Mistral AI
Mistral Small 4
Mistral Small 4 — 119B MoE model unifying instruction following, reasoning, coding, and vision with 256K context.
mistral-small-4Pricing
~69%- Input
- $0.046875 / 1,000,000 tokens
- Output
- $0.1875 / 1,000,000 tokens
- Cache read
- $0.007031 / 1,000,000 tokens
- Cache write
- $0.046875 / 1,000,000 tokens
Discount history
Model details
- Input
- text, image
- Output
- text
- Context window
- 256,000 tokens
- Maximum output
- 32,768 tokens
- Availability
- $210Uncapped capacity
- Updated
- 11/8/2026, 3:58:06 AM UTC
Capacity is reserved when your request is accepted.
Capabilities
ChatStreamingTool callingVisionReasoning
Supported parameters
max_tokenstemperaturetop_pfrequency_penaltypresence_penaltystoptoolstool_choiceresponse_formatseedstructured_outputs