Skip to main content

​
Overview

Mistral is an OpenAI-compatible provider with custom compatibility handling for specific features. Bifrost converts requests to Mistral’s expected format while supporting their unique API endpoints. Key characteristics:
  • OpenAI-compatible format - Chat and streaming endpoints
  • Transcription API - Native audio transcription support
  • Tool calling support - Function definitions with string-based tool choice
  • Streaming support - Server-Sent Events for chat and transcription
  • Parameter compatibility - max_completion_tokens → max_tokens conversion

​
Supported Operations

OperationNon-StreamingStreamingEndpoint
Chat Completions✅✅/v1/chat/completions
Responses API✅✅/v1/chat/completions
Transcriptions (STT)✅✅/v1/audio/transcriptions
Embeddings✅-/v1/embeddings
List Models✅-/v1/models
Text Completions❌❌-
Speech (TTS)❌❌-
Files❌❌-
Batch❌❌-
Unsupported Operations (❌): Text Completions, Speech (TTS), Files, and Batch are not supported by the upstream Mistral API. These return UnsupportedOperationError.

​
1. Chat Completions

​
Request Parameters

Mistral supports most OpenAI chat completion parameters with some conversions. For standard OpenAI parameter reference, see OpenAI Chat Completions.

​
Parameter Mapping & Conversions

ParameterOpenAIMistralNotes
max_completion_tokens✅max_tokensConversion required
temperature✅✅Direct pass-through
top_p✅✅Direct pass-through
stop✅✅Stop sequences
tools✅✅Function definitions
tool_choiceString onlyString onlyLimitations apply
user✅✅Max 64 characters
frequency_penalty, presence_penalty✅✅Direct pass-through

​
Critical Conversions

max_completion_tokens → max_tokens: 
// Bifrost request
{"max_completion_tokens": 4096}

// Mistral API
{"max_tokens": 4096}
Tool Choice Simplification: Mistral only supports simple string tool choice, not structured constraints: 
// OpenAI supports specific tool forcing
{"tool_choice": {"type": "function", "function": {"name": "specific_tool"}}}

// Mistral only supports
{"tool_choice": "any"}  // or "none", "auto"

​
Filtered Parameters

Removed for Mistral compatibility:
  • prompt_cache_key - Not supported
  • cache_control - Stripped from content blocks
  • verbosity - Anthropic-specific
  • store - Not supported
  • service_tier - Not supported

​
Message Conversion

Full OpenAI message support:
  • All roles: user, assistant, system, tool, developer
  • Content types: text, images, audio, files

​
Tool Conversion

Tool definitions supported with constraints:
AspectSupportNotes
Function definitions✅Full parameter schema support
Tool choice “auto”✅Default mode
Tool choice “any”✅Requires any tool
Tool choice “none”✅No tools
Specific tool forcing❌Not supported - simplified to “any”
Parallel tools✅Multiple tools in one turn
Limitation Caveat: 
// Bifrost allows specifying a specific tool
{
  "tool_choice": {
    "type": "function",
    "function": {"name": "get_weather"}  // ❌ Not supported
  }
}

// Mistral compatibility - converted to generic "any"
{
  "tool_choice": "any"
}

​
Response Conversion

Standard OpenAI-compatible response:
  • choices[].message.content - Response text
  • choices[].message.tool_calls - Function calls
  • usage - Token counts (prompt_tokens, completion_tokens)
  • finish_reason - stop, tool_calls, length

​
2. Responses API

Converted internally to Chat Completions with format transformation: 
ResponsesRequest → ChatRequest → ChatCompletion → ResponsesResponse
Same parameter support and tool handling as Chat Completions.

​
3. Transcription

Mistral provides native audio transcription with streaming support.

​
Request Parameters

​
Parameter Mapping

ParameterBifrostMistralNotes
fileBinary audioMultipart formConverted to multipart
modelModel namemodel
languageISO-639-1languageOptional language hint
promptOptionalpromptContext for recognition
response_formatFormat typeresponse_formatjson, text, etc.
temperaturefloattemperatureSampling temperature
timestamp_granularitiesArrayArray fieldSegment/word timestamps

​
Multipart Form Structure

Transcription requests are sent as multipart/form-data: 
--boundary
Content-Disposition: form-data; name="file"; filename="audio.mp3"
[binary audio data]
--boundary
Content-Disposition: form-data; name="model"
voxtral-mini-latest
--boundary
Content-Disposition: form-data; name="language"
en
--boundary--

​
Transcription Response

{
  "text": "transcribed text",
  "language": "en",
  "duration": 3.5,
  "segments": [{
    "id": 0,
    "start": 0.0,
    "end": 1.5,
    "text": "transcribed segment",
    "temperature": 0.0,
    "avg_logprob": -0.45,
    "compression_ratio": 1.2,
    "no_speech_prob": 0.001
  }],
  "words": [{
    "word": "transcribed",
    "start": 0.0,
    "end": 0.8
  }]
}

​
Transcription Streaming

Mistral supports SSE streaming for transcription with custom event types:
Event TypeContentNotes
transcription.languageLanguage codeLanguage detected
transcription.text.deltaText deltaIncremental text
transcription.segmentFull segmentComplete segment data
transcription.doneFinal usageCompletion with tokens

​
4. Embeddings

Mistral supports text embeddings:
ParameterNotes
inputText or array of texts
modelEmbedding model name
dimensionsCustom output dimensions (optional)
encoding_format”float” or “base64”
Response returns embedding vectors with token usage.

​
5. List Models

Lists available Mistral models with context length and capabilities.

​
Unsupported Features

FeatureReason
Text CompletionsNot offered by Mistral API
Speech/TTSNot offered by Mistral API
File ManagementNot offered by Mistral API
Batch OperationsNot offered by Mistral API

​
Caveats

Severity: Medium Behavior: Cache control directives removed from messages 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