Cheapest by list price
The cheapest LLM APIs with a 1M-token context window
Only providers that list a context window of at least one million tokens count, so a cheap host with a short limit does not qualify. Right now DeepSeek V4 Flash 0731 at DeepInfra is cheapest at $0.105 per 1M blended tokens.
Standard list prices in USD, ranked by blended price (3 input : 1 output tokens). Last price change Oct 21, 2026. How we rank.
Top 25 by price
Cheapest is not the same as best. Price says nothing about output quality, speed or rate limits, so check public benchmarks such as Artificial Analysis before you switch.
| # | Model | Cheapest provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|---|
| 1 | DeepSeek V4 Flash 0731 | DeepInfraPricing page | $0.08 | $0.18 | $0.105 | 1M |
| 2 | DeepSeek-V4-Flash | DeepInfraPricing page | $0.09 | $0.18 | $0.1125 | 1M |
| 3 | Gemini 2.5 Flash-Lite | Oracle Cloud Generative AIPricing page | $0.075 | $0.30 | $0.1313 | 1M |
| 4 | gpt-4.1-nano | Microsoft Azure AI FoundryPricing page | $0.10 | $0.40 | $0.175 | 1M |
| 5 | MiMo-V2.6-Flash | DeepInfraPricing page | $0.14 | $0.28 | $0.175 | 1M |
| 6 | Qwen3.8 Flash | DeepInfraPricing page | $0.113 | $0.382 | $0.1803 | 1M |
| 7 | Claude Haiku 5.5 | AnthropicPricing page | $0.10 | $0.50 | $0.20 | 1M |
| 8 | DeepSeek V4.1 Flash 1017 | DeepInfraPricing page | $0.14 | $0.42 | $0.21 | 1M |
| 9 | DeepSeek-V4.1-Flash | DeepInfraPricing page | $0.14 | $0.42 | $0.21 | 1M |
| 10 | MiMo-V2.5 | Novita AIPricing page | $0.168 | $0.336 | $0.21 | 1M |
| 11 | GLM-5.3-Flash | Z.aiPricing page | $0.15 | $0.50 | $0.2375 | 1M |
| 12 | Gemini 2.5 Flash | Oracle Cloud Generative AIPricing page | $0.15 | $0.60 | $0.2625 | 1M |
| 13 | MiniMax-M3.1-Flash | Fireworks AIPricing page | $0.15 | $0.60 | $0.2625 | 1M |
| 14 | Nemotron 3.5 Super VL | BasetenPricing page | $0.20 | $0.50 | $0.275 | 1M |
| 15 | Llama 4 Scout 17B 16E Instruct | Microsoft Azure AI FoundryPricing page | $0.20 | $0.78 | $0.345 | 10M |
| 16 | Llama 4 Maverick 17B 128E Instruct FP8 | DeepInfraPricing page | $0.20 | $0.80 | $0.35 | 1M |
| 17 | DeepSeek V4 Flash Vision Exp | DeepSeekPricing page | $0.30 | $1.20 | $0.525 | 1M |
| 18 | DeepSeek V4.1 Flash 1017 | DeepSeekPricing page | $0.30 | $1.20 | $0.525 | 1M |
| 19 | minimax-m2 | Amazon BedrockPricing page | $0.30 | $1.20 | $0.525 | 1M |
| 20 | MiniMax-M3 | Novita AIPricing page | $0.30 | $1.20 | $0.525 | 1M |
| 21 | MiMo-V2.6-Pro | DeepInfraPricing page | $0.43 | $0.87 | $0.54 | 1M |
| 22 | Qwen3.7 Plus | Together AIPricing page | $0.32 | $1.28 | $0.56 | 1M |
| 23 | Gemini 3.1 Flash Lite | Google Gemini APIPricing page | $0.25 | $1.50 | $0.5625 | 1M |
| 24 | Beam 1.0 501B A23B | Together AIPricing page | $0.40 | $1.20 | $0.60 | 1M |
| 25 | MiMo-V2.5-Pro | Novita AIPricing page | $0.522 | $1.04 | $0.6525 | 1M |
Only models listed by at least three providers are ranked. Order depends on listed price only; no provider pays for its position.
Compare more
Pick a model to see every provider
The cheapest LLM APIs right now - All LLM API prices - Recent price changes