The AI arena is free today

Open Superagent
MistralReleased on Sep 17, 2024

Mistral Small: API Pricing, Context Window & Benchmarks

Mistral Small is a language model from Mistral, released in September 2024.

An enterprise-grade 22B parameter model optimized for tasks like translation, summarization, and sentiment analysis. Offers significant improvements in human alignment, reasoning capabilities, and code generation compared to previous

Input
Text
Output
Text
Speed
Latency p95500ms
Throughput P950.1char/s
Cost
$0.22/ 1M · 20:1 in:out
$0.20 in · $0.60 out

Mistral Small pricing

Providers

Mistral Small starts at $0.200 per million input tokens and $0.600 per million output tokens via Mistral AI.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
Mistral AI logoMistral AI
$0.200—$0.60032.8K/32.8K
0.50
—
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Mistral Small context window

Input and output token limits for Mistral Small, plus how it ranks on long-context understanding.

InputOutput
33Ktokens
33Ktokens
≈ 49 pages of text
33K
8K128K1M

Mistral Small API

Available from the model provider

Mistral Small has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

Mistral Small latency

Mistral Small time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Mistral Small examples

Recent arena outputs from Mistral Small, picked from the highest-ranked matchups.

Mistral Small license

Mistral Small is a proprietary model available under its provider's product and API terms, has 22.0B parameters.

License
Mistral Research License
Hosted access
Parameters
22.0B

Mistral Small resources

Official sources for Mistral Small: api documentation, official playground, official launch post, model weights.

FAQ

Common questions about Mistral Small.

When was Mistral Small released?

Mistral Small was released on September 17, 2024 by Mistral. This is the official Mistral Small release date tracked on LLM Stats.

How much does Mistral Small cost?

Mistral Small pricing starts at $0.20 per million input tokens and $0.60 per million output tokens via Mistral AI, the lowest price among tracked providers.

Is Mistral Small available via API?

Yes, Mistral Small is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

How big is Mistral Small?

Mistral Small has 22 billion parameters.

Who created Mistral Small?

Mistral Small was created by Mistral.

What is the license for Mistral Small?

Mistral Small is released under the Mistral Research License license.

What is Mistral Small latency?

Mistral Small p95 time to first token is 0.50 seconds via Mistral AI over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use Mistral Small?

Mistral Small is available through 1 provider including Mistral AI.

Where is the Mistral Small paper or technical report?

Mistral Small has a paper or technical report available at https://mistral.ai/news/september-24-release/. Use that source for architecture, training, release and evaluation details.