MistralReleased on Sep 17, 2024

Pixtral-12B: API Pricing, Context Window & Benchmarks

Pixtral-12B is a language model from Mistral, released in September 2024, with multimodal input.

A 12B parameter multimodal model with a 400M parameter vision encoder, capable of understanding both natural images and documents. Excels at multimodal tasks while maintaining strong text-only performance. Supports variable image sizes and

Input
TextImage
Output
Text

Pixtral-12B benchmarks

Rankings

Quality Tracker

Pixtral-12B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Sun Jul 26 2026
Notice missing or incorrect data?

Pixtral-12B pricing

Providers

Pixtral-12B starts at $0.150 per million input tokens and $0.150 per million output tokens via Mistral AI.

ProviderInput $/MOutput $/MContext in / outTTFT p50 / p95 sOutput avg / p5 c/sSuccess 7dModalities in / out
Mistral AI logoMistral AI
$0.150$0.150128.0K/8.2K
/0.50
0/
/

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. Success is calculated from completed versus failed requests over the trailing seven days.

Pixtral-12B model size

Pixtral-12B has 12.4 billion parameters. See how it compares to other models in the same parameter range.

Parameters
12.4B
Medium (10–30B)
12.4B
1B7B70B405B

Pixtral-12B context window

Input and output token limits for Pixtral-12B, plus how it ranks on long-context understanding.

InputOutput
128Ktokens
8Ktokens
192 pages of text
128K
8K128K1M

Pixtral-12B API

Available from the model provider

Pixtral-12B has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

Pixtral-12B latency

Pixtral-12B time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Pixtral-12B examples

Recent arena outputs from Pixtral-12B, picked from the highest-ranked matchups.

Pixtral-12B license

Pixtral-12B is released under the Apache 2.0 license, which permits commercial use, has 12.4B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
12.4B

Apache License 2.0 - allows commercial use

Pixtral-12B resources

Official sources for Pixtral-12B: api documentation, official playground, official launch post, source repository.

Pixtral-12B vs other models

The most-compared alternatives to Pixtral-12B are Claude 3 Sonnet, Phi 4, Mistral NeMo Instruct. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Pixtral-12B

Models ranked just above and below Pixtral-12B by LLM Stats score.

 

Claude 3 Sonnet

Score pending
 

Phi 4

Score pending
 

Mistral NeMo Instruct

Score pending
 

Phi-3.5-MoE-instruct

Score pending
 

Llama 3.1 8B Instruct

Score pending
 

IBM Granite 4.0 Tiny Preview

Score pending

FAQ

Common questions about Pixtral-12B.

When was Pixtral-12B released?

Pixtral-12B was released on September 17, 2024 by Mistral. This is the official Pixtral-12B release date tracked on LLM Stats.

How much does Pixtral-12B cost?

Pixtral-12B pricing starts at $0.15 per million input tokens and $0.15 per million output tokens via Mistral AI, the lowest price among tracked providers.

Is Pixtral-12B available via API?

Yes, Pixtral-12B 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 Pixtral-12B?

Pixtral-12B has 12.4 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Pixtral-12B?

Pixtral-12B was created by Mistral.

What is the license for Pixtral-12B?

Pixtral-12B is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Is Pixtral-12B multimodal?

Yes, Pixtral-12B is multimodal and can accept both text and images as input.

What is Pixtral-12B latency?

Pixtral-12B 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 Pixtral-12B?

Pixtral-12B is available through 1 provider including Mistral AI.

Where is the Pixtral-12B paper or technical report?

Pixtral-12B has a paper or technical report available at https://mistral.ai/news/pixtral-12b/. Use that source for architecture, training, release and evaluation details.

What models should I compare Pixtral-12B against?

Common Pixtral-12B comparisons include Pixtral-12B vs Claude 3 Sonnet, Pixtral-12B vs Phi 4, Pixtral-12B vs Mistral NeMo Instruct. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.