Cheapest long-context models
Models with at least a 200K-token context window, ranked by input price — for summarising books, legal dumps and codebases.
Current leader: Gemini Exp 1114 (Google Gemini). Refreshed 2026-10-28 12:57 UTC.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | Gemini Exp 1114 | Google Gemini | free | free | — | 1.0M |
| 2 | Gemini Exp 1206 | Google Gemini | free | free | — | 2.1M |
| 3 | Gemma 4 26b A4b It | Google Gemini | free | free | — | 262K |
| 4 | Gemma 4 31b It | Google Gemini | free | free | — | 262K |
| 5 | Labs Leanstral 1 5 | Mistral AI | free | free | — | 262K |
| 6 | Labs Leanstral 1 5 1 | Mistral AI | free | free | — | 262K |
| 7 | Qwen3 Coder:480b Cloud | Ollama | free | free | — | 262K |
| 8 | Ternary Bonsai 27B | Together AI | free | free | — | 262K |
| 9 | Databricks GPT 5 Nano | Databricks | $0.05 | $0.4 | $0.005 | 272K |
| 10 | Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | — | 1M |
| 11 | Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | — | 1M |
| 12 | Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | — | 1M |
| 13 | GPT 5 Nano | OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 14 | GPT 5 Nano | OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 15 | GPT 5 Nano | Azure OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 16 | Nemotron 3 Nano 30B A3B | DeepInfra | $0.05 | $0.2 | $0.025 | 262K |
| 17 | Nemotron Lightning 3p5 30b A3b | Fireworks AI | $0.05 | $0.2 | $0.01 | 262K |
| 18 | Nemotron 3 Nano 30b A3b | Novita AI | $0.05 | $0.2 | — | 262K |
| 19 | GPT 5 Nano | Azure OpenAI | $0.055 | $0.44 | $0.0055 | 272K |
| 20 | GLM 4.7 Flash | DeepInfra | $0.06 | $0.4 | $0.01 | 203K |
| 21 | NVIDIA Nemotron 3 Nano 30B A3B | Nebius | $0.06 | $0.24 | — | 262K |
| 22 | Nemotron 3 Nano Omni | Nebius | $0.06 | $0.24 | — | 262K |
| 23 | Nemotron 3 5 Lightning | Nebius | $0.06 | $0.24 | — | 1.0M |
| 24 | Ling 3.0 Flash Fast | Novita AI | $0.06 | $0.18 | $0.012 | 262K |
| 25 | Ling 3.0 Flash | Novita AI | $0.06 | $0.18 | $0.012 | 262K |
| 26 | Gemma 4 26B A4B It | DeepInfra | $0.07 | $0.34 | — | 262K |
| 27 | Glm 4.7 Flash | Novita AI | $0.07 | $0.4 | $0.01 | 200K |
| 28 | Amazon.nova Lite V1:0 | Amazon Bedrock | $0.072 | $0.288 | $0.018 | 300K |
| 29 | Nvidia.nemotron Nano 3 30b | Amazon Bedrock | $0.072 | $0.288 | — | 262K |
| 30 | NVIDIA Nemotron 3.5 Lightning | DeepInfra | $0.08 | $0.2 | $0.04 | 262K |
| 31 | DeepSeek V4 Flash 0731 | DeepInfra | $0.08 | $0.18 | $0.016 | 1.0M |
| 32 | NVIDIA Nemotron 3 Super 120B A12B | DeepInfra | $0.085 | $0.4 | — | 262K |
| 33 | Qwen3 235B A22B Instruct 2507 | DeepInfra | $0.09 | $0.55 | — | 262K |
| 34 | Qwen3 Next 80B A3B Instruct | DeepInfra | $0.09 | $1.1 | — | 262K |
| 35 | Gemma 4 31B It Turbo | DeepInfra | $0.09 | $0.34 | $0.05 | 262K |
| 36 | DeepSeek V4 Flash | DeepInfra | $0.09 | $0.18 | $0.018 | 1.0M |
| 37 | Claude Haiku 5 5 | Anthropic | $0.1 | $0.5 | $0.01 | 1M |
| 38 | Gemini 2.5 Flash Lite | Google Gemini | $0.1 | $0.4 | $0.01 | 1.0M |
| 39 | Muse Spark 1.2 Contributor | Meta | $0.1 | $0.2 | $0.002 | 1.0M |
| 40 | Muse Spark 1.3 Contributor | Meta | $0.1 | $0.2 | $0.002 | 1.0M |
| 41 | Devstral Small | Mistral AI | $0.1 | $0.3 | $0.01 | 256K |
| 42 | GPT 4.1 Nano | OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 43 | GPT 4.1 Nano | OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 44 | GPT 6 Luna | OpenAI | $0.1 | $0.5 | $0.01 | 922K |
| 45 | GPT 4.1 Nano | Azure OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 46 | GPT 4.1 Nano | Azure OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 47 | GPT 6 Luna | Azure OpenAI | $0.1 | $0.5 | $0.01 | 922K |
| 48 | GPT 6 Luna | Azure OpenAI | $0.1 | $0.5 | $0.01 | 922K |
| 49 | Claude Haiku 5 5 | Amazon Bedrock | $0.1 | $0.5 | $0.01 | 1M |
| 50 | Gemma 4 26b A4b It | Cloudflare Workers AI | $0.1 | $0.3 | — | 256K |
| 51 | Llama 4 Scout 17B 16E Instruct | DeepInfra | $0.1 | $0.3 | — | 328K |
| 52 | Qwen3.6 35B A3B | DeepInfra | $0.1 | $0.95 | — | 262K |
| 53 | Seed 2.0 Mini | DeepInfra | $0.1 | $0.4 | $0.02 | 256K |
| 54 | Qwen3.5 9B | DeepInfra | $0.1 | $0.15 | — | 262K |
| 55 | Ministral 3 3b Instruct 2512 | Fireworks AI | $0.1 | $0.1 | — | 256K |
| 56 | Qwen3 1p7b Fp8 Draft | Fireworks AI | $0.1 | $0.1 | — | 262K |
| 57 | Cosmos3 Super Reasoner | Nebius | $0.1 | $0.3 | — | 262K |
| 58 | Qwen3 30B A3B Instruct 2507 | Nebius | $0.1 | $0.3 | — | 262K |
| 59 | Mimo V2 Flash | Novita AI | $0.11 | $0.33 | $0.024 | 262K |
| 60 | Anthropic.claude Haiku 5 5 | Amazon Bedrock | $0.12 | $0.6 | $0.012 | 1M |
Other use cases
Frequently asked
› Which AI model is cheapest for very long documents?
Gemini Exp 1114 from Google Gemini currently leads this list, at $0/1M input tokens. Rankings are recomputed from the raw dataset on every refresh, so they track price cuts automatically.
› How are these rankings calculated?
Each use case applies a capability filter (context size, vision, tool calling, cache pricing) and then ranks the surviving models by the blended cost that profile actually pays. See the methodology page for the exact formulas.
› Is the cheapest model always the right choice?
No. Check the capability flags and context window, and benchmark quality on your own data — the cheapest model that fails your evals costs more than the second cheapest that passes them.