Mistral 7B (Anyscale)
The 7B Mistral that put open-weights chat models on the map. v0.3 added function calling and an extended vocabulary.
Mistral 7B (Anyscale) is a efficient AI model from Anyscale. It costs $0.150 per million input tokens and $0.150 per million output tokens (blended $0.150/M), with a 32,000-token context window.
Profile inherited from upstream Mistral 7B ↗ — this is a hosted variant of the same open-weights model.
- Open weights (Apache 2.0)
- Single-GPU
- Function calling
- Wide ecosystem
- Self-hosted small chat
- Fine-tune base
- Edge deployments
Benchmarks
More from Anyscale
See all 4 →Frequently asked questions
How much does Mistral 7B (Anyscale) cost?
Mistral 7B (Anyscale) costs $0.150 per million input tokens and $0.150 per million output tokens, for a blended reference rate of $0.150 per million tokens.
What is Mistral 7B (Anyscale)'s context window?
Mistral 7B (Anyscale) supports up to 32,000 tokens of context in a single request.
What is Mistral 7B (Anyscale) best for?
Mistral 7B (Anyscale) is well suited to Open weights (Apache 2.0), Single-GPU and Function calling.
Who makes Mistral 7B (Anyscale)?
Mistral 7B (Anyscale) is developed and served by Anyscale. It was released in May 2024.