Anyscale API pricing
Hosted12 language models
As of Oct 14, 2026, Anyscale lists 12 language models through its API. Its cheapest language model is Mixtral 8x7b Instruct V0.1 at $0.15 input / $0.15 output per million tokens.
Language models (12)
Prices per million tokens.
anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1
- Input
- $0.15
- Output
- $0.15
- Context
- 16K
Codellama 34B Instruct Hf
anyscale/codellama/CodeLlama-34b-Instruct-hf
- Input
- $1.00
- Output
- $1.00
- Context
- 4K
Codellama 70B Instruct Hf
anyscale/codellama/CodeLlama-70b-Instruct-hf
- Input
- $1.00
- Output
- $1.00
- Context
- 4K
Gemma 7B IT
anyscale/google/gemma-7b-it
- Input
- $0.15
- Output
- $0.15
- Context
- 8K
Llama 2 7B Chat Hf
anyscale/meta-llama/Llama-2-7b-chat-hf
- Input
- $0.15
- Output
- $0.15
- Context
- 4K
Llama 2 13B Chat Hf
anyscale/meta-llama/Llama-2-13b-chat-hf
- Input
- $0.25
- Output
- $0.25
- Context
- 4K
Llama 2 70B Chat Hf
anyscale/meta-llama/Llama-2-70b-chat-hf
- Input
- $1.00
- Output
- $1.00
- Context
- 4K
Meta Llama 3 8B Instruct
anyscale/meta-llama/Meta-Llama-3-8B-Instruct
- Input
- $0.15
- Output
- $0.15
- Context
- 8K
Meta Llama 3 70B Instruct
anyscale/meta-llama/Meta-Llama-3-70B-Instruct
- Input
- $1.00
- Output
- $1.00
- Context
- 8K
Mistral 7B Instruct V0.1
anyscale/mistralai/Mistral-7B-Instruct-v0.1
- Input
- $0.15
- Output
- $0.15
- Context
- 16K
Mixtral 8x22b Instruct V0.1
anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1
- Input
- $0.90
- Output
- $0.90
- Context
- 66K
Zephyr 7B Beta
anyscale/HuggingFaceH4/zephyr-7b-beta
- Input
- $0.15
- Output
- $0.15
- Context
- 16K
Prices in USD from LiteLLM and models.dev, checked daily; confirm on Anyscale's pricing page before you rely on a number.