Pricingby GlyphMistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.
Ways to buy 3
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
zdr · cached $0.015 | $0.15 | $0.6 | $0.15 / $0.6Cheapest | $0.015 | Cheapest |
eu · cached $0.017 | $0.165 | $0.66 | $0.165 / $0.66+10% vs cheapest | $0.017 | +10% vs cheapest |
us · cached $0.017 | $0.165 | $0.66 | $0.165 / $0.66+10% vs cheapest | $0.017 | +10% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $27.00 direct.
Kong AI Gateway$27.00+0%
LiteLLM$27.00+0%
Requesty$28.35+5%
Eden AI$28.48+5.5%
OpenRouter$28.48+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
Vercel AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Mistral AI · 1M | $0.7 | $2.1 | $0.7 / $2.1 | $1.05 | 1M | on Mistral AI (zdr) | · | Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. |
Mistral AI · 262K | $1.5 | $7.5 | $1.5 / $7.5 | $3 | 262K | Lab list price | · | Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. |
Mistral AI · 262K | $0.4 | $2 | $0.4 / $2 | $0.8 | 262K | on Mistral AI (eu) | · | Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. |
Mistral AI · 262K | $0.2 | $0.2 | $0.2 / $0.2 | $0.2 | 262K | on Mistral AI (zdr) | · | The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. |
DeepSeek · 1MCheapest: $0.081 on Particle AI (us-flex) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.081 on Particle AI (us-flex) | · | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. |
Z.ai · 1M | $0.179 | $1.4 | $0.179 / $1.4 | $0.484 | 1M | on Wafer (fp4) | · | GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. |
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. |
NVIDIA · 1M | $0.06 | $0.35 | $0.06 / $0.35 | $0.133 | 1M | on Darkbloom (nvfp4) | · | NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. |
About Mistral Small 4
Takes text, image in and returns text. First listed Sep 23, 2026. Up to 210K output tokens. Blended price $0.262 per 1M tokens at 3 input to 1 output. Model id mistral-small-2603.
Price history
List price since Sep 23, 2026, from daily reads of the OpenRouter catalog.
Questions
How much does Mistral Small 4 cost?
$0.15 per million input tokens and $0.6 per million output tokens, with cached input at $0.015.
What is the context window of Mistral Small 4?
262K tokens, with up to 210K tokens of output.
Where is Mistral Small 4 cheapest?
Of 3 routes tracked, Mistral AI is cheapest at $0.15 input and $0.6 output per million tokens.