Long Context Models

LLMs with the Longest Context Windows: 100K+ Tokens

Compare LLMs with the largest context windows. These models accept 100,000+ tokens of input, making them ideal for analyzing long documents, entire codebases, extended conversations, and large-scale data processing. Essential for AI agents that need to maintain long conversation histories.

272 models·42 providers·$0.0100 to $150.00/1M input

Top Picks

Related Categories

Cost per 1M Tokens / Flagship Models

Input
Output

All Long Context Models

272 models
ProviderModelInput $/1MOutput $/1MContextQuality
InclusionaiLing 2.6 Flash$0.0100$0.0300262.1KN/A
Ibm-graniteGranite 4.0 H Micro$0.0170$0.1120131K
36.3Good
MetaLlama 3.1 8b Instruct$0.0200$0.0300131.1KN/A
MistralMistral Nemo$0.0200$0.0300131.1KN/A
MetaLlama 3.2 1b Instruct$0.0270$0.2010131.1KN/A
OpenAIGPT Oss 20b$0.0290$0.1400131.1KN/A
LiquidLfm 2 24b A2b$0.0300$0.1200128KN/A
AmazonNova Micro V1$0.0350$0.1400128KN/A
CohereCommand R7b 12 2024$0.0375$0.1500128KN/A
OpenAIGPT Oss 120b$0.0390$0.1800131.1K
47.7Good
QwenQwen 2.5 7b Instruct$0.0400$0.1000131.1KN/A
Arcee-aiTrinity Mini$0.0450$0.1500131.1KN/A
QwenQwen3 30b A3b Instruct 2507$0.0482$0.1931131.1K
38.2Good
Ibm-graniteGranite 4.1 8b$0.0500$0.1000131.1KN/A
NVIDIANemotron 3 Nano 30b A3b$0.0500$0.2000262.1KN/A
OpenAIGPT 5 Nano$0.0500$0.4000400K
49.9Good
QwenQwen3 8b$0.0500$0.4000131.1KN/A
GoogleGemma 3 4b It$0.0500$0.1000131.1KN/A
GoogleGemma 3 12b It$0.0500$0.1500131.1KN/A
MetaLlama 3.2 3b Instruct$0.0509$0.3350131.1KN/A
GoogleGemma 4 26b A4b It$0.0600$0.3300262.1KN/A
xAIGlm 4.7 Flash$0.0600$0.4000202.8KN/A
AmazonNova Lite V1$0.0600$0.2400300KN/A
TencentHy3 Preview$0.0630$0.2100262.1KN/A
QwenQwen3.5 Flash 02 23$0.0650$0.26001MN/A
QwenQwen3 Coder 30b A3b Instruct$0.0700$0.2700160KN/A
InclusionaiRing 2.6 1t$0.0750$0.6250262.1KN/A
InclusionaiLing 2.6 1t$0.0750$0.6250262.1KN/A
Bytedance-seedSeed 1.6 Flash$0.0750$0.3000262.1KN/A
OpenAIGPT Oss Safeguard 20b$0.0750$0.3000131.1KN/A
MistralMistral Small 3.2 24b Instruct$0.0750$0.2000128KN/A
MicrosoftPhi 4 Mini Instruct$0.0800$0.3500131.1KN/A
QwenQwen3 Vl 8b Instruct$0.0800$0.5000256KN/A
QwenQwen3 30b A3b Thinking 2507$0.0800$0.4000131.1K
38.2Good
QwenQwen3 32b$0.0800$0.2800131.1K
42.2Good
GoogleGemma 3 27b It$0.0800$0.1600131.1KN/A
DeepSeekDeepseek V4 Flash$0.0900$0.18001.0M
68.9Frontier
NVIDIANemotron 3 Super 120b A12b$0.0900$0.45001MN/A
StepfunStep 3.5 Flash$0.0900$0.3000262.1KN/A
QwenQwen3 Next 80b A3b Instruct$0.0900$1.10262.1K
50.7Strong
QwenQwen3 235b A22b 2507$0.0900$0.1000262.1K
52.2Strong
QwenQwen3 Next 80b A3b Thinking$0.0975$0.7800262.1K
50.7Strong
PoolsideLaguna Xs.2$0.1000$0.2000262.1KN/A
QwenQwen3.5 9b$0.1000$0.1500262.1KN/A
Bytedance-seedSeed 2.0 Mini$0.1000$0.4000262.1KN/A
MistralMinistral 3b 2512$0.1000$0.1000131.1KN/A
GoogleGemini 2.5 Flash Lite Preview 09 2025$0.1000$0.40001.0M
40.8Good
QwenQwen3 235b A22b Thinking 2507$0.1000$0.1000262.1K
52.2Strong
BytedanceUi Tars 1.5 7b$0.1000$0.2000128KN/A
GoogleGemini 2.5 Flash Lite$0.1000$0.40001.0M
40.9Good

Page 1 of 6

Deploy your AI agent for $33/mo flat.

Managed Telegram bot hosting. We handle the infrastructure.

Any model. Any channel. Zero infrastructure.