Mistral Small (Mistral) API

Mistral AI · serves mistral-small

Pricing

Input / 1M	$0.15
Output / 1M	$0.60
Blended / 1M	$0.75cheapest of 2
Context window	131,072 tokens
Max output	32,768 tokens
License	Open weights · Apache 2.0 permissive
Knowledge cutoff	June 2025 · source

textfunction-calling

Price verified 2026-09-03 (2 days ago) · sourcesources disagree

Sources

Sources disagree by 47% on this price. The figure above is the primary source; cross-check before relying on it.

Source	Input / 1M	Output / 1M	Verified
OpenRouter	$0.15	$0.60	2026-09-03
LiteLLM	$0.10	$0.30	2026-09-03
models.dev	$0.10	$0.30	2026-09-04

Independent sources disagree — treat with caution.

Latency measured

Region	TTFT p50	TTFT p95	Total p50	Total p95	Throughput	Samples
eu-paris	270.5 ms	320.3 ms	1,575.7 ms	1,630.3 ms	142.1 tok/s	5

Time-to-first-token, measured server-side. Measured 2026-09-04 (0 days ago).

Call it

OpenAI-compatible endpoint — set MISTRAL_API_KEY.

curl https://api.mistral.ai/v1/chat/completions \
  -H "Authorization: Bearer $MISTRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-small-2603",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

from openai import OpenAI  # pip install openai

client = OpenAI(
    base_url="https://api.mistral.ai/v1",
    api_key="...",  # MISTRAL_API_KEY
)
resp = client.chat.completions.create(
    model="mistral-small-2603",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Price unchanged since 2026-09-03 — 1 point on record.

Use this data

Raw JSON for this page: mistral-small.json. Free to reuse under CC BY 4.0 with attribution to apipriceindex.com.