API pricing comparison

The cheapest LLM API prices per token

As of 2026-06-22, the cheapest LLM API input tokens are Amazon nova-micro at $0.035 per 1M, and the cheapest output is Mistral ministral-3-3b at $0.10 per 1M. Every price is dated and first-party-sourced.

Cheapest input tokens

#ModelProviderInput /1MSource
1nova-microAmazon$0.035aws.amazon.com
2command-r7bCohere$0.037cohere.com
3qwen-flashAlibaba$0.050www.alibabacloud.com
4qwen-turboAlibaba$0.050www.alibabacloud.com
5nova-liteAmazon$0.060aws.amazon.com
6gemini-1.5-flashGoogle$0.075web.archive.org
7qwen3.5-flashAlibaba$0.10www.alibabacloud.com
8gemini-2.5-flash-liteGoogle$0.10web.archive.org
9devstral-small-2Mistral$0.10mistral.ai
10ministral-3-3bMistral$0.10mistral.ai

Cheapest output tokens

#ModelProviderOutput /1MSource
1ministral-3-3bMistral$0.10mistral.ai
2nova-microAmazon$0.14aws.amazon.com
3command-r7bCohere$0.15cohere.com
4ministral-3-8bMistral$0.15mistral.ai
5llama-3.1-8bMeta$0.18www.together.ai
6qwen-turboAlibaba$0.20www.alibabacloud.com
7ministral-3-14bMistral$0.20mistral.ai
8nova-liteAmazon$0.24aws.amazon.com
9deepseek-v4-flashDeepSeek$0.28api-docs.deepseek.com
10gemini-1.5-flashGoogle$0.30web.archive.org

Cheap per token is not the same as cheap per job: the lowest-priced models are usually small, so they can spend more tokens to do the same work. And list price is not your bill once caching and short prompts are counted. To see what you actually spend, priced at the rate in effect each day, use Goei.

More from the index

Open data, CC BY 4.0. Prices validated as of 2026-06-22.