Mistral's hybrid MoE small model (119B total, 6.5B active) unifying instruction, reasoning, and coding with image input.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.
Mistral's hybrid MoE small model (119B total, 6.5B active) unifying instruction, reasoning, and coding with image input. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Mistral Small 4 on LLM Gateway starts at $0.15 per million input tokens and $0.60 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Mistral Small 4 supports a context window of up to 262,144 tokens on its largest provider deployment.
Mistral Small 4 is served by Mistral AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Yes. Mistral Small 4 supports both tool (function) calling and strict JSON output schema (upstream-enforced) through LLM Gateway.
Mistral Small 4 was released on March 17, 2026.
Mistral Medium 3.5
262,144 context$1.50 in / $7.50 out per 1M
Devstral 2
262,144 context$0.40 in / $2.00 out per 1M
Ministral 3B
131,072 context$0.10 in / $0.10 out per 1M
Ministral 8B
262,144 context$0.15 in / $0.15 out per 1M
Ministral 14B
262,144 context$0.20 in / $0.20 out per 1M
Mistral Large 3
262,144 context$0.50 in / $1.50 out per 1M