Best of / AI models / Cheapest LLM API with a 1M-token context window
Best of · AI API prices · checked Oct 23, 2026
Cheapest LLM API with a 1M-token context window
Short answerClaude Haiku 5.5 (Anthropic) is the cheapest: $0.35 per 1,000 chatbot replies. Next: GPT-6 Luna at $0.35 and GPT-5.6 Luna at $0.78. 24 current models qualify (prices checked Oct 23, 2026). Price only, not answer quality.
Every model that qualifies, cheapest first
| # | Model | Provider | Per 1,000 chatbot replies | Context | Input / output per 1M |
|---|---|---|---|---|---|
| 1 | Claude Haiku 5.5 | Anthropic | $0.35 | 1M | $0.1 / $0.5 |
| 2 | GPT-6 Luna | OpenAI | $0.35 | 1.05M | $0.1 / $0.5 |
| 3 | GPT-5.6 Luna | OpenAI | $0.78 | 1.05M | $0.2 / $1.2 |
| 4 | DeepSeek Flash | DeepSeek | $0.93 | 1M | $0.3 / $1.2 |
| 5 | Gemini 3.1 Flash-Lite | $0.97 | 1.05M | $0.25 / $1.5 | |
| 6 | Gemini 3.5 Flash-Lite | $1.45 | 1.05M | $0.3 / $2.5 | |
| 7 | Gemini 3 Flash Preview | $1.95 | 1.05M | $0.5 / $3 | |
| 8 | Gemini 3.8 Flash | $2.62 | 1.05M | $0.75 / $3.75 | |
| 9 | Gemini 3.6 Flash | $2.62 | 1.05M | $0.75 / $3.75 | |
| 10 | DeepSeek V4 Pro | DeepSeek | $3.56 | 1M | $1.32 / $3.96 |
| 11 | Claude Sonnet 5.5 | Anthropic | $7.00 | 1M | $2 / $10 |
| 12 | GPT-6.1 Sol | OpenAI | $7.00 | 1.05M | $2 / $10 |
| 13 | GPT-6 Sol | OpenAI | $7.00 | 1.05M | $2 / $10 |
| 14 | Gemini 4 Argon | $7.00 | 1.05M | $2 / $10 | |
| 15 | GPT-5.6 Terra | OpenAI | $7.80 | 1.05M | $2 / $12 |
| 16 | Gemini 3.1 Pro Preview | $7.80 | 1.05M | $2 / $12 | |
| 17 | GPT-5.4 | OpenAI | $9.75 | 1.05M | $2.5 / $15 |
| 18 | Claude Opus 5.5 | Anthropic | $14.00 | 1M | $4 / $20 |
| 19 | GPT-5.6 Sol | OpenAI | $14.00 | 1.05M | $4 / $20 |
| 20 | GPT-5.5 | OpenAI | $19.50 | 1.05M | $5 / $30 |
Rules
Current models whose provider page lists a context window of 1,000,000 tokens or more, ranked by the cost of 1,000 chatbot replies (1,500 tokens in, 400 out) at standard prices. Current = not deprecated, legacy or shut down on the provider's model page. Prices from each provider's pricing page; full method on LLM prices.
Want a pick for your exact job and volume? Pick for me, or see the cheapest model for each job.
Up next
Another best-of list: Same prices, a different requirement.Cheapest LLM API with prompt cachingRead it next →