Anyscale LLM API pricing

Every model Anyscale serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.

Models served

12

on this provider

Cheapest input

$0.15

per 1M tokens

Cheapest output

$0.15

per 1M tokens

Max context

131K

tokens

Model ID
Llama 2 7B Chat HFMeta4K$0.15$0.15anyscale/meta-llama/Llama-2-7b-chat-hf
Zephyr 7B BetaOther33K$0.15$0.15anyscale/HuggingFaceH4/zephyr-7b-beta
Gemma 7B ItGoogle8K$0.15$0.15anyscale/google/gemma-7b-it
Mixtral 8x7B Instruct V0 1Mistral33K$0.15$0.15anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1
Meta Llama 3 8B InstructMeta8K$0.15$0.15anyscale/meta-llama/Meta-Llama-3-8B-Instruct
Mistral 7B Instruct V0 1Mistral16K$0.15$0.15anyscale/mistralai/Mistral-7B-Instruct-v0.1
Llama 2 13B Chat HFMeta4K$0.25$0.25anyscale/meta-llama/Llama-2-13b-chat-hf
Mixtral 8x22B Instruct V0 1Mistral66K$0.90$0.90anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1
Codellama 34B Instruct HFMeta4K$1.00$1.00anyscale/codellama/CodeLlama-34b-Instruct-hf
Codellama 70B Instruct HFMeta4K$1.00$1.00anyscale/codellama/CodeLlama-70b-Instruct-hf
Llama 2 70B Chat HFMeta4K$1.00$1.00anyscale/meta-llama/Llama-2-70b-chat-hf
Meta Llama 3 70B InstructMeta131K$1.00$1.00anyscale/meta-llama/Meta-Llama-3-70B-Instruct
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI