Mistral

Overview

Mistral is an OpenAI-compatible provider with custom compatibility handling for specific features. DeepIntShield 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

Operation	Non-Streaming	Streaming	Endpoint
Chat Completions	✅	✅	`/v1/chat/completions`
Responses API	✅	✅	`/v1/chat/completions`
Transcriptions (STT)	✅	✅	`/v1/audio/transcriptions`
Embeddings	✅	-	`/v1/embeddings`
List Models	✅	-	`/v1/models`
Image Generation	❌	❌	-
Text Completions	❌	❌	-
Speech (TTS)	❌	❌	-
Files	❌	❌	-
Batch	❌	❌	-

1. Chat Completions

Request Parameters

Mistral supports most OpenAI chat completion parameters. For standard OpenAI parameter reference, see OpenAI Chat Completions. temperature, top_p, stop, frequency_penalty, and presence_penalty pass through directly. The user field is limited to 64 characters.

The following parameters are not supported and are ignored: prompt_cache_key, cache_control, verbosity, store, service_tier.

Message Content

Full OpenAI message support:

All roles: user, assistant, system, tool, developer
Content types: text, images, audio, files

Tool Support

Tool definitions are supported with the following constraints:

Aspect	Support	Notes
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 by Mistral
Parallel tools	✅	Multiple tools in one turn

Mistral supports only string-valued tool_choice (auto, any, none) - forcing a specific tool by name is not supported.

Response

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

Mistral supports the Responses API with the same parameter support and tool handling as Chat Completions. Responses are returned in Responses format.

3. Transcription

Mistral provides native audio transcription with streaming support. Requests are sent as multipart/form-data to /v1/audio/transcriptions.

Request Parameters

Parameter	Notes
`file`	Audio file (required)
`model`	Model name (e.g. `voxtral-mini-latest`)
`language`	ISO-639-1 language hint (optional)
`prompt`	Context for recognition (optional)
`response_format`	`json`, `text`, etc.
`temperature`	Sampling temperature
`timestamp_granularities`	Segment/word timestamps

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 Type	Content	Notes
`transcription.language`	Language code	Language detected
`transcription.text.delta`	Text delta	Incremental text
`transcription.segment`	Full segment	Complete segment data
`transcription.done`	Final usage	Completion with tokens

4. Embeddings

Mistral supports text embeddings:

Parameter	Notes
`input`	Text or array of texts
`model`	Embedding model name
`dimensions`	Custom 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

Feature	Reason
Text Completions	Not offered by Mistral API
Image Generation	Not yet implemented in DeepIntShield integration (Mistral API supports this)
Speech/TTS	Not offered by Mistral API
File Management	Not offered by Mistral API
Batch Operations	Not offered by Mistral API

Caveats

Cache Control Stripped

Severity: Medium Behavior: Cache control directives removed from messages Impact: Prompt caching features unavailable

Parameter Filtering

Severity: Low Behavior: OpenAI-specific parameters filtered Impact: prompt_cache_key, verbosity, store removed

User Field Size Limit

Severity: Low Behavior: User field > 64 characters silently dropped Impact: Longer user identifiers are lost