API pricing

Anyscale Pricing

Anyscale charges between $0.150 and $1.00 per 1 million output tokens, depending on the model. Google Gemma 7B It is the cheapest at $0.150/1M output and $0.150/1M input; Codellama Codellama 34B Instruct Hf is the most expensive at $1.00/1M output. The largest context window is 66K tokens (Mistralai Mixtral 8X22B Instruct V0.1). Prices are USD, current as of July 20, 2026.

Last updated · synced weekly from the upstream model catalog

Cheapest input

$0.150/1M

Google Gemma 7B It

Cheapest output

$0.150/1M

Google Gemma 7B It

Longest context

66K

Mistralai Mixtral 8X22B Instruct V0.1

Models priced

12

Avg $0.504/1M output

Pricing by model

All prices in USD per 1 million tokens. All 12 priced models, cheapest first.

ModelInput / 1MOutput / 1MContext
Google Gemma 7B It$0.150$0.1508K
Huggingfaceh4 Zephyr 7B Beta$0.150$0.15016K
Meta Llama Llama 2 7B Chat Hf$0.150$0.1504K
Meta Llama Meta Llama 3 8B Instruct$0.150$0.1508K
Mistralai Mistral 7B Instruct V0.1$0.150$0.15016K
Mistralai Mixtral 8X7B Instruct V0.1$0.150$0.15016K
Meta Llama Llama 2 13B Chat Hf$0.250$0.2504K
Mistralai Mixtral 8X22B Instruct V0.1$0.900$0.90066K
Codellama Codellama 34B Instruct Hf$1.00$1.004K
Codellama Codellama 70B Instruct Hf$1.00$1.004K
Meta Llama Llama 2 70B Chat Hf$1.00$1.004K
Meta Llama Meta Llama 3 70B Instruct$1.00$1.008K

Frequently asked questions

How much does Anyscale cost per 1M tokens?

Anyscale pricing ranges from $0.150 to $1.00 per 1 million output tokens across 12 models. Input tokens are cheaper than output on every model. Rates current as of July 20, 2026.

What is the cheapest Anyscale model?

Google Gemma 7B It is the cheapest Anyscale model on both axes — $0.150 per 1M input tokens and $0.150 per 1M output. It is the right default for high-volume, low-complexity work such as classification, extraction and routing.

What is the largest Anyscale context window?

Mistralai Mixtral 8X22B Instruct V0.1 has the largest context window in the Anyscale catalog at 66K input tokens, with up to 66K output tokens per response.

How do I calculate my actual Anyscale bill?

Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.

Other providers

What will this actually cost you?

Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.

Open the free cost calculator