​

Mistral: Mistral Small 3.2 to Mistral Small 4

• mistral/mistral-small-4-2026-03-16

• mistral/mistral-small-3-2-2025-06-20

​

What changed

• Mistral Small 4 exposes a reasoning mode control via reasoning_effort.
• Gateway sends only two upstream values for this model route:
  • none (reasoning off)
  • high (reasoning on)
• Gateway normalizes Mistral thinking blocks back into standard response fields:
  • message.content for assistant-visible text
  • message.reasoning_content and message.reasoning_details for reasoning text

​

Required request changes

• if you omit reasoning controls, Gateway sends reasoning_effort: "none"
• if you pass reasoning.enabled: true, Gateway sends reasoning_effort: "high"
• if you pass reasoning.effort: "none", Gateway sends reasoning_effort: "none"
• if you pass any other reasoning.effort value, Gateway sends reasoning_effort: "high"

• use reasoning.effort: "none" for lightweight behavior
• use reasoning.effort: "high" for deep reasoning

{
  "model": "mistral/mistral-small-4-2026-03-16",
  "messages": [
    { "role": "user", "content": "Why is fast inference important?" }
  ],
  "reasoning": {
    "effort": "high"
  }
}

​

Response handling notes

• final user-visible answer from choices[0].message.content
• reasoning text from choices[0].message.reasoning_content

​

Rollout checklist

1. Update model ID to mistral/mistral-small-4-2026-03-16.
2. Validate reasoning controls using only none and high.
3. Re-run output quality and schema tests on your high-effort routes.
4. Compare latency/cost for none vs high before full cutover.