Skip to content

LLMs with the largest context windows

1,932 models publish a context window across the gateways tracked here, and 797 of them accept a million tokens or more. The largest is Pokee-Isaac 28B at 10M.

Models by context window
1M or more
797
200K – 1M
566
128K – 200K
280
32K – 128K
155
Under 32K
134
ModelVendorTypeAvailable onContextInput / Mtok
Pokee-Isaac 28B pokee-isaac Pokee Text NanoGPT 10M $0.150
Qwen Long 10M qwen/qwen-long Qwen Text NanoGPT 10M $0.100
Gemini 2.0 Pro 0205 gemini-2.0-pro-exp-02-05 Google Multimodal NanoGPT 2.1M $1.99
Gemini 2.0 Pro 1206 gemini-exp-1206 Google Multimodal NanoGPT 2.1M $1.26
Auto Router auto — Image CloudflareLLM GatewayOpenRouter 2M Free
Auto Router (Beta) auto-beta — Image OpenRouter 2M —
Grok 4 grok-4 xAI Multimodal Cheaper InferenceExperiential LabsLLM Gateway 2M $1.70–$3.00
Grok 4.20 Beta Non-Reasoning (0309) grok-4-20-beta-0309-non-reasoning xAI Multimodal LLM Gateway 2M $2.00
Grok 4.20 Beta Reasoning (0309) grok-4-20-beta-0309-reasoning xAI Multimodal LLM Gateway 2M $2.00
Grok 4.20 Non-Reasoning grok-4-20-non-reasoning xAI Multimodal LLM Gateway 2M $1.25
Grok 4.20 Reasoning grok-4-20-reasoning xAI Multimodal LLM Gateway 2M $1.25
grok-4.20-multi-agent grok-4.20-multi-agent xAI Multimodal Cheaper InferenceExperiential Labs 2M $0.813–$1.25
grok-4.20-multi-agent-batch grok-4.20-multi-agent-batch xAI Multimodal Cheaper Inference 2M $0.850
grok-4.20-multi-agent-beta grok-4.20-multi-agent-beta xAI Multimodal Cheaper Inference 2M $1.06
Grok 4.20 Non Reasoning grok-4.20-non-reasoning xAI Text Cheaper InferenceConcentrateExperiential Labs 2M $1.06–$1.25
grok-4.20-non-reasoning-batch grok-4.20-non-reasoning-batch xAI Multimodal Cheaper Inference 2M $0.850
grok-4.20-non-reasoning-beta grok-4.20-non-reasoning-beta xAI Multimodal Cheaper Inference 2M $0.813
grok-4.20-reasoning grok-4.20-reasoning xAI Multimodal Cheaper Inference 2M $1.06
grok-4.20-reasoning-batch grok-4.20-reasoning-batch xAI Multimodal Cheaper Inference 2M $0.850
grok-4.20-reasoning-beta grok-4.20-reasoning-beta xAI Multimodal Cheaper Inference 2M $1.06
Pareto Code Router pareto-code — Text OpenRouter 2M —
grok-4-fast x-ai/grok-4-fast xAI Text CloudflareRequesty 2M $0.200
grok-4-fast-non-reasoning x-ai/grok-4-fast-non-reasoning xAI Text CloudflareRequesty 2M $0.200
grok-4.1-fast-non-reasoning x-ai/grok-4.1-fast-non-reasoning xAI Multimodal CloudflareRequesty 2M $0.200
grok-4.1-fast-reasoning x-ai/grok-4.1-fast-reasoning xAI Multimodal CloudflareRequesty 2M $0.200
grok-4.2-beta x-ai/grok-4.2-beta xAI Multimodal Requesty 2M $2.00
Grok 4.20 x-ai/grok-4.20 xAI Multimodal CloudflareNanoGPTOpenRouter 2M $1.25
Grok 4.20 Multi-Agent x-ai/grok-4.20-multi-agent xAI Multimodal CloudflareNanoGPTOpenRouterVercel 2M $1.25
Grok 4.20 Multi-Agent (Batch) x-ai/grok-4.20-multi-agent-batch xAI Text Vercel 2M $1.00
Grok 4.20 Multi Agent Beta x-ai/grok-4.20-multi-agent-beta xAI Text CloudflareVercel 2M $1.25
Grok 4.20 Non-Reasoning x-ai/grok-4.20-non-reasoning xAI Text CloudflareVercel 2M $1.25
Grok 4.20 Non-Reasoning (Batch) x-ai/grok-4.20-non-reasoning-batch xAI Text Vercel 2M $1.00
Grok 4.20 Beta Non-Reasoning x-ai/grok-4.20-non-reasoning-beta xAI Text Vercel 2M $1.25
Grok 4.20 Reasoning x-ai/grok-4.20-reasoning xAI Text CloudflareVercel 2M $1.25
Grok 4.20 Reasoning (Batch) x-ai/grok-4.20-reasoning-batch xAI Text Vercel 2M $1.00
Grok 4.20 Beta Reasoning x-ai/grok-4.20-reasoning-beta xAI Text Vercel 2M $1.25
Llama 4 Scout llama-4-scout Meta Text Cheaper InferenceConcentrateExperiential Labs 1.3M $0.077–$0.200
Llama 4 Scout meta-llama/llama-4-scout Meta Multimodal CloudflareNanoGPTOpenRouterVercel 1.3M $0.085–$0.170
DeepSeek V4 Flash deepseek-v4-flash DeepSeek Text Cheaper InferenceExperiential LabsLLM GatewayRamp 1.1M $0.076–$0.190
DeepSeek V4 Pro deepseek-v4-pro DeepSeek Text Cheaper InferenceConcentrateExperiential LabsLLM Gateway 1.1M $0.429–$1.74
DeepSeek V4.1 Flash 1017 deepseek-v4.1-flash-1017 DeepSeek Multimodal Cheaper InferenceConcentrateExperiential LabsIsoquantLLM GatewayRampSayGM 1.1M $0.030–$0.375
GPT-5.4 gpt-5.4 OpenAI Multimodal Cheaper InferenceConcentrateExperiential LabsLLM GatewayRampSayGM 1.1M $1.54–$2.50
gpt-5.4-batch gpt-5.4-batch OpenAI Multimodal Cheaper Inference 1.1M $1.06
gpt-5.4-fast gpt-5.4-fast OpenAI Multimodal Cheaper Inference 1.1M $3.25
GPT-5.4 Pro gpt-5.4-pro OpenAI Multimodal Cheaper InferenceConcentrateExperiential LabsLLM GatewayRamp 1.1M $19.50–$30.00
GPT-5.5 gpt-5.5 OpenAI Multimodal Cheaper InferenceConcentrateExperiential LabsLLM GatewayRampSayGM 1.1M $3.09–$5.00
GPT-5.5 Pro gpt-5.5-pro OpenAI Multimodal Cheaper InferenceExperiential LabsLLM GatewayRampSayGM 1.1M $19.50–$30.00
GPT-5.6 Luna gpt-5.6-luna OpenAI Multimodal Cheaper InferenceConcentrateExperiential LabsLLM GatewayOrcaRouterRampSayGM 1.1M $0.107–$0.200
gpt-5.6-luna-batch gpt-5.6-luna-batch OpenAI Multimodal Cheaper Inference 1.1M $0.085
gpt-5.6-luna-fast gpt-5.6-luna-fast OpenAI Multimodal Cheaper Inference 1.1M $0.260

Showing the top 50 of 1,932. Search the full catalog to go further.

How this is measured. Ranked on the largest context window any tracked gateway publishes for the model — gateways sometimes differ on the same model, and the per-model page shows each one. Models whose gateways publish no context window are excluded rather than sorted as zero.