📏 AI Model Context Window Comparison

Compare context windows across 4,587 AI models. Find the largest context LLMs for your use case — from 1M+ token monsters to compact 8K models.

4,587Models
2,195128K+ Context
95Providers
🔍 Interactive Catalog ⭐ Star on GitHub

🏆 Top 20 Largest Context Windows

# Model Provider Context Input $/1M Tool Call
1 meta-llama-4-scout meta 10M $0.17 ✅
2 gemini-1.5-pro google 2M $1.25 ✅
3 xai--grok-4-fast-non-reasoning aimlapi 2M $0.52 ✅
4 xai--grok-4-fast-reasoning aimlapi 2M $0.52 ✅
5 meta-llama-4-maverick-17b amazon-bedrock 1M $0.24 ✅
6 meta-llama-4-scout-17b amazon-bedrock 1M $0.17 ✅
7 minimax-m2-1 amazon-bedrock 1M $0.3 ✅
8 minimax-m2-5 amazon-bedrock 1M $0.3 ✅
9 minimax-m2 amazon-bedrock 1M $0.3 ✅
10 deepseek-v4-flash baidu 1M $0.126 ✅
11 minimax-m2-5 baseten 1M $0.3 ✅
12 gpt-5-1 clarifai 1M $1.5625 ✅
13 deepseek-v4-flash deepinfra 1M $0.14
14 llama-4-maverick-17b-128e-instruct-fp8 deepinfra 1M $0.15
15 mimo-v2.5-pro deepinfra 1M $1
16 llama-4-maverick digitalocean 1M $0.25 ✅
17 deepseek-v4-pro fireworks 1M $1.74 ✅
18 meta-llama--Llama-4-Maverick-17B-128E-Instruct-FP8 gmicloud 1M $0.25 ✅
19 gemini-1.5-flash-8b google 1M $0.075 ✅
20 gemini-1.5-flash google 1M $0.075 ✅

📊 1M+ Tokens (93 models)

Model Provider Context Input $/1M Output $/1M Tool Call Reasoning
meta-llama-4-scout meta 10M $0.17 $0.66 ✅
gemini-1.5-pro google 2M $1.25 $5 ✅
xai--grok-4-fast-non-reasoning aimlapi 2M $0.52 $1.3 ✅
xai--grok-4-fast-reasoning aimlapi 2M $0.52 $1.3 ✅
meta-llama-4-maverick-17b amazon-bedrock 1M $0.24 $0.97 ✅
meta-llama-4-scout-17b amazon-bedrock 1M $0.17 $0.66 ✅
minimax-m2-1 amazon-bedrock 1M $0.3 $1.2 ✅
minimax-m2-5 amazon-bedrock 1M $0.3 $1.2 ✅
minimax-m2 amazon-bedrock 1M $0.3 $1.2 ✅
deepseek-v4-flash baidu 1M $0.126 $0.252 ✅ ✅
minimax-m2-5 baseten 1M $0.3 $1.2 ✅
gpt-5-1 clarifai 1M $1.5625 $12.5 ✅
deepseek-v4-flash deepinfra 1M $0.14 $0.28 ✅
llama-4-maverick-17b-128e-instruct-fp8 deepinfra 1M $0.15 $0.6
mimo-v2.5-pro deepinfra 1M $1 $3 ✅
... and 78 more models

📊 512K–1M Tokens (1 models)

Model Provider Context Input $/1M Output $/1M Tool Call Reasoning
deepseek-v4-pro baidu 716K $1.521 $3.042 ✅ ✅

📊 256K–512K Tokens (187 models)

Model Provider Context Input $/1M Output $/1M Tool Call Reasoning
openai--gpt-5-chat aimlapi 400K $1.625 $13
openai--gpt-5-mini aimlapi 400K $0.325 $2.6 ✅
openai--gpt-5-nano aimlapi 400K $0.065 $0.52 ✅
openai--gpt-5.1-chat-latest aimlapi 400K $1.625 $13 ✅
openai--gpt-5.1 aimlapi 400K $1.625 $13 ✅
openai--gpt-5.2 aimlapi 400K $2.275 $18.2 ✅
openai--gpt-5 aimlapi 400K $1.625 $13 ✅
llama-4-scout-17b-16e-instruct cloudflare 327K $0.27 $0.85 ✅
llama-4-scout-17b-16e-instruct deepinfra 327K $0.08 $0.3
meta-llama--Llama-4-Scout-17B-16E-Instruct gmicloud 327K $0.08 $0.5 ✅
llama-4-scout-17b-16e-instruct vultr 327K $0.55 $2.75 ✅
llama-4-scout-17b-16e vultr 327K $0.55 $2.75
amazon-nova-lite amazon 300K $0.06 $0.24 ✅
amazon-nova-pro amazon 300K $0.8 $3.2 ✅
amazon-nova-lite amazon-bedrock 300K $0.06 $0.24 ✅
... and 172 more models

📊 128K–256K Tokens (685 models)

Model Provider Context Input $/1M Output $/1M Tool Call Reasoning
hunyuan-lite tencent 250K Free
hunyuan-a13b tencent 224K $0.5 $2 ✅
minimax-m2.5 dinference 204K $0.22 $0.88
minimax--minimax-m2.5 hpc-ai 204K $0.3 $1.2 ✅ ✅
MiniMax-M2.1-highspeed minimax 204K $4.2 $16.8
MiniMax-M2.1 minimax 204K $2.1 $8.4
MiniMax-M2.5-highspeed minimax 204K $4.2 $16.8
MiniMax-M2.5 minimax 204K $2.1 $8.4
MiniMax-M2.7-highspeed minimax 204K $4.2 $16.8
MiniMax-M2.7 minimax 204K $2.1 $8.4
MiniMax-M2 minimax 204K $2.1 $8.4
minimax--minimax-m2.1 novitaai 204K $0.3 $1.2 ✅
minimax--minimax-m2.5-highspeed novitaai 204K $0.6 $2.4 ✅ ✅
minimax--minimax-m2.5 novitaai 204K $0.3 $1.2 ✅ ✅
minimax--minimax-m2.7 novitaai 204K $0.3 $1.2 ✅ ✅
... and 670 more models

📊 64K–128K Tokens (56 models)

Model Provider Context Input $/1M Output $/1M Tool Call Reasoning
sonar perplexity 127K $1 $1 ✅
baidu--ernie-4.5-300b-a47b-paddle novitaai 123K $0.28 $1.1
baidu--ernie-4.5-vl-424b-a47b novitaai 123K $0.42 $1.25 ✅
baidu--ernie-4.5-300b-a47b-paddle ppio 123K $2 $7
baidu--ernie-4.5-vl-424b-a47b ppio 123K $3 $9
baidu--ernie-4.5-0.3b aimlapi 120K Free ✅
baidu--ernie-4.5-21B-a3b novitaai 120K $0.07 $0.28 ✅
baidu--ernie-4.5-0.3b ppio 120K Free
baidu--ernie-4.5-21B-a3b ppio 120K $0.5 $2
qwen3.6-27b vultr 120K $0.55 $2.75
step-r1-v-mini stepfun 100K $2.5 $8
google--gemma-3-27b-it novitaai 98K $0.119 $0.2
Gemma-3-27b-it nebius 96K $0.1 $0.3 ✅ ✅
gemma-3-27b privatemode 96K $0.77 $1.27
gemma-4-31b privatemode 96K $0.77 $1.27
... and 41 more models

📊 32K–64K Tokens (74 models)

Model Provider Context Input $/1M Output $/1M Tool Call Reasoning
mistralai--mistral-nemo novitaai 60K $0.04 $0.17
Qwen--Qwen3-32B-TEE chutes 40K $0.08 $0.24 ✅ ✅
qwen3-30b-a3b-fp8 cloudflare 40K $0.051 $0.335 ✅ ✅
qwen3-14b deepinfra 40K $0.12 $0.24 ✅
qwen3-30b-a3b deepinfra 40K $0.09 $0.45 ✅
qwen3-32b deepinfra 40K $0.08 $0.28 ✅
Qwen--Qwen3-30B-A3B-Instruct evroc 40K $0.1 $0.8
Qwen--Qwen3-VL-30B-A3B-Instruct evroc 40K $0.2 $0.8
Qwen--Qwen3-30B-A3B gmicloud 40K $0.08 $0.25
Qwen--Qwen3-32B-FP8 gmicloud 40K $0.1 $0.6
Qwen--Qwen3-235B-A22B-FP8 klusterai 40K $0.13 $2 ✅ ✅
mistralai--Magistral-Small-2506 klusterai 40K $0.1 $0.3
qwen--qwen3-235b-a22b-fp8 novitaai 40K $0.2 $0.8 ✅
qwen--qwen3-30b-a3b-fp8 novitaai 40K $0.09 $0.45 ✅ ✅
qwen--qwen3-32b-fp8 novitaai 40K $0.1 $0.45 ✅
... and 59 more models

📊 8K–32K Tokens (79 models)

Model Provider Context Input $/1M Output $/1M Tool Call Reasoning
baidu--ernie-4.5-vl-28b-a3b novitaai 30K $0.14 $0.56 ✅ ✅
baidu--ernie-4.5-vl-28b-a3b ppio 30K $1 $4
gpt-oss-120b vultr 30K $0.55 $2.75
gpt-oss-20b vultr 30K $0.55 $2.75
hunyuan-large-role-latest tencent 28K $2.4 $9.6
hunyuan-t1-vision tencent 28K $3 $9 ✅
hunyuan-role tencent-tokenhub 28K $2.4 $9.6
hunyuan-turbos-vision-video tencent 24K $3 $9
hunyuan-turbos-vision tencent 24K $3 $9
hunyuan-vision-1.5-instruct tencent 24K $3 $9
autoglm-phone zhipuai 20K Free ✅
gpt-3.5-turbo-16k openai 16K $3 $4 ✅
gpt-3.5-turbo openai 16K $0.5 $1.5 ✅
yi-lightning 01ai 16K $1 $1 ✅
yi-medium 01ai 16K $2.5 $2.5 ✅
... and 64 more models

📊 Under 8K Tokens (13 models)

Model Provider Context Input $/1M Output $/1M Tool Call Reasoning
nvidia-nemotron-3-super-120b amazon-bedrock 4K $0.15 $0.65
nvidia-nemotron-nano-2-vl amazon-bedrock 4K $0.2 $0.6
nvidia-nemotron-nano-2 amazon-bedrock 4K $0.06 $0.23
nvidia-nemotron-nano-3-30b amazon-bedrock 4K $0.06 $0.24
llama-2-7b-chat-fp16 cloudflare 4K $0.556 $6.667
mythomax-l2-13b deepinfra 4K $0.4 $0.4
nvidia-nemotron-3-super-120b digitalocean 4K $0.3 $0.65
nemotron3-super inferencenet 4K $2.5 $5
gryphe--mythomax-l2-13b novitaai 4K $0.09 $0.09
nemotron-3-super-120b-a12b-bf16 vultr 4K $0.55 $2.75
hunyuan-translation-lite tencent 4K $1 $3
hunyuan-translation tencent 4K $1.2 $3.6
EleutherAI--gpt-j-6B textsynth 2K $0.2 $2

💰 Cheapest Models by Context Tier

Find the most affordable model in each context window tier.

Context Tier Cheapest Model Provider Context Input $/1M
1M+ Tokens gemini-1.5-flash-8b deepinfra 1M $0.0375
512K–1M Tokens deepseek-v4-pro baidu 716K $1.521
256K–512K Tokens qwen3.5-0.8b deepinfra 262K $0.01
128K–256K Tokens mistralai--Mistral-Nemo-Instruct-2407 klusterai 131K $0.008
64K–128K Tokens zai-org--autoglm-phone-9b-multilingual novitaai 65K $0.035
32K–64K Tokens meta-llama--llama-3.2-3b-instruct novitaai 32K $0.03
8K–32K Tokens Gemma-2-2b-it nebius 8K $0.02

📊 Methodology

All data is sourced from first-party APIs — not third-party aggregators. Context windows are as reported by each provider. Aggregator providers are excluded from ranking tables to avoid duplicate models.

🔗 More Resources

Small Language Models

🎯 AI Model Picker

⚡ GitHub Action