Context window costs
A context window is a ceiling, not a target. It tells you what a model will accept. It says nothing about what you should send, and the price of sending it climbs in a straight line with every token you add.
This page prices that line. It takes four input sizes and charges every model in the catalogue for reading each one once.
What it costs to fill a context window
466 models, snapshot 2026-10-31. Regenerated from the models.dev catalogue by apps/web/scripts/fetch-models.ts on every build, not maintained by hand.
| Context | Models | Cheapest | Median | Dearest |
|---|---|---|---|---|
| 430 of 466 | $0.0010 | $0.030 | $14.00 | |
| 268 of 466 | $0.0039 | $0.071 | $6.44 | |
| 146 of 466 | $0.0081 | $0.173 | $13.64 | |
| 140 of 466 | $0.016 | $0.345 | $27.27 |
Pick a size to price it against every model below. 236K is the median repository bundle measured across 60 public repositories, not a round number.
268 models accept 236,218 tokens
| Model | Per 1M in | To fill |
|---|---|---|
| GLM-5.3-FlashOpenRouter | $0.016 | $0.0039 |
| Gemma 4 26B A4B ITKilo Gateway | $0.020 | $0.0047 |
| Qwen3.5 2BRequesty | $0.020 | $0.0047 |
| Ling 3.0 FlashOpenRouter | $0.021 | $0.0050 |
| Qwen FlashAlibaba (China) | $0.022 | $0.0052 |
| Seed 1.6 FlashVolcengine Ark | $0.022 | $0.0053 |
| Nemotron 3.5 Lightning 30B A3BKilo Gateway | $0.025 | $0.0059 |
| Qwen3.5 FlashAIHubMix | $0.028 | $0.0067 |
| Qwen3.7 FlashAIHubMix | $0.028 | $0.0067 |
| Seed 2.0 MiniVolcengine Ark | $0.030 | $0.0070 |
| DeepSeek V4.1 Flashengy | $0.030 | $0.0071 |
| DeepSeek V4.1 Flash 1017engy | $0.030 | $0.0071 |
| Solar Pro 4NanoGPT | $0.030 | $0.0071 |
| DeepSeek V4 Flash 0731Merge Gateway | $0.035 | $0.0083 |
| GPT-5 MiniQiHang | $0.040 | $0.0094 |
| Mercury 2.5OpenRouter | $0.040 | $0.0094 |
| Qwen3.5 4BEmpirioLabs AI | $0.040 | $0.0094 |
| Qwen TurboQiniu | $0.043 | $0.010 |
| Qwen3.6 35B-A3Bengy | $0.045 | $0.011 |
| Qwen3.8 27Bengy | $0.045 | $0.011 |
| GPT-5 NanoPoe | $0.045 | $0.011 |
| Nemotron 3 Nano 30B A3BCrusoe | $0.050 | $0.012 |
| Qwen3.5 9BNanoGPT | $0.050 | $0.012 |
| Solar Mini 4NanoGPT | $0.050 | $0.012 |
| Gemini 2.0 Flash-LitePoe | $0.052 | $0.012 |
| Qwen3.5 35B-A3BAIHubMix | $0.056 | $0.013 |
| Ling 3.0 Flash VLNanoGPT | $0.060 | $0.014 |
| Nova LiteAmazon Bedrock | $0.060 | $0.014 |
| Nova Lite 1.0OpenRouter | $0.060 | $0.014 |
| DeepSeek V4 FlashUnoRouter | $0.063 | $0.015 |
| GLM-5.3OpenRouter | $0.070 | $0.017 |
| Gemini 3 Flash PreviewQiHang | $0.070 | $0.017 |
| GLM-5.2NanoGPT | $0.070 | $0.017 |
| Qwen3-Coder 30B-A3B InstructHugging Face | $0.070 | $0.017 |
| Ling 3.0 Flash FinNovita AI | $0.075 | $0.018 |
| Ling 3.0 Flash SanteNovita AI | $0.075 | $0.018 |
| Ling 3.1 FlashNanoGPT | $0.075 | $0.018 |
| MiniMax-M3.1-FlashEden AI | $0.075 | $0.018 |
| Mistral Small 3.2 24BOpenRouter | $0.075 | $0.018 |
| Nemotron 3 Super 120B A12BKilo Gateway | $0.080 | $0.019 |
| Nemotron 3.5 Super VL 120B A12BPioneer | $0.080 | $0.019 |
| Hy3Kilo Gateway | $0.083 | $0.019 |
| Qwen3.5 27BAIHubMix | $0.085 | $0.020 |
| MiMo-V2.6-FlashKilo Gateway | $0.087 | $0.021 |
| Seed 2.0 LiteVolcengine Ark | $0.089 | $0.021 |
| Gemini 2.5 FlashQiHang | $0.090 | $0.021 |
| Gemini 2.5 Flash-Lite Preview 06-17Jiekou.AI | $0.090 | $0.021 |
| Gemini 2.5 Flash-Lite Preview 09-2025Jiekou.AI | $0.090 | $0.021 |
| GPT-4.1 nanoPoe | $0.090 | $0.021 |
| Laguna S 2.1Vultr | $0.090 | $0.021 |
| Qwen3 235B-A22B Instruct 2507Meganova | $0.090 | $0.021 |
| Qwen3 30B-A3B Instruct 2507Ambient | $0.090 | $0.021 |
| Step 3.5 FlashCommandCode | $0.090 | $0.021 |
| Claude Haiku 5.5302.AI | $0.100 | $0.024 |
| Gemini 2.0 FlashPoe | $0.100 | $0.024 |
| Gemini 2.5 Flash-LiteLLMTR | $0.100 | $0.024 |
| Gemma 4 12B ITSiliconFlow | $0.100 | $0.024 |
| Gemma 4 31B ITDevPass (LLM Gateway) | $0.100 | $0.024 |
| GPT-6 Luna302.AI | $0.100 | $0.024 |
| Mercury 3Inception | $0.100 | $0.024 |
| MiMo-V2-FlashMeganova | $0.100 | $0.024 |
| Ministral 3 3BAmazon Bedrock | $0.100 | $0.024 |
| Nemotron 3 Nano Omni 30B A3B ReasoningVultr | $0.100 | $0.024 |
| Nemotron 3 Ultra 550B A55Brouting.run | $0.100 | $0.024 |
| Ornith 1.5 35B A3BRunInfra | $0.100 | $0.024 |
| Qwen3.8 Flash NextVultr | $0.100 | $0.024 |
| Step 3.5 Flash 2603EmpirioLabs AI | $0.100 | $0.024 |
| Qwen3.5 PlusAIHubMix | $0.110 | $0.026 |
| Qwen3.5 122B-A10BAIHubMix | $0.113 | $0.027 |
| Qwen3.8 FlashAIHubMix | $0.113 | $0.027 |
| Qwen3.8 Omni FlashAIHubMix | $0.113 | $0.027 |
| Qwen PlusAlibaba (China) | $0.115 | $0.027 |
| Seed 1.6Volcengine Ark | $0.119 | $0.028 |
| Seed 1.6 VisionVolcengine Ark | $0.119 | $0.028 |
| Seed 1.8Volcengine Ark | $0.119 | $0.028 |
| Seed CharacterVolcengine Ark | $0.119 | $0.028 |
| Qwen3 Coder NextKilo Gateway | $0.120 | $0.028 |
| Gemini 3.1 Flash LiteKilo Gateway | $0.125 | $0.030 |
| Gemini 3.1 Flash Lite PreviewKilo Gateway | $0.125 | $0.030 |
| Kolibri 1Munito AI | $0.130 | $0.031 |
| Viv FastVivgrid | $0.130 | $0.031 |
| Qwen3-VL PlusAIHubMix | $0.137 | $0.032 |
| DeepSeek V4 Flash 0423Venice AI | $0.138 | $0.033 |
| DeepSeek V4 Flash Vision ExpOpenCode | $0.140 | $0.033 |
| GPT-5.2 CodexQiHang | $0.140 | $0.033 |
| Llama 4 Maverick 17B InstructAbacus | $0.140 | $0.033 |
| MiMo-V2.5ClinePass | $0.140 | $0.033 |
| Gemini 2.5 Flash Preview 05-20Jiekou.AI | $0.142 | $0.034 |
| Qwen3 Coder FlashAlibaba (China) | $0.144 | $0.034 |
| Qwen3-Next 80B-A3B InstructAlibaba (China) | $0.144 | $0.034 |
| Kimi K3NanoGPT | $0.149 | $0.035 |
| DeepSeek ChatEden AI | $0.150 | $0.035 |
| Gemini 3.5 Flash LiteKilo Gateway | $0.150 | $0.035 |
| Ministral 3 8BMistral | $0.150 | $0.035 |
| Ministral 3 8B 2512Eden AI | $0.150 | $0.035 |
| Mistral Small (latest)Eden AI | $0.150 | $0.035 |
| Mistral Small 4Eden AI | $0.150 | $0.035 |
| Qwen3 VL 30B A3B InstructNEAR AI Cloud | $0.150 | $0.035 |
| Qwen3-Next 80B-A3B (Thinking)NanoGPT | $0.150 | $0.035 |
| Qwen3.5 397B-A17BAIHubMix | $0.164 | $0.039 |
| Qwen3.6 FlashAlibaba (China) | $0.165 | $0.039 |
| Hy3 previewAIHubMix | $0.170 | $0.040 |
| Llama 4 Scout 17B InstructDevPass (LLM Gateway) | $0.180 | $0.043 |
| GPT-5.4 nanoPoe | $0.182 | $0.043 |
| Gemini 3.5 FlashUnoRouter | $0.186 | $0.044 |
| GPT-5.5UnoRouter | $0.188 | $0.044 |
| GPT-5.6 LunaKenari | $0.200 | $0.047 |
| Grok 4.1 FastOfox | $0.200 | $0.047 |
| Grok 4.1 Fast (Reasoning)FrogBot | $0.200 | $0.047 |
| Jamba MiniAI21 Labs | $0.200 | $0.047 |
| MAI-Code-1.1-FlashGitHub Copilot | $0.200 | $0.047 |
| MiniMax Text 01 (MiniMax)LLM Gateway | $0.200 | $0.047 |
| MiniMax-M3Vultr | $0.200 | $0.047 |
| Ministral 14BDevPass (LLM Gateway) | $0.200 | $0.047 |
| Ministral 3 14BDigitalOcean | $0.200 | $0.047 |
| Ministral 3 14B 2512Eden AI | $0.200 | $0.047 |
| Nemotron 3.5 Super 120B A12BPerplexity Agent | $0.200 | $0.047 |
| Qwen3 235B-A22B Thinking 2507submodel | $0.200 | $0.047 |
| Qwen3-Coder 480B-A35B Instructsubmodel | $0.200 | $0.047 |
| Step 3.7 FlashDeep Infra | $0.200 | $0.047 |
| X-Ai/Grok-4-Fast-Non-ReasoningEden AI | $0.200 | $0.047 |
| GPT-5.1 Codex miniPoe | $0.220 | $0.052 |
| Qwen3.7 Plus302.AI | $0.228 | $0.054 |
| DeepSeek ReasonerOrcaRouter | $0.242 | $0.057 |
| Macaron V1 TallNovita AI | $0.247 | $0.058 |
| Beam 1.0 501B A23BNebius Token Factory | $0.250 | $0.059 |
| Gemini Flash-Lite LatestMerge Gateway | $0.250 | $0.059 |
| GPT-5.2QiHang | $0.250 | $0.059 |
| Trinity Large ThinkingArcee | $0.250 | $0.059 |
| Kimi K2.6routing.run | $0.275 | $0.065 |
| Kimi K2.7 Coderouting.run | $0.275 | $0.065 |
| Qwen3.6 PlusAlibaba (China) | $0.276 | $0.065 |
| DeepSeek V4 Pro 0813NanoGPT | $0.284 | $0.067 |
| Codestral (latest)Eden AI | $0.300 | $0.071 |
| Command AOpenRouter | $0.300 | $0.071 |
| Command AOpenRouter | $0.300 | $0.071 |
| Inkling SmallThinking Machines | $0.300 | $0.071 |
| LongCat-2.0OpenRouter | $0.300 | $0.071 |
| LongCat-2.5-PreviewLongCat | $0.300 | $0.071 |
| Nova 2 LiteOpenRouter | $0.300 | $0.071 |
| Nova 2 LiteOpenRouter | $0.300 | $0.071 |
| Qwen3.5 9B BaseThinking Machines | $0.300 | $0.071 |
| MiMo-V2.5-ProVercel AI Gateway | $0.304 | $0.072 |
| Qwen3.8 Max PreviewAIHubMix | $0.338 | $0.080 |
| Gemini 3.6 FlashKenari | $0.343 | $0.081 |
| Gemini 3.7 FlashKenari | $0.343 | $0.081 |
| DeepSeek V4 Prorouting.run | $0.348 | $0.082 |
| Seed 2.1 TurboOfox | $0.354 | $0.084 |
| Qwen3 MaxOfox | $0.360 | $0.085 |
| GPT-4.1 miniPoe | $0.364 | $0.086 |
| GPT-5.4 miniXpersona | $0.375 | $0.089 |
| Kimi K2.5NanoGPT | $0.375 | $0.089 |
| Devstral 2Eden AI | $0.400 | $0.094 |
| Devstral 2 (latest)Eden AI | $0.400 | $0.094 |
| MiMo-V2.6-ProVultr | $0.400 | $0.094 |
| Mistral Medium (latest)Merge Gateway | $0.400 | $0.094 |
| Seed 2.0 CodeEmpirioLabs AI | $0.400 | $0.094 |
| UnslopNemo 12BOpenRouter | $0.400 | $0.094 |
| Claude Opus 4.8UnoRouter | $0.425 | $0.100 |
| Seed 2.0 ProVolcengine Ark | $0.475 | $0.112 |
| Kimi K2 ThinkingHelicone | $0.480 | $0.113 |
| Gemini Flash LatestOrcaRouter | $0.500 | $0.118 |
| Mistral Large (latest)Merge Gateway | $0.500 | $0.118 |
| Mistral Large 3Amazon Bedrock | $0.500 | $0.118 |
| Motif 3ai& | $0.500 | $0.118 |
| Nex-N2-ProSiliconFlow | $0.500 | $0.118 |
| Qwen3.6 27BSTACKIT | $0.530 | $0.125 |
| Qwen3.5 35B-A3B BaseThinking Machines | $0.540 | $0.128 |
| MiniMax M1 80KHugging Face | $0.550 | $0.130 |
| Gemini 3 Pro PreviewQiHang | $0.570 | $0.135 |
| Qwen3 Coder PlusMerge Gateway | $0.574 | $0.136 |
| Kimi K2 Instruct 0905Kilo Gateway | $0.600 | $0.142 |
| Palmyra X5Amazon Bedrock | $0.600 | $0.142 |
| Gemini 2.5 ProKilo Gateway | $0.625 | $0.148 |
| Gemini 2.5 Pro Preview 06-05Kilo Gateway | $0.625 | $0.148 |
| Hy4 previewVancine | $0.670 | $0.158 |
| Mistral Large 4Ollama Cloud | $0.680 | $0.161 |
| Seed 2.1 ProOfox | $0.707 | $0.167 |
| Gemini 3.8 Flash302.AI | $0.750 | $0.177 |
| GPT-5.4Xpersona | $0.750 | $0.177 |
| Morph V3 FastMorph | $0.800 | $0.189 |
| Nova ProAmazon Bedrock | $0.800 | $0.189 |
| Nova Pro 1.0OpenRouter | $0.800 | $0.189 |
| Macaron V1 VentiNovita AI | $0.825 | $0.195 |
| Qwen3.7 MaxMerge Gateway | $0.825 | $0.195 |
| Relace Apply 3OpenRouter | $0.850 | $0.201 |
| Qwen3 Max PreviewQiniu | $0.870 | $0.205 |
| Seed EvolvingOfox | $0.884 | $0.209 |
| Claude Sonnet 4.6Xpersona | $0.900 | $0.213 |
| Morph V3 LargeMorph | $0.900 | $0.213 |
| InklingDeep Infra | $0.950 | $0.224 |
| Sakana NamazuKilo Gateway | $0.950 | $0.224 |
| Gemini 3.1 Pro PreviewKilo Gateway | $1.00 | $0.236 |
| GPT-6.1 TerraAI/ML API | $1.00 | $0.236 |
| Grok Build 0.1AIHubMix | $1.00 | $0.236 |
| Kimi K2.8 PreviewDevPass (LLM Gateway) | $1.00 | $0.236 |
| MiMo-V2-ProAbacus | $1.00 | $0.236 |
| Relace SearchOpenRouter | $1.00 | $0.236 |
| Step 5 PreviewDeep Infra | $1.00 | $0.236 |
| Qwen3.6 Max PreviewNanoGPT | $1.04 | $0.246 |
| Vision SmallVispark | $1.05 | $0.248 |
| GPT-5OpenCode | $1.07 | $0.253 |
| GPT-5-CodexOpenCode | $1.07 | $0.253 |
| GPT-5.1OpenCode | $1.07 | $0.253 |
| GPT-5.1 CodexOpenCode | $1.07 | $0.253 |
| GPT-5.1 Codex MaxPoe | $1.10 | $0.260 |
| GPT-5 Chat (latest)Jiekou.AI | $1.13 | $0.266 |
| Grok 4.20 (Non-Reasoning)AI/ML API | $1.25 | $0.295 |
| Grok 4.20 (Reasoning)Vertex | $1.25 | $0.295 |
| Grok 4.3302.AI | $1.25 | $0.295 |
| Muse Spark 1.1Cloudflare AI Gateway | $1.25 | $0.295 |
| Muse Spark 1.2Abacus | $1.25 | $0.295 |
| Muse Spark 1.3Cloudflare AI Gateway | $1.25 | $0.295 |
| Muse Spark Openai& | $1.25 | $0.295 |
| MiMo-V2.5-Pro-UltraSpeedXiaomi | $1.30 | $0.308 |
| Claude Sonnet 5Kenari | $1.43 | $0.337 |
| GPT-5.6 TerraXpersona | $1.50 | $0.354 |
| Grok 4.7Prime Inference | $1.60 | $0.378 |
| Qwen3.8 MaxVancine | $1.60 | $0.378 |
| DeepSeek V4 Pro 0423Merge Gateway | $1.65 | $0.390 |
| Qwen3.8 Max 0902Ofox | $1.71 | $0.404 |
| Mistral Medium 3.5evroc | $1.73 | $0.407 |
| Mistral Medium 3.5evroc | $1.73 | $0.407 |
| GPT-4.1Poe | $1.82 | $0.429 |
| Kimi K2.7 Code HighspeedAIHubMix | $1.90 | $0.449 |
| Qwen3.8 2.4T A95BIteraCompute | $1.95 | $0.461 |
| Claude Sonnet 5.5302.AI | $2.00 | $0.472 |
| Deep Research Max PreviewEden AI | $2.00 | $0.472 |
| Fugu MaxEmpirioLabs AI | $2.00 | $0.472 |
| Gemini 3.1 Pro Preview Custom ToolsAIHubMix | $2.00 | $0.472 |
| Gemini 4 ArgonAIHubMix | $2.00 | $0.472 |
| Gemini Deep Research PreviewEden AI | $2.00 | $0.472 |
| GPT-5.3 CodexCommandCode | $2.00 | $0.472 |
| GPT-5.6 SolNanoGPT | $2.00 | $0.472 |
| GPT-6 Sol302.AI | $2.00 | $0.472 |
| GPT-6.1 Sol302.AI | $2.00 | $0.472 |
| Grok 4.5302.AI | $2.00 | $0.472 |
| Grok 4.6Vertex | $2.00 | $0.472 |
| Jamba LargeAI21 Labs | $2.00 | $0.472 |
| Kimi K3.1 ProEden AI | $2.00 | $0.472 |
| LightOnOCR-3 0.8BScaleway | $2.46 | $0.582 |
| Command A ReasoningCohere | $2.50 | $0.591 |
| GPT-5 Image MiniKilo Gateway | $2.50 | $0.591 |
| ParetoCloudflare AI Gateway | $2.50 | $0.591 |
| Claude Fable 5Xpersona | $3.00 | $0.709 |
| Ember-1Fireworks AI | $3.00 | $0.709 |
| Claude Opus 5.5302.AI | $4.00 | $0.945 |
| Muse WonderCloudflare AI Gateway | $4.00 | $0.945 |
| Qwen 3.8 Max PrimeKilo Gateway | $4.00 | $0.945 |
| Vision MediumVispark | $4.21 | $0.994 |
| Claude Opus 4.6Poe | $4.29 | $1.01 |
| Claude Opus 4.7Poe | $4.29 | $1.01 |
| MiMo-V2.6-Pro-UltraSpeedEmpirioLabs AI | $4.35 | $1.03 |
| Claude Opus 5302.AI | $5.00 | $1.18 |
| Fugu UltraRequesty | $5.00 | $1.18 |
| Fugu Ultra v2Kilo Gateway | $5.00 | $1.18 |
| Arrow 2 TelosVercel AI Gateway | $6.00 | $1.42 |
| Vision LargeVispark | $7.37 | $1.74 |
| GPT-5.4 Image 2Kilo Gateway | $8.00 | $1.89 |
| Claude Fable 5.1302.AI | $10.00 | $2.36 |
| Claude Mythos 5Azure | $10.00 | $2.36 |
| GPT-5 ImageKilo Gateway | $10.00 | $2.36 |
| GPT-6 Astra302.AI | $10.00 | $2.36 |
| GPT-5 ProPoe | $13.64 | $3.22 |
| GPT-5.2 ProPoe | $19.09 | $4.51 |
| GPT-6 Astra (Fast)Vercel AI Gateway | $20.00 | $4.72 |
| GPT-5.4 ProPoe | $27.27 | $6.44 |
| GPT-5.5 ProPoe | $27.27 | $6.44 |
Input only: what the model charges to read the context once. Output is billed separately and depends on what you ask for. Each row carries the cheapest listed provider for that model, which is often a gateway rather than the lab that trained it.
Why the window is not the target
Two things move when you send more context.
The first is the bill, and it is exactly linear. Input is priced per million tokens, so doubling the context doubles the cost every time. A model having room to spare is not a discount.
The second is harder to price. Retrieval accuracy does not stay flat across a full window. Liu et al. found that performance "is often highest when relevant information occurs at the beginning or end of the input context, and significantly degrades" in the middle, "even for explicitly long-context models". Chroma's sweep of 18 models across 8 input lengths reported that "across all experiments, model performance consistently degrades with increasing input length". Neither result says long context is useless. Both say the last half million tokens are not free even when you can afford them.
What a repository weighs
Across 60 public repositories tokenized on 2026-09-11, the median assembles into 236,218 tokens. Only 38% fit a 128,000 token window, 43% fit 200,000 and 72% fit 1,000,000. The spread runs from 34,860 to 3,044,662 between the 10th and 90th percentiles.
So for most projects the question is not whether a model can hold the codebase. It is whether sending all of it is the cheapest way to get the answer.
Filtering does less of that work than people expect. On a fresh clone the
defaults remove a median of 22.7% of tokens. More than half of that is test
files left out by name, and a clone has no node_modules to remove in the first
place. What moves the number past that is deciding that a whole directory does
not belong in this bundle.
Cross-link
How many tokens is a codebase has the measurement behind the 236,218 figure and the distribution around it. Token estimation covers the tokenizer that produces the count on the result screen, and Token costs covers the output settings that change how much of a window a bundle consumes. File filtering is where you decide what goes in. ChatGPT Projects source limit is the other kind of ceiling, a file count per Project, which is why a folder goes in as one bundle.
References
- Lost in the Middle: How Language Models Use Long Contexts, Liu et al., TACL vol. 12, 2024, DOI 10.1162/tacl_a_00638
- Context Rot: How Increasing Input Tokens Impacts LLM Performance, Chroma Research, 2025
- models.dev, the catalogue this page prices against