ZMIME
Mistral AI · Released Dec 11, 2023

Mixtral 8x7B

Mistral model for multilingual chat, reasoning, and tool-assisted workflows.

  • Open weights
  • Tool calling
  • Retired
Capability
118.5ECI · #153 of 158
Input
$0.70per 1M tokens
Output
$0.70per 1M tokens
Context
32K32K max output

Retired Mixtral 8x7B is no longer offered by Mistral AI or any API host we track (since Nov 2, 2026). The specs and prices below are its last published listing, kept for reference.

Pricing

What it costs

Input
$0.70per million tokens
Output
$0.70per million tokens
Blended (3:1)
$0.70cheaper than 51% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$1.75
Team assistant25M input + 5M output tokens$21.00
Production app250M input + 50M output tokens$210.00

Official Mistral API price, as listed on models.dev.

Capability

Independent benchmarks

118.5Epoch Capabilities Index
#153 of 158 scored models
68Median 147174

The shaded band is Epoch AI’s confidence range (111.3–121.3); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions30.6%

Scores from Epoch AI, run independently of Mistral AI.

Specifications

The details

Lab
Mistral AI
Released
Dec 11, 2023
Knowledge cutoff
Jan 2024
Context window
32,000 tokens
Max output
32,000 tokens
Inputs
Text
Output
Text
Reasoning
No
Tool calling
Yes
Structured output
No
Weights
Open weights
API model ID
open-mixtral-8x7bon Mistral
Availability
1 API providerlisted on models.dev
Status
Retired no provider has listed it since Nov 2, 2026

Mistral model documentation

Same lab

More from Mistral AI

Questions

About Mixtral 8x7B

Is Mixtral 8x7B still available?

No. Mixtral 8x7B has been retired: neither Mistral AI nor any API host we track lists it since Nov 2, 2026. This page keeps its last published specs and prices for reference.

How much does Mixtral 8x7B cost?

Mixtral 8x7B costs $0.70 input / $0.70 output per million tokens (official Mistral API price). At a 3:1 input-to-output mix that is $0.70 per million tokens, cheaper than 51% of the 469 priced models we track.

What is the context window of Mixtral 8x7B?

Mixtral 8x7B accepts up to 32,000 tokens per request and can write up to 32,000 tokens in one response.

How good is Mixtral 8x7B?

Epoch AI gives Mixtral 8x7B a Capabilities Index score of 118.5 (likely range 111.3–121.3), ranking it #153 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 30.6%.

Is Mixtral 8x7B open source?

Yes. Mistral AI publishes the weights, so it can be downloaded and self-hosted.

What inputs does Mixtral 8x7B support?

Mixtral 8x7B accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling.

When was Mixtral 8x7B released?

Mistral AI released Mixtral 8x7B on Dec 11, 2023. Its training data runs to Jan 2024.

What are the best alternatives to Mixtral 8x7B?

The closest current models from other labs on capability, price and release date are Claude Haiku 3 (Anthropic, ECI 117.8, $0.25 / $1.25), Qwen2.5 7B Instruct (Alibaba (Qwen), $0.075 / $0.15), Llama-3.1-70B-Instruct (Meta, ECI 124.7, $0.72 / $0.72) and Nova Pro (Amazon, $0.80 / $3.20).