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, with models Anyscale lists no paid price for at the end. Listed prices from LiteLLM, OpenRouter and Vercel.
Models served
12
on this provider
Cheapest input
$0.15
per 1M tokens
Cheapest output
$0.15
per 1M tokens
Max context
131K
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
| Model ID | |||||
|---|---|---|---|---|---|
| Gemma 7B It | 8K | $0.15 | $0.15 | anyscale/google/gemma-7b-it | |
| Llama 2 7B Chat HF | Meta | 4K | $0.15 | $0.15 | anyscale/meta-llama/Llama-2-7b-chat-hf |
| Llama 3 8B Instruct | Meta | 8K | $0.15 | $0.15 | anyscale/meta-llama/Meta-Llama-3-8B-Instruct |
| Mistral 7B Instruct V0.1 | Mistral | 33K | $0.15 | $0.15 | anyscale/mistralai/Mistral-7B-Instruct-v0.1 |
| Mixtral 8x7B Instruct V0.1 | Mistral | 33K | $0.15 | $0.15 | anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1 |
| Zephyr 7B Beta | Other | 33K | $0.15 | $0.15 | anyscale/HuggingFaceH4/zephyr-7b-beta |
| Llama 2 13B Chat HF | Meta | 4K | $0.25 | $0.25 | anyscale/meta-llama/Llama-2-13b-chat-hf |
| Mixtral 8x22B Instruct V0.1 | Mistral | 66K | $0.90 | $0.90 | anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1 |
| Codellama 34B Instruct HF | Meta | 4K | $1.00 | $1.00 | anyscale/codellama/CodeLlama-34b-Instruct-hf |
| Codellama 70B Instruct HF | Meta | 4K | $1.00 | $1.00 | anyscale/codellama/CodeLlama-70b-Instruct-hf |
| Llama 2 70B Chat HF | Meta | 4K | $1.00 | $1.00 | anyscale/meta-llama/Llama-2-70b-chat-hf |
| Llama 3 70B Instruct | Meta | 131K | $1.00 | $1.00 | anyscale/meta-llama/Meta-Llama-3-70B-Instruct |
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI