant variable assignment.
- Updated `openai.go` to override the finish reason to `FinishReasonToolUse` when tool calls are present.
- Ensured consistent finish reason handling in both `send` and `stream` methods of the OpenAI provider.

[feature/openrouter-provider] Refactor finish reason handling and tool call logic in agent and OpenAI provider

- Simplified finish reason check in `agent.go` by removing redundant variable assignment.
- Updated `openai.go` to override the finish reason to `FinishReasonToolUse` when tool calls are present.
- Ensured consistent finish reason handling in both `send` and `stream` methods of the OpenAI provider.

* **[feature/openrouter-provider] Add support for custom headers in OpenAI client configuration**

- Introduced a new `extraHeaders` field in the `openaiOptions` struct to allow specifying additional HTTP headers.
- Added logic in `newOpenAIClient` to apply `extraHeaders` to the OpenAI client configuration.
- Implemented a new option function `WithOpenAIExtraHeaders` to set custom headers in `openaiOptions`.
- Updated the OpenRouter provider configuration in `NewProvider` to include default headers (`HTTP-Referer` and `X-Title`) for OpenRouter API requests.

* Update OpenRouter model config and remove unsupported models

* [feature/openrouter-provider] Update OpenRouter models and default configurations

- Added new OpenRouter models: `claude-3.5-sonnet`, `claude-3-haiku`, `claude-3.7-sonnet`, `claude-3.5-haiku`, and `claude-3-opus` in `openrouter.go`.
- Updated default agent models in `config.go`:
  - `agents.coder.model` now uses `claude-3.7-sonnet`.
  - `agents.task.model` now uses `claude-3.7-sonnet`.
  - `agents.title.model` now uses `claude-3.5-haiku`.
- Updated `opencode-schema.json` to include the new models in the allowed list for schema validation.
- Adjusted logic in `setDefaultModelForAgent` to reflect the new default models.

* [feature/openrouter-provider] Remove unused ProviderEvent emission in stream function

The changes remove the emission of a `ProviderEvent` with type `EventContentStop` in the `stream` function of the `openaiClient` implementation. This event was sent upon successful stream completion but is no longer used.

README.md

@@ -11,7 +11,7 @@ OpenCode is a Go-based CLI application that brings AI assistance to your termina
 ## Features
 
 - **Interactive TUI**: Built with [Bubble Tea](https://github.com/charmbracelet/bubbletea) for a smooth terminal experience
-- **Multiple AI Providers**: Support for OpenAI, Anthropic Claude, Google Gemini, AWS Bedrock, Groq, and Azure OpenAI
+- **Multiple AI Providers**: Support for OpenAI, Anthropic Claude, Google Gemini, AWS Bedrock, Groq, Azure OpenAI, and OpenRouter
 - **Session Management**: Save and manage multiple conversation sessions
 - **Tool Integration**: AI can execute commands, search files, and modify code
 - **Vim-like Editor**: Integrated editor with text input capabilities
@@ -97,8 +97,12 @@ You can configure OpenCode using environment variables:
       "disabled": false
     },
     "groq": {
-        "apiKey": "your-api-key",
-        "disabled": false
+      "apiKey": "your-api-key",
+      "disabled": false
+    },
+    "openrouter": {
+      "apiKey": "your-api-key",
+      "disabled": false
     }
   },
   "agents": {

cmd/schema/main.go

@@ -173,6 +173,7 @@ func generateSchema() map[string]any {
 		string(models.ProviderOpenAI),
 		string(models.ProviderGemini),
 		string(models.ProviderGROQ),
+		string(models.ProviderOpenRouter),
 		string(models.ProviderBedrock),
 		string(models.ProviderAzure),
 	}

internal/config/config.go

@@ -267,6 +267,15 @@ func setProviderDefaults() {
 		return
 	}
 
+	// OpenRouter configuration
+	if apiKey := os.Getenv("OPENROUTER_API_KEY"); apiKey != "" {
+		viper.SetDefault("providers.openrouter.apiKey", apiKey)
+		viper.SetDefault("agents.coder.model", models.OpenRouterClaude37Sonnet)
+		viper.SetDefault("agents.task.model", models.OpenRouterClaude37Sonnet)
+		viper.SetDefault("agents.title.model", models.OpenRouterClaude35Haiku)
+		return
+	}
+
 	// AWS Bedrock configuration
 	if hasAWSCredentials() {
 		viper.SetDefault("agents.coder.model", models.BedrockClaude37Sonnet)
@@ -527,6 +536,8 @@ func getProviderAPIKey(provider models.ModelProvider) string {
 		return os.Getenv("GROQ_API_KEY")
 	case models.ProviderAzure:
 		return os.Getenv("AZURE_OPENAI_API_KEY")
+	case models.ProviderOpenRouter:
+		return os.Getenv("OPENROUTER_API_KEY")
 	case models.ProviderBedrock:
 		if hasAWSCredentials() {
 			return "aws-credentials-available"
@@ -578,6 +589,34 @@ func setDefaultModelForAgent(agent AgentName) bool {
 		return true
 	}
 
+	if apiKey := os.Getenv("OPENROUTER_API_KEY"); apiKey != "" {
+		var model models.ModelID
+		maxTokens := int64(5000)
+		reasoningEffort := ""
+
+		switch agent {
+		case AgentTitle:
+			model = models.OpenRouterClaude35Haiku
+			maxTokens = 80
+		case AgentTask:
+			model = models.OpenRouterClaude37Sonnet
+		default:
+			model = models.OpenRouterClaude37Sonnet
+		}
+
+		// Check if model supports reasoning
+		if modelInfo, ok := models.SupportedModels[model]; ok && modelInfo.CanReason {
+			reasoningEffort = "medium"
+		}
+
+		cfg.Agents[agent] = Agent{
+			Model:           model,
+			MaxTokens:       maxTokens,
+			ReasoningEffort: reasoningEffort,
+		}
+		return true
+	}
+
 	if apiKey := os.Getenv("GEMINI_API_KEY"); apiKey != "" {
 		var model models.ModelID
 		maxTokens := int64(5000)

internal/llm/models/models.go

@@ -86,4 +86,5 @@ func init() {
 	maps.Copy(SupportedModels, GeminiModels)
 	maps.Copy(SupportedModels, GroqModels)
 	maps.Copy(SupportedModels, AzureModels)
+	maps.Copy(SupportedModels, OpenRouterModels)
 }

internal/llm/models/openrouter.go

@@ -0,0 +1,262 @@
+package models
+
+const (
+	ProviderOpenRouter ModelProvider = "openrouter"
+
+	OpenRouterGPT41          ModelID = "openrouter.gpt-4.1"
+	OpenRouterGPT41Mini      ModelID = "openrouter.gpt-4.1-mini"
+	OpenRouterGPT41Nano      ModelID = "openrouter.gpt-4.1-nano"
+	OpenRouterGPT45Preview   ModelID = "openrouter.gpt-4.5-preview"
+	OpenRouterGPT4o          ModelID = "openrouter.gpt-4o"
+	OpenRouterGPT4oMini      ModelID = "openrouter.gpt-4o-mini"
+	OpenRouterO1             ModelID = "openrouter.o1"
+	OpenRouterO1Pro          ModelID = "openrouter.o1-pro"
+	OpenRouterO1Mini         ModelID = "openrouter.o1-mini"
+	OpenRouterO3             ModelID = "openrouter.o3"
+	OpenRouterO3Mini         ModelID = "openrouter.o3-mini"
+	OpenRouterO4Mini         ModelID = "openrouter.o4-mini"
+	OpenRouterGemini25Flash  ModelID = "openrouter.gemini-2.5-flash"
+	OpenRouterGemini25       ModelID = "openrouter.gemini-2.5"
+	OpenRouterClaude35Sonnet ModelID = "openrouter.claude-3.5-sonnet"
+	OpenRouterClaude3Haiku   ModelID = "openrouter.claude-3-haiku"
+	OpenRouterClaude37Sonnet ModelID = "openrouter.claude-3.7-sonnet"
+	OpenRouterClaude35Haiku  ModelID = "openrouter.claude-3.5-haiku"
+	OpenRouterClaude3Opus    ModelID = "openrouter.claude-3-opus"
+)
+
+var OpenRouterModels = map[ModelID]Model{
+	OpenRouterGPT41: {
+		ID:                 OpenRouterGPT41,
+		Name:               "OpenRouter – GPT 4.1",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4.1",
+		CostPer1MIn:        OpenAIModels[GPT41].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT41].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT41].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT41].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT41].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT41].DefaultMaxTokens,
+	},
+	OpenRouterGPT41Mini: {
+		ID:                 OpenRouterGPT41Mini,
+		Name:               "OpenRouter – GPT 4.1 mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4.1-mini",
+		CostPer1MIn:        OpenAIModels[GPT41Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT41Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT41Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT41Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT41Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT41Mini].DefaultMaxTokens,
+	},
+	OpenRouterGPT41Nano: {
+		ID:                 OpenRouterGPT41Nano,
+		Name:               "OpenRouter – GPT 4.1 nano",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4.1-nano",
+		CostPer1MIn:        OpenAIModels[GPT41Nano].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT41Nano].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT41Nano].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT41Nano].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT41Nano].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT41Nano].DefaultMaxTokens,
+	},
+	OpenRouterGPT45Preview: {
+		ID:                 OpenRouterGPT45Preview,
+		Name:               "OpenRouter – GPT 4.5 preview",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4.5-preview",
+		CostPer1MIn:        OpenAIModels[GPT45Preview].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT45Preview].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT45Preview].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT45Preview].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT45Preview].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT45Preview].DefaultMaxTokens,
+	},
+	OpenRouterGPT4o: {
+		ID:                 OpenRouterGPT4o,
+		Name:               "OpenRouter – GPT 4o",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4o",
+		CostPer1MIn:        OpenAIModels[GPT4o].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT4o].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT4o].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT4o].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT4o].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT4o].DefaultMaxTokens,
+	},
+	OpenRouterGPT4oMini: {
+		ID:                 OpenRouterGPT4oMini,
+		Name:               "OpenRouter – GPT 4o mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4o-mini",
+		CostPer1MIn:        OpenAIModels[GPT4oMini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT4oMini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT4oMini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT4oMini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT4oMini].ContextWindow,
+	},
+	OpenRouterO1: {
+		ID:                 OpenRouterO1,
+		Name:               "OpenRouter – O1",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o1",
+		CostPer1MIn:        OpenAIModels[O1].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O1].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O1].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O1].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O1].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O1].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O1].CanReason,
+	},
+	OpenRouterO1Pro: {
+		ID:                 OpenRouterO1Pro,
+		Name:               "OpenRouter – o1 pro",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o1-pro",
+		CostPer1MIn:        OpenAIModels[O1Pro].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O1Pro].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O1Pro].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O1Pro].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O1Pro].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O1Pro].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O1Pro].CanReason,
+	},
+	OpenRouterO1Mini: {
+		ID:                 OpenRouterO1Mini,
+		Name:               "OpenRouter – o1 mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o1-mini",
+		CostPer1MIn:        OpenAIModels[O1Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O1Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O1Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O1Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O1Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O1Mini].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O1Mini].CanReason,
+	},
+	OpenRouterO3: {
+		ID:                 OpenRouterO3,
+		Name:               "OpenRouter – o3",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o3",
+		CostPer1MIn:        OpenAIModels[O3].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O3].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O3].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O3].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O3].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O3].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O3].CanReason,
+	},
+	OpenRouterO3Mini: {
+		ID:                 OpenRouterO3Mini,
+		Name:               "OpenRouter – o3 mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o3-mini-high",
+		CostPer1MIn:        OpenAIModels[O3Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O3Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O3Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O3Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O3Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O3Mini].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O3Mini].CanReason,
+	},
+	OpenRouterO4Mini: {
+		ID:                 OpenRouterO4Mini,
+		Name:               "OpenRouter – o4 mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o4-mini-high",
+		CostPer1MIn:        OpenAIModels[O4Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O4Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O4Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O4Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O4Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O4Mini].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O4Mini].CanReason,
+	},
+	OpenRouterGemini25Flash: {
+		ID:                 OpenRouterGemini25Flash,
+		Name:               "OpenRouter – Gemini 2.5 Flash",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "google/gemini-2.5-flash-preview:thinking",
+		CostPer1MIn:        GeminiModels[Gemini25Flash].CostPer1MIn,
+		CostPer1MInCached:  GeminiModels[Gemini25Flash].CostPer1MInCached,
+		CostPer1MOut:       GeminiModels[Gemini25Flash].CostPer1MOut,
+		CostPer1MOutCached: GeminiModels[Gemini25Flash].CostPer1MOutCached,
+		ContextWindow:      GeminiModels[Gemini25Flash].ContextWindow,
+		DefaultMaxTokens:   GeminiModels[Gemini25Flash].DefaultMaxTokens,
+	},
+	OpenRouterGemini25: {
+		ID:                 OpenRouterGemini25,
+		Name:               "OpenRouter – Gemini 2.5 Pro",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "google/gemini-2.5-pro-preview-03-25",
+		CostPer1MIn:        GeminiModels[Gemini25].CostPer1MIn,
+		CostPer1MInCached:  GeminiModels[Gemini25].CostPer1MInCached,
+		CostPer1MOut:       GeminiModels[Gemini25].CostPer1MOut,
+		CostPer1MOutCached: GeminiModels[Gemini25].CostPer1MOutCached,
+		ContextWindow:      GeminiModels[Gemini25].ContextWindow,
+		DefaultMaxTokens:   GeminiModels[Gemini25].DefaultMaxTokens,
+	},
+	OpenRouterClaude35Sonnet: {
+		ID:                 OpenRouterClaude35Sonnet,
+		Name:               "OpenRouter – Claude 3.5 Sonnet",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3.5-sonnet",
+		CostPer1MIn:        AnthropicModels[Claude35Sonnet].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude35Sonnet].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude35Sonnet].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude35Sonnet].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude35Sonnet].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude35Sonnet].DefaultMaxTokens,
+	},
+	OpenRouterClaude3Haiku: {
+		ID:                 OpenRouterClaude3Haiku,
+		Name:               "OpenRouter – Claude 3 Haiku",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3-haiku",
+		CostPer1MIn:        AnthropicModels[Claude3Haiku].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude3Haiku].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude3Haiku].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude3Haiku].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude3Haiku].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude3Haiku].DefaultMaxTokens,
+	},
+	OpenRouterClaude37Sonnet: {
+		ID:                 OpenRouterClaude37Sonnet,
+		Name:               "OpenRouter – Claude 3.7 Sonnet",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3.7-sonnet",
+		CostPer1MIn:        AnthropicModels[Claude37Sonnet].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude37Sonnet].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude37Sonnet].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude37Sonnet].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude37Sonnet].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude37Sonnet].DefaultMaxTokens,
+		CanReason:          AnthropicModels[Claude37Sonnet].CanReason,
+	},
+	OpenRouterClaude35Haiku: {
+		ID:                 OpenRouterClaude35Haiku,
+		Name:               "OpenRouter – Claude 3.5 Haiku",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3.5-haiku",
+		CostPer1MIn:        AnthropicModels[Claude35Haiku].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude35Haiku].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude35Haiku].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude35Haiku].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude35Haiku].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude35Haiku].DefaultMaxTokens,
+	},
+	OpenRouterClaude3Opus: {
+		ID:                 OpenRouterClaude3Opus,
+		Name:               "OpenRouter – Claude 3 Opus",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3-opus",
+		CostPer1MIn:        AnthropicModels[Claude3Opus].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude3Opus].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude3Opus].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude3Opus].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude3Opus].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude3Opus].DefaultMaxTokens,
+	},
+}

internal/llm/provider/openai.go

@@ -21,6 +21,7 @@ type openaiOptions struct {
 	baseURL         string
 	disableCache    bool
 	reasoningEffort string
+	extraHeaders    map[string]string
 }
 
 type OpenAIOption func(*openaiOptions)
@@ -49,6 +50,12 @@ func newOpenAIClient(opts providerClientOptions) OpenAIClient {
 		openaiClientOptions = append(openaiClientOptions, option.WithBaseURL(openaiOpts.baseURL))
 	}
 
+	if openaiOpts.extraHeaders != nil {
+		for key, value := range openaiOpts.extraHeaders {
+			openaiClientOptions = append(openaiClientOptions, option.WithHeader(key, value))
+		}
+	}
+
 	client := openai.NewClient(openaiClientOptions...)
 	return &openaiClient{
 		providerOptions: opts,
@@ -204,11 +211,18 @@ func (o *openaiClient) send(ctx context.Context, messages []message.Message, too
 			content = openaiResponse.Choices[0].Message.Content
 		}
 
+		toolCalls := o.toolCalls(*openaiResponse)
+		finishReason := o.finishReason(string(openaiResponse.Choices[0].FinishReason))
+
+		if len(toolCalls) > 0 {
+			finishReason = message.FinishReasonToolUse
+		}
+
 		return &ProviderResponse{
 			Content:      content,
-			ToolCalls:    o.toolCalls(*openaiResponse),
+			ToolCalls:    toolCalls,
 			Usage:        o.usage(*openaiResponse),
-			FinishReason: o.finishReason(string(openaiResponse.Choices[0].FinishReason)),
+			FinishReason: finishReason,
 		}, nil
 	}
 }
@@ -267,13 +281,19 @@ func (o *openaiClient) stream(ctx context.Context, messages []message.Message, t
 			err := openaiStream.Err()
 			if err == nil || errors.Is(err, io.EOF) {
 				// Stream completed successfully
+				finishReason := o.finishReason(string(acc.ChatCompletion.Choices[0].FinishReason))
+
+				if len(toolCalls) > 0 {
+					finishReason = message.FinishReasonToolUse
+				}
+
 				eventChan <- ProviderEvent{
 					Type: EventComplete,
 					Response: &ProviderResponse{
 						Content:      currentContent,
 						ToolCalls:    toolCalls,
 						Usage:        o.usage(acc.ChatCompletion),
-						FinishReason: o.finishReason(string(acc.ChatCompletion.Choices[0].FinishReason)),
+						FinishReason: finishReason,
 					},
 				}
 				close(eventChan)
@@ -375,6 +395,12 @@ func WithOpenAIBaseURL(baseURL string) OpenAIOption {
 	}
 }
 
+func WithOpenAIExtraHeaders(headers map[string]string) OpenAIOption {
+	return func(options *openaiOptions) {
+		options.extraHeaders = headers
+	}
+}
+
 func WithOpenAIDisableCache() OpenAIOption {
 	return func(options *openaiOptions) {
 		options.disableCache = true

internal/llm/provider/provider.go

@@ -120,6 +120,18 @@ func NewProvider(providerName models.ModelProvider, opts ...ProviderClientOption
 			options: clientOptions,
 			client:  newAzureClient(clientOptions),
 		}, nil
+	case models.ProviderOpenRouter:
+		clientOptions.openaiOptions = append(clientOptions.openaiOptions,
+			WithOpenAIBaseURL("https://openrouter.ai/api/v1"),
+			WithOpenAIExtraHeaders(map[string]string{
+				"HTTP-Referer": "opencode.ai",
+				"X-Title":      "OpenCode",
+			}),
+		)
+		return &baseProvider[OpenAIClient]{
+			options: clientOptions,
+			client:  newOpenAIClient(clientOptions),
+		}, nil
 	case models.ProviderMock:
 		// TODO: implement mock client for test
 		panic("not implemented")

opencode-schema.json

@@ -49,23 +49,38 @@
             "gpt-4.1-mini",
             "azure.gpt-4.1-mini",
             "gemini-2.5",
-            "meta-llama/llama-4-scout-17b-16e-instruct"
+            "meta-llama/llama-4-scout-17b-16e-instruct",
+            "openrouter.deepseek-chat-free",
+            "openrouter.deepseek-r1-free",
+            "openrouter.gpt-4.1",
+            "openrouter.gpt-4.1-mini",
+            "openrouter.gpt-4.1-nano",
+            "openrouter.gpt-4.5-preview",
+            "openrouter.gpt-4o",
+            "openrouter.gpt-4o-mini",
+            "openrouter.o1",
+            "openrouter.o1-pro",
+            "openrouter.o1-mini",
+            "openrouter.o3",
+            "openrouter.o3-mini",
+            "openrouter.o4-mini",
+            "openrouter.gemini-2.5-flash",
+            "openrouter.gemini-2.5",
+            "openrouter.claude-3.5-sonnet",
+            "openrouter.claude-3-haiku",
+            "openrouter.claude-3.7-sonnet",
+            "openrouter.claude-3.5-haiku",
+            "openrouter.claude-3-opus"
           ],
           "type": "string"
         },
         "reasoningEffort": {
           "description": "Reasoning effort for models that support it (OpenAI, Anthropic)",
-          "enum": [
-            "low",
-            "medium",
-            "high"
-          ],
+          "enum": ["low", "medium", "high"],
           "type": "string"
         }
       },
-      "required": [
-        "model"
-      ],
+      "required": ["model"],
       "type": "object"
     }
   },
@@ -120,23 +135,38 @@
               "gpt-4.1-mini",
               "azure.gpt-4.1-mini",
               "gemini-2.5",
-              "meta-llama/llama-4-scout-17b-16e-instruct"
+              "meta-llama/llama-4-scout-17b-16e-instruct",
+              "openrouter.deepseek-chat-free",
+              "openrouter.deepseek-r1-free",
+              "openrouter.gpt-4.1",
+              "openrouter.gpt-4.1-mini",
+              "openrouter.gpt-4.1-nano",
+              "openrouter.gpt-4.5-preview",
+              "openrouter.gpt-4o",
+              "openrouter.gpt-4o-mini",
+              "openrouter.o1",
+              "openrouter.o1-pro",
+              "openrouter.o1-mini",
+              "openrouter.o3",
+              "openrouter.o3-mini",
+              "openrouter.o4-mini",
+              "openrouter.gemini-2.5-flash",
+              "openrouter.gemini-2.5",
+              "openrouter.claude-3.5-sonnet",
+              "openrouter.claude-3-haiku",
+              "openrouter.claude-3.7-sonnet",
+              "openrouter.claude-3.5-haiku",
+              "openrouter.claude-3-opus"
             ],
             "type": "string"
           },
           "reasoningEffort": {
             "description": "Reasoning effort for models that support it (OpenAI, Anthropic)",
-            "enum": [
-              "low",
-              "medium",
-              "high"
-            ],
+            "enum": ["low", "medium", "high"],
             "type": "string"
           }
         },
-        "required": [
-          "model"
-        ],
+        "required": ["model"],
         "type": "object"
       },
       "description": "Agent configurations",
@@ -182,9 +212,7 @@
           "type": "string"
         }
       },
-      "required": [
-        "directory"
-      ],
+      "required": ["directory"],
       "type": "object"
     },
     "debug": {
@@ -222,9 +250,7 @@
             "type": "object"
           }
         },
-        "required": [
-          "command"
-        ],
+        "required": ["command"],
         "type": "object"
       },
       "description": "Language Server Protocol configurations",
@@ -262,10 +288,7 @@
           "type": {
             "default": "stdio",
             "description": "Type of MCP server",
-            "enum": [
-              "stdio",
-              "sse"
-            ],
+            "enum": ["stdio", "sse"],
             "type": "string"
           },
           "url": {
@@ -273,9 +296,7 @@
             "type": "string"
           }
         },
-        "required": [
-          "command"
-        ],
+        "required": ["command"],
         "type": "object"
       },
       "description": "Model Control Protocol server configurations",
@@ -302,7 +323,8 @@
               "gemini",
               "groq",
               "bedrock",
-              "azure"
+              "azure",
+              "openrouter"
             ],
             "type": "string"
           }