Mistral Small 4 unifies instruction following, reasoning, coding, and vision in a single 119B MoE model with 256K context and configurable reasoning effort.
Beta
Modalities
In / out price
$0.1875 / $0.75
per 1M
Context
256K
Max output
66K
Released
Mar 16, 2026
Updated
Jul 17, 2026
Privacy
2 / 3Private routing
Private tier
- Anonymous
- Private
- E2EE
- Prompt and response content is not retained after the request.
- Request content is visible to the inference runtime while it is being processed.
Moderation
Not specified
No model-level moderation classification is recorded in this catalog.
Data retention
Zero retention
The provider reports that request content is discarded after inference.
Features
7Streaming
Tool calling
Reasoning
Vision
JSON/schema
Web search
Code optimized
Routing
2Anonrouter hosted
Routed through AnonRouter's gateway with metadata-only logging.
Provider direct
Requests egress directly to the provider runtime.
USD per 1M tokens from the Venice models API.