Current small/open-weight model (v26.03); hybrid model unifying instruct, reasoning, and coding in one model, 119B params with 6.5B active. Primary source: docs.mistral.ai model card (https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03) — verbatim: "Our powerful hybrid model unifying
profile normalized against the 70-model field
Context window· 262K of 10M3%
Max output—
Output speed—
Affordability· $0.60 / Mtok out100%
Capability breadth· 3 of 1127%
Capability switches · 3 of 11
Reasoning mode
Tool / function use
Streaming
JSON mode
Structured outputs
Prompt caching
Fine-tuning
Web search
Code execution
Vision input
Audio input
Specifications
Every value carries a primary source and a verification date.
Capacity
Context window
262K
Pricing
Input $/Mtok
$0.15 / 1M input tokens USD per 1M tokens
Output $/Mtok
$0.60 / 1M output tokens USD per 1M tokens
Capabilities
Reasoning mode
Yes
Tool / function use
Yes
Vision input
Yes
API
API model ID
mistral-small-2603
General
Release date
March 16, 2026
Benchmarks
Sourced evaluation scores, each verified against its primary source.
AA LCR
On AA LCR, Mistral Small 4 scores 0.72 with just 1.6K characters, whereas Qwen models need 3.5-4x more output (5.8-6.1K) for comparable performance.