Mistral AI · Released Dec 11, 2023Mixtral 8x7B Instruct v0.1
Open sparse mixture-of-experts Mistral instruction model.
- Capability
- 118.4ECI · #160 of 165
- Input
- $0.444per 1M tokens
- Output
- $0.579per 1M tokens
- Context
- 33K33K max output
What it costs
- Input
- $0.444per million tokens
- Output
- $0.579per million tokens
- Blended (3:1)
- $0.478cheaper than 61% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $1.18 |
| Team assistant25M input + 5M output tokens | $13.99 |
| Production app250M input + 50M output tokens | $139.95 |
Median of 2 paid API providers on models.dev.
Independent benchmarks
#160 of 165 scored models
The shaded band is Epoch AI’s confidence range (110.9–121.0); the tick marks the median scored model.
Scores from Epoch AI, run independently of Mistral AI.
The details
- Lab
- Mistral AI
- Released
- Dec 11, 2023
- Context window
- 32,768 tokens
- Max output
- 32,768 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- No
- Weights
- Open weights · Apache 2.0
- Availability
- 2 API providerslisted on models.dev
More from Mistral AI
About Mixtral 8x7B Instruct v0.1
How much does Mixtral 8x7B Instruct v0.1 cost?
Mixtral 8x7B Instruct v0.1 costs $0.444 input / $0.579 output per million tokens (median across 2 API providers). At a 3:1 input-to-output mix that is $0.478 per million tokens, cheaper than 61% of the 445 priced models we track.
What is the context window of Mixtral 8x7B Instruct v0.1?
Mixtral 8x7B Instruct v0.1 accepts up to 32,768 tokens per request and can write up to 32,768 tokens in one response.
How good is Mixtral 8x7B Instruct v0.1?
Epoch AI gives Mixtral 8x7B Instruct v0.1 a Capabilities Index score of 118.4 (likely range 110.9–121.0), ranking it #160 of 165 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 30.6%.
Is Mixtral 8x7B Instruct v0.1 open source?
Yes. Mistral AI publishes the weights under the Apache 2.0 licence, so it can be downloaded and self-hosted.
What inputs does Mixtral 8x7B Instruct v0.1 support?
Mixtral 8x7B Instruct v0.1 accepts text and replies in text. It is not a dedicated reasoning model, does not support tool calling.
When was Mixtral 8x7B Instruct v0.1 released?
Mistral AI released Mixtral 8x7B Instruct v0.1 on Dec 11, 2023.
What are the best alternatives to Mixtral 8x7B Instruct v0.1?
The closest current models from other labs on capability, price and release date are Claude Haiku 3 (Anthropic, ECI 118.8, $0.25 / $1.25), Gemma 2 27B (Google, ECI 122.1, $0.65 / $0.65), Llama-3.1-70B-Instruct (Meta, ECI 125.9, $0.72 / $0.72) and GPT-4o mini (OpenAI, ECI 126.5, $0.15 / $0.60).