Skip to main content

​
Overview

OpenRouter is an OpenAI-compatible provider routing service that accesses models from multiple providers (OpenAI, Anthropic, Google, Meta, etc.) through a unified interface. Bifrost delegates to the OpenAI implementation with special handling for reasoning models. Key features:
  • Provider aggregation - Access 100+ models from multiple vendors
  • Reasoning support - Extended thinking for supported models
  • Parameter compatibility - Intelligent reasoning effort conversion
  • Streaming support - Full SSE support with usage tracking
  • Tool calling - Complete function definition and execution

​
Supported Operations

OperationNon-StreamingStreamingEndpoint
Chat Completions✅✅/v1/chat/completions
Responses API✅✅/v1/responses
Text Completions✅✅/v1/completions
List Models✅-/v1/models
Embeddings❌❌-
Speech (TTS)❌❌-
Transcriptions (STT)❌❌-
Files❌❌-
Batch❌❌-
Unsupported Operations (❌): Embeddings, Speech, Transcriptions, Files, and Batch are not supported by the upstream OpenRouter API. These return UnsupportedOperationError.Note: OpenRouter’s Responses API is currently in beta.

​
1. Chat Completions

​
Request Parameters

OpenRouter supports all standard OpenAI chat completion parameters. For full parameter reference and behavior, see OpenAI Chat Completions.

​
Reasoning Parameter Handling

OpenRouter supports extended thinking on compatible models: 
// Bifrost request
{
  "reasoning": {
    "effort": "high",
    "max_tokens": 10000
  }
}

// OpenRouter conversion
{
  "reasoning_effort": "high"
}
Reasoning Models: gpt-oss-120b and compatible models with special handling for reasoning content.

​
Cache Control Stripping

Anthropic-specific cache control directives are automatically removed: 
// Bifrost supports cache control from Anthropic
{
  "messages": [{
    "role": "user",
    "content": [{
      "type": "text",
      "text": "...",
      "cache_control": {"type": "ephemeral"}  // ← Stripped
    }]
  }]
}

// Sent to OpenRouter without cache directives

​
Filtered Parameters

Removed for OpenRouter compatibility:
  • prompt_cache_key - Not supported
  • verbosity - Anthropic-specific
  • store - Not supported
  • service_tier - OpenAI-specific
OpenRouter supports all standard OpenAI message types, tools, responses, and streaming formats. For details on message handling, tool conversion, responses, and streaming, refer to OpenAI Chat Completions.

​
2. Responses API

OpenRouter’s Responses API is handled as a distinct endpoint at /v1/responses. This API is currently in beta on OpenRouter. Same parameter support as Chat Completions, with requests forwarded directly to the Responses API endpoint without conversion to Chat Completions. Special Message Handling (gpt-oss vs other models): For details on how reasoning is handled differently between gpt-oss and other models, see OpenAI Responses API documentation for the comprehensive explanation of reasoning conversion (summaries vs. content blocks).

​
3. Text Completions

OpenRouter supports legacy text completion format:
ParameterMapping
promptDirect pass-through
max_tokensmax_tokens
temperature, top_pDirect pass-through
stopStop sequences

​
4. List Models

Lists 100+ models available through OpenRouter, including:
  • OpenAI (GPT-4, GPT-4 Turbo, etc.)
  • Anthropic (Claude 3 family)
  • Google (Gemini)
  • Meta (Llama)
  • Mistral
  • And many more

​
Unsupported Features

FeatureReason
EmbeddingNot offered by OpenRouter API
Speech/TTSNot offered by OpenRouter API
Transcription/STTNot offered by OpenRouter API
Batch OperationsNot offered by OpenRouter API
File ManagementNot offered by OpenRouter API

​
Caveats

Severity: Medium Behavior: Anthropic cache control directives are removed Impact: Prompt caching features unavailable Code: Stripped during JSON marshaling
Severity: Low Behavior: OpenAI-specific parameters filtered Impact: prompt_cache_key, verbosity, store removed Code: filterOpenAISpecificParameters
Severity: Low Behavior: User field > 64 characters silently dropped Impact: Longer user identifiers are lost Code: SanitizeUserField enforces 64-char max