Mixtral 8x7B v0.1
The original Mixtral MoE from late 2023. Kicked off the open-weights MoE wave; now superseded by 8x22B and Llama 3.x.
Mixtral 8x7B v0.1 is a efficient AI model from Mistral. It costs $0.2400 per million input tokens and $0.2400 per million output tokens (blended $0.2400/M), with a 32,000-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
Hand-maintained from Mistral's published pricing; no check date on record.
- Open weights
- 32K context
- Wide ecosystem
- Legacy Mixtral 8x7B deployments
- Fine-tune base
Benchmarks
More from Mistral
See all 15 →Frequently asked questions
How much does Mixtral 8x7B v0.1 cost?
Mixtral 8x7B v0.1 costs $0.2400 per million input tokens and $0.2400 per million output tokens, for a blended reference rate of $0.2400 per million tokens.
What is Mixtral 8x7B v0.1's context window?
Mixtral 8x7B v0.1 supports up to 32,000 tokens of context in a single request.
What is Mixtral 8x7B v0.1 best for?
Mixtral 8x7B v0.1 is well suited to Open weights, 32K context and Wide ecosystem.
Who makes Mixtral 8x7B v0.1?
Mixtral 8x7B v0.1 is developed and served by Mistral. It was released in Dec 2023.
