Verified November 2026

Home › Best › Cheapest LLM API

Cheapest LLM API in 2026

Ranked by blended list price — three input tokens to one output token, roughly the mix of a chat or retrieval workload. Cached input and batch discounts can pull the real bill lower; the calculator applies both. Six reseller-priced rows are excluded because their vendors no longer publish per-token rates.

Top 15 by blended price

#ModelProviderInput $/MOutput $/MBlended $/MContext
1GPT-6 LunaOpenAI$0.10$0.50$0.2251,050,000
2Claude Haiku 5.5Anthropic$0.10$0.50$0.225200,000
3Mistral Small 4Mistral AI$0.15$0.60$0.30256,000
4GPT-5.6 LunaOpenAI$0.20$1.20$0.501,050,000
5GPT-5.4 nanoOpenAI$0.20$1.25$0.512400,000
6DeepSeek V4.1 FlashDeepSeek$0.30$1.20$0.601,100,000
7Gemini 3.1 Flash-LiteGoogle$0.25$1.50$0.6251,000,000
8Gemini 3.5 Flash-LiteGoogle$0.30$2.50$0.9251,000,000
9Mistral Large 4Mistral AI$0.70$2.10$1.231,000,000
10Gemini 3.8 FlashGoogle$0.75$3.75$1.691,000,000
11Gemini 3.6 FlashGoogle$0.75$3.75$1.691,000,000
12GPT-5.4 miniOpenAI$0.75$4.50$1.88400,000
13Grok 4.3xAI$1.25$2.50$1.881,000,000
14GPT-6.1 TerraOpenAI$1$5$2.251,050,000
15Claude Haiku 4.5Anthropic$1$5$2.25200,000

Frequently asked

What is the cheapest LLM API in 2026?

By blended list price, the cheapest tier is GPT-6 Luna and Claude Haiku 5.5 at about $0.20 per million tokens, followed by Mistral Small 4 at $0.26 and DeepSeek V4.1 Flash at $0.48. Cached input and batch discounts can cut these by a further 50-90%.

Is the cheapest model always the best choice?

No. The cheapest models have smaller context windows and lower quality on hard tasks. Route by task: use a budget model for classification and extraction, and a frontier model only where the quality difference matters.

How is blended price calculated?

Blended price is (3 x input price + 1 x output price) / 4, which approximates a 3:1 input-to-output workload. Your own mix may differ, so check the calculator.

Browse all 45 models · Compare two models