API pricing
Pricing for Mistral models, organized by family.
Generalist models
Generalist models
Text and multimodal models for broad reasoning, coding, tool use, and agentic tasks.
Mistral Large 4
- Input
- $0.7 /M Tokens
- Output
- $2.1 /M Tokens
Z.ai GLM 5.3 Flash
- Input
- $0.15 /M Tokens
- Output
- $0.5 /M Tokens
| Model | Input | Cached input | Output |
|---|---|---|---|
| Z.ai GLM 5.3 Flash ↗ | $0.15 | $0.03 | $0.5 |
| DeepSeek V4.1 Flash 1017 ↗ | $0.3 | $0.007 | $1.2 |
| Z.ai GLM 5.3 ↗ | $1.4 | $0.14 | $4.4 |
| Mistral Small 4 ↗ | $0.15 | $0.015 | $0.6 |
| Mistral Large 4 ↗ | $0.7 | $0.07 | $2.1 |
| Ministral 3 14B ↗ | $0.2 | $0.02 | $0.2 |
| Ministral 3 8B ↗ | $0.15 | $0.015 | $0.15 |
| Ministral 3 3B ↗ | $0.1 | $0.01 | $0.1 |
OCR models
OCR models
Models for document understanding, text extraction, and structured OCR outputs.
Audio models
Audio models
Models for speech transcription, realtime transcription, and speech generation.
Voxtral Mini Transcribe 3
- Input
- $0.0035 /Min
Voxtral Small Transcribe 3
- Input
- $0.004 /Min
Voxtral TTS 3
- Input
- $13 /M Chars
| Model | Input | Cached input | Output |
|---|---|---|---|
| Voxtral Mini Transcribe 3 ↗ | $0.0035 /Min | $0.00035 /Min | — |
| Voxtral Mini Transcribe Realtime 3 ↗ | $0.008 /Min | $0.0008 /Min | — |
| Voxtral Small Transcribe 3 ↗ | $0.004 /Min | $0.0004 /Min | — |
| Voxtral TTS 3 ↗ | $13 /M Chars | $1.3 /M Chars | — |
| Voxtral Small ↗ | $0.004 /Min | $0.0004 /Min | $0.4 /M Tokens |
Code models
Code models
Specialized models for code generation, completion, and software engineering agents.
| Model | Input | Cached input | Output |
|---|---|---|---|
| Codestral ↗ | $0.3 | $0.03 | $0.9 |
Embedding models
Embedding models
Models that turn text or code into vectors for retrieval and similarity search.
| Model | Input | Cached input | Output |
|---|---|---|---|
| Codestral Embed ↗ | $0.15 | $0.015 | — |
| Mistral Embed ↗ | $0.1 | $0.01 | — |
Moderation and safety models
Moderation and safety models
Models for safety filtering, moderation, and policy checks.
| Model | Input | Cached input | Output |
|---|---|---|---|
| Mistral Moderation 2 ↗ | Free | Free | Free |
| Shieldstral 1.0 ↗Self-hosted · Open weights | Costs depend on your own infrastructure | ||
Time series models
Time series models
Models for zero-shot time series forecasting with covariate support and probabilistic outputs.
| Model | Input | Cached input | Output |
|---|---|---|---|
| Timestral 1.0 209M ↗Self-hosted · Open weights | Costs depend on your own infrastructure | ||
| Timestral 1.0 123M ↗Self-hosted · Open weights | Costs depend on your own infrastructure | ||
| Timestral 1.0 28M ↗Self-hosted · Open weights | Costs depend on your own infrastructure | ||
| Timestral 1.0 5M ↗Self-hosted · Open weights | Costs depend on your own infrastructure | ||
Voice agents
Voice agents
Pricing for the Voice Agents API, billed per minute of conversation.
| Model | Price |
|---|---|
| Mistral Small 4 | $0.04/min |
| Larger models | $0.08/min |