Cheapest LLM API models by price
Ranked cheapest first by combined input + output price per 1M tokens, using the same list prices as the main pricing table, verified 2026-10-20. The blended column is the cost of one typical request: a 1,000-token prompt and a 500-token response. Cheapest on list price is not always cheapest in production: check output price and retries before choosing.
| Rank | Model | Vendor | Input / 1M | Output / 1M | Blended / request |
|---|---|---|---|---|---|
| 1 | GPT-5 nano | OpenAI | $0.05 | $0.40 | $0.0003 |
| 2 | DeepSeek V3.2 (chat) | DeepSeek | $0.28 | $0.42 | $0.0005 |
| 3 | GPT-4o mini | OpenAI | $0.15 | $0.60 | $0.0004 |
| 4 | Llama 4 Maverick | Meta | $0.27 | $0.85 | $0.0007 |
| 5 | GPT-5 mini | OpenAI | $0.25 | $2.00 | $0.0013 |
| 6 | DeepSeek R1 (reasoner) | DeepSeek | $0.55 | $2.19 | $0.0016 |
| 7 | Gemini 2.5 Flash | $0.30 | $2.50 | $0.0015 | |
| 8 | Kimi K2 | Moonshot | $0.60 | $2.50 | $0.0019 |
| 9 | Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | $0.0035 |
| 10 | Qwen3 Max | Alibaba | $1.20 | $6.00 | $0.0042 |
| 11 | Mistral Large 2 | Mistral | $2.00 | $6.00 | $0.005 |
| 12 | GPT-5 | OpenAI | $1.25 | $10.00 | $0.0063 |
| 13 | Gemini 2.5 Pro | $1.25 | $10.00 | $0.0063 | |
| 14 | GPT-4o | OpenAI | $2.50 | $10.00 | $0.0075 |
| 15 | Claude Sonnet 4.5 | Anthropic | $3.00 | $15.00 | $0.01 |
| 16 | Grok 4 | xAI | $3.00 | $15.00 | $0.01 |
| 17 | Claude Opus 4.1 | Anthropic | $15.00 | $75.00 | $0.05 |
Prices are list prices from official provider pages and may change. Always confirm on the provider's site before making purchasing decisions.