Low-latency IDE autocomplete, fill-in-the-middle completion, code generation, code editing, test generation and developer assistants
Type
Coding
Context
128K
Reasoning
6/10
Speed
9/10
Tool use
Streaming
Input
$0.30 per million tokens; cached input $0.03 per million tokens
Output
$0.90 per million tokens
View model
→
Semantic code search, repository retrieval, coding-agent RAG, code similarity, duplicate detection, clustering, and code analytics
Type
Embedding
Context
8K
Speed
8/10
Input
$0.15 per million input tokens
View model
→
Lean 4 theorem proving, formal verification, autoformalization, proof debugging, and agentic proof engineering
Type
Other
Context
256K
Reasoning
9/10
Speed
7/10
Tool use
Status
Public Preview; scheduled for retirement on 2026-09-30
View model
→
Low-cost edge and local inference, image-aware assistants, document analysis, structured extraction, lightweight agents, task routing, and privacy-sensitive deployments.
Type
Lightweight
Context
256K
Reasoning
6/10
Speed
9/10
Multimodal
Image input
Tool use
Status
Active; generally available
Input
$0.10 per 1 million tokens; cached input $0.01 per 1 million tokens
Output
$0.10 per 1 million tokens
View model
→
Efficient edge and local inference, image understanding, document workflows, structured extraction, lightweight agents, and high-volume text generation.
Type
Lightweight
Context
256K
Reasoning
7/10
Speed
9/10
Multimodal
Image input
Tool use
Status
Active; generally available
Input
$0.15 per million tokens; cached input $0.015 per million tokens
Output
$0.15 per million tokens
View model
→
Private assistants, local vision-language applications, multilingual workloads, document and image analysis, and cost-efficient agentic systems
Type
Multimodal
Context
262K
Reasoning
8/10
Speed
8/10
Multimodal
Image input
Tool use
Status
Active; generally available
Input
$0.20 per 1 million tokens; cached input $0.02 per 1 million tokens
Output
$0.20 per 1 million tokens
View model
→
Semantic search, retrieval-augmented generation, vector databases, document classification, clustering, duplicate detection and general text retrieval
Type
Other
Context
8K
Speed
8/10
Status
Generally available
Input
$0.10 per 1 million tokens
Output
$0.10 per 1 million tokens
View model
→
Long-context enterprise assistants, multilingual applications, image-aware document analysis, agentic workflows, coding, RAG and self-hosted sovereign deployments
Type
Multimodal
Context
256K
Reasoning
8/10
Speed
5/10
Multimodal
Image input
Tool use
Status
Active; generally available; open-weight
Input
$0.50 per 1M tokens; cached input $0.05 per 1M tokens
Output
$1.50 per 1M tokens
View model
→
Agentic coding, software engineering, long-context analysis, multimodal document workflows, structured outputs and multi-step tool use
Type
Multimodal
Context
256K
Reasoning
8/10
Speed
7/10
Multimodal
Image input
Tool use
Status
GA; currently available; open weights
Input
$1.50 per million input tokens; $0.15 per million cached input tokens
Output
$7.50 per million output tokens
View model
→
Text moderation, conversational safety classification, content filtering, policy enforcement, guardrails, and jailbreaking detection
Type
Moderation
Context
131K
Reasoning
2/10
Speed
8/10
Status
Active; generally available; Premier
View model
→
High-volume OCR, structured document extraction, enterprise search, RAG ingestion, invoice processing, compliance workflows, and document automation
Type
Other
Reasoning
2/10
Speed
8/10
Multimodal
Image input
Status
Generally available; superseded by OCR 4.1 as Mistral's latest OCR model
Input
$4 per 1,000 pages; $0.40 per 1,000 cached pages; Batch API pricing reported at $2 per 1,000 pages
Output
Included in page-based processing price; no separate output-token price
View model
→
Cost-efficient general chat, multimodal document analysis, coding, agentic workflows, and configurable reasoning
Type
Multimodal
Context
256K
Reasoning
8/10
Speed
8/10
Multimodal
Image input
Tool use
Status
Active; generally available
Input
$0.15 per 1M tokens; cached input $0.015 per 1M tokens
Output
$0.60 per 1M tokens
View model
→
High-volume document extraction, scanned forms, handwriting, invoices, complex tables, archival digitization, and document-to-knowledge pipelines.
Type
Other
Reasoning
2/10
Speed
8/10
Multimodal
Image input
Media output
Status
Legacy; available for existing integrations and production workloads. OCR 4 is the newer model.
Input
$2 per 1,000 pages
Output
$3 per 1,000 annotated pages
View model
→
OCR, document parsing, structured extraction, enterprise search, RAG ingestion, invoice processing, and document AI workflows
Type
Other
Reasoning
3/10
Speed
8/10
Multimodal
Image input
Status
Generally Available
Input
$4 per 1,000 pages; cached input $0.40 per 1,000 pages
View model
→
Policy-based moderation of prompts, model responses, refusals, text, images, and text-image combinations
Type
Other
Context
33K
Reasoning
2/10
Speed
8/10
Multimodal
Image input
Streaming
Status
Public Preview; open weights; self-hosted
View model
→
Batch transcription of meetings, interviews, calls, subtitles, compliance recordings, and searchable audio
Type
Other
Reasoning
1/10
Speed
8/10
Audio input
Status
Active; GA; Premier hosted model
View model
→
Live speech transcription, realtime captions, voice interfaces, realtime note-taking and speech-to-speech pipelines
Type
Other
Reasoning
1/10
Speed
10/10
Audio input
Streaming
Input
$0.006 per minute
Output
$0 per minute; transcription output is included in the audio-minute price
View model
→
Production-scale audio understanding, multilingual transcription, audio Q&A, meeting and call summarization, speech translation, and voice-driven function calling
Type
Multimodal
Context
32K
Reasoning
6/10
Speed
6/10
Multimodal
Audio input
Tool use
Status
Active; generally available
Input
$0.004 per minute of audio; $0.10 per 1 million input tokens
Output
$0.40 per 1 million output tokens
View model
→
Multilingual voice generation, expressive voice agents, zero-shot voice cloning, custom voice adaptation, and low-latency speech output
Type
Text To Speech
Reasoning
1/10
Speed
9/10
Multimodal
Audio input
Media output
Status
GA; currently available through the Mistral API and Mistral Studio
Input
$0 per 1 million input characters
Output
$16 per 1 million output characters
View model
→
