AI models and what they cost in toman

430 models from 51 providers, priced in toman and charged only for the tokens you actually send and receive. Free models are here too, with a daily cap per account. How billing works

430 of 430 models

per 1M tokens · toman

Input / 1M

Aion-2.0
aion-labs/aion-2.0131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 232,100
Output / 1M: 464,200
Input / 1M232,100Output / 1M464,200
Aion-3.0
aion-labs/aion-3.0131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 870,375
Output / 1M: 1,740,750
Input / 1M870,375Output / 1M1,740,750
Aion-3.0-Mini
aion-labs/aion-3.0-mini131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 203,088
Output / 1M: 406,175
Input / 1M203,088Output / 1M406,175
Aion-RP 1.0 (8B)
aion-labs/aion-rp-llama-3.1-8b32,768 ctx
Context: 32,768
Input / 1M: 232,100
Output / 1M: 464,200
Input / 1M232,100Output / 1M464,200
Nova 2 Lite
amazon/nova-2-lite-v11,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 87,038
Output / 1M: 725,313
Input / 1M87,038Output / 1M725,313
Nova Lite 1.0
amazon/nova-lite-v1300,000 ctxtoolsvision
Context: 300,000
Input / 1M: 17,408
Output / 1M: 69,630
Input / 1M17,408Output / 1M69,630
Nova Micro 1.0
amazon/nova-micro-v1128,000 ctxtools
Context: 128,000
Input / 1M: 10,154
Output / 1M: 40,618
Input / 1M10,154Output / 1M40,618
Nova Premier 1.0
amazon/nova-premier-v11,000,000 ctxtoolsvision
Context: 1,000,000
Input / 1M: 725,313
Output / 1M: 3,626,563
Input / 1M725,313Output / 1M3,626,563
Nova Pro 1.0
amazon/nova-pro-v1300,000 ctxtoolsvision
Context: 300,000
Input / 1M: 232,100
Output / 1M: 928,400
Input / 1M232,100Output / 1M928,400
Magnum v4 72B
anthracite-org/magnum-v4-72b32,768 ctxJSON
Context: 32,768
Input / 1M: 725,313
Output / 1M: 1,450,625
Input / 1M725,313Output / 1M1,450,625
Claude 3 Haiku
anthropic/claude-3-haiku200,000 ctxtoolsvision
Context: 200,000
Input / 1M: 72,531
Output / 1M: 362,656
Input / 1M72,531Output / 1M362,656
Claude Fable 5
anthropic/claude-fable-51,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 2,901,250
Output / 1M: 14,506,250
Input / 1M2,901,250Output / 1M14,506,250
Claude Fable 5.1
anthropic/claude-fable-5.11,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 2,901,250
Output / 1M: 14,506,250
Input / 1M2,901,250Output / 1M14,506,250
Claude Fable 5.1 (batch)
anthropic/claude-fable-5.1:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
Claude Fable 5 (batch)
anthropic/claude-fable-5:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
Claude Haiku 4.5
anthropic/claude-haiku-4.5200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 290,125
Output / 1M: 1,450,625
Input / 1M290,125Output / 1M1,450,625
Claude Haiku 4.5 (batch)
anthropic/claude-haiku-4.5:batch200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 145,063
Output / 1M: 725,313
Input / 1M145,063Output / 1M725,313
Claude Opus 4
anthropic/claude-opus-4200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 4,351,875
Output / 1M: 21,759,375
Input / 1M4,351,875Output / 1M21,759,375
Claude Opus 4.1
anthropic/claude-opus-4.1200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 4,351,875
Output / 1M: 21,759,375
Input / 1M4,351,875Output / 1M21,759,375
Claude Opus 4.1 (batch)
anthropic/claude-opus-4.1:batch200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 2,175,938
Output / 1M: 10,879,688
Input / 1M2,175,938Output / 1M10,879,688
Claude Opus 4.5
anthropic/claude-opus-4.5200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
Claude Opus 4.5 (batch)
anthropic/claude-opus-4.5:batch200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 725,313
Output / 1M: 3,626,563
Input / 1M725,313Output / 1M3,626,563
Claude Opus 4.6
anthropic/claude-opus-4.61,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
Claude Opus 4.6 (batch)
anthropic/claude-opus-4.6:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 725,313
Output / 1M: 3,626,563
Input / 1M725,313Output / 1M3,626,563
Claude Opus 4.7
anthropic/claude-opus-4.71,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
Claude Opus 4.7 (batch)
anthropic/claude-opus-4.7:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 725,313
Output / 1M: 3,626,563
Input / 1M725,313Output / 1M3,626,563
Claude Opus 4.8
anthropic/claude-opus-4.81,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
Claude Opus 4.8 (batch)
anthropic/claude-opus-4.8:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 725,313
Output / 1M: 3,626,563
Input / 1M725,313Output / 1M3,626,563
Claude Opus 5
anthropic/claude-opus-51,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
Claude Opus 5 (batch)
anthropic/claude-opus-5:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 725,313
Output / 1M: 3,626,563
Input / 1M725,313Output / 1M3,626,563
Claude Sonnet 4
anthropic/claude-sonnet-41,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 870,375
Output / 1M: 4,351,875
Input / 1M870,375Output / 1M4,351,875
Claude Sonnet 4.5
anthropic/claude-sonnet-4.51,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 870,375
Output / 1M: 4,351,875
Input / 1M870,375Output / 1M4,351,875
Claude Sonnet 4.5 (batch)
anthropic/claude-sonnet-4.5:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 435,188
Output / 1M: 2,175,938
Input / 1M435,188Output / 1M2,175,938
Claude Sonnet 4.6
anthropic/claude-sonnet-4.61,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 870,375
Output / 1M: 4,351,875
Input / 1M870,375Output / 1M4,351,875
Claude Sonnet 4.6 (batch)
anthropic/claude-sonnet-4.6:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 435,188
Output / 1M: 2,175,938
Input / 1M435,188Output / 1M2,175,938
Claude Sonnet 5
anthropic/claude-sonnet-51,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 580,250
Output / 1M: 2,901,250
Input / 1M580,250Output / 1M2,901,250
Claude Sonnet 5 (batch)
anthropic/claude-sonnet-5:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 290,125
Output / 1M: 1,450,625
Input / 1M290,125Output / 1M1,450,625
Trinity Large Thinking
arcee-ai/trinity-large-thinking262,144 ctxreasoningtools
Context: 262,144
Input / 1M: 72,531
Output / 1M: 232,100
Input / 1M72,531Output / 1M232,100
ERNIE 4.5 VL 424B A47B
baidu/ernie-4.5-vl-424b-a47b123,000 ctxreasoningvision
Context: 123,000
Input / 1M: 121,853
Output / 1M: 362,656
Input / 1M121,853Output / 1M362,656
Seed 1.6
bytedance-seed/seed-1.6262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 72,531
Output / 1M: 580,250
Input / 1M72,531Output / 1M580,250
Seed 1.6 Flash
bytedance-seed/seed-1.6-flash262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 21,759
Output / 1M: 87,038
Input / 1M21,759Output / 1M87,038
Seed 2.1 Turbo
bytedance-seed/seed-2-1-turbo262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 145,063
Output / 1M: 725,313
Input / 1M145,063Output / 1M725,313
Seed-2.0-Code
bytedance-seed/seed-2.0-code262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 145,063
Output / 1M: 870,375
Input / 1M145,063Output / 1M870,375
Seed-2.0-Lite
bytedance-seed/seed-2.0-lite262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 72,531
Output / 1M: 580,250
Input / 1M72,531Output / 1M580,250
Seed-2.0-Mini
bytedance-seed/seed-2.0-mini262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 29,013
Output / 1M: 116,050
Input / 1M29,013Output / 1M116,050
UI-TARS 7B
bytedance/ui-tars-1.5-7b128,000 ctxvisionJSON
Context: 128,000
Input / 1M: 29,013
Output / 1M: 58,025
Input / 1M29,013Output / 1M58,025
Uncensored
cognitivecomputations/dolphin-mistral-24b-venice-edition128,000 ctxJSON
Context: 128,000
Input / 1M: 58,025
Output / 1M: 261,113
Input / 1M58,025Output / 1M261,113
Command A
cohere/command-a256,000 ctxJSON
Context: 256,000
Input / 1M: 725,313
Output / 1M: 2,901,250
Input / 1M725,313Output / 1M2,901,250
Command R (08-2024)
cohere/command-r-08-2024128,000 ctxtoolsJSON
Context: 128,000
Input / 1M: 43,519
Output / 1M: 174,075
Input / 1M43,519Output / 1M174,075
Command R+ (08-2024)
cohere/command-r-plus-08-2024128,000 ctxtoolsJSON
Context: 128,000
Input / 1M: 725,313
Output / 1M: 2,901,250
Input / 1M725,313Output / 1M2,901,250
Command R7B (12-2024)
cohere/command-r7b-12-2024128,000 ctxJSON
Context: 128,000
Input / 1M: 10,880
Output / 1M: 43,519
Input / 1M10,880Output / 1M43,519
North Mini Code (free)Free
cohere/north-mini-code:free256,000 ctxreasoningtools
Context: 256,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
DeepSeek V3
deepseek/deepseek-chat163,840 ctxtoolsJSON
Context: 163,840
Input / 1M: 92,840
Output / 1M: 258,211
Input / 1M92,840Output / 1M258,211
DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324163,840 ctxtoolsJSON
Context: 163,840
Input / 1M: 72,531
Output / 1M: 290,125
Input / 1M72,531Output / 1M290,125
DeepSeek V3.1
deepseek/deepseek-chat-v3.1163,840 ctxreasoningtoolsJSON
Context: 163,840
Input / 1M: 159,569
Output / 1M: 478,706
Input / 1M159,569Output / 1M478,706
R1
deepseek/deepseek-r164,000 ctxreasoningtoolsJSON
Context: 64,000
Input / 1M: 203,088
Output / 1M: 725,313
Input / 1M203,088Output / 1M725,313
R1 0528
deepseek/deepseek-r1-0528163,840 ctxreasoningtoolsJSON
Context: 163,840
Input / 1M: 145,063
Output / 1M: 623,769
Input / 1M145,063Output / 1M623,769
R1 Distill Llama 70B
deepseek/deepseek-r1-distill-llama-70b8,192 ctxreasoning
Context: 8,192
Input / 1M: 232,100
Output / 1M: 232,100
Input / 1M232,100Output / 1M232,100
DeepSeek V3.1 Terminus
deepseek/deepseek-v3.1-terminus163,840 ctxreasoningtoolsJSON
Context: 163,840
Input / 1M: 78,334
Output / 1M: 290,125
Input / 1M78,334Output / 1M290,125
DeepSeek V3.2
deepseek/deepseek-v3.2163,840 ctxreasoningtoolsJSON
Context: 163,840
Input / 1M: 78,044
Output / 1M: 116,050
Input / 1M78,044Output / 1M116,050
DeepSeek V3.2 Exp
deepseek/deepseek-v3.2-exp163,840 ctxreasoningtoolsJSON
Context: 163,840
Input / 1M: 78,334
Output / 1M: 118,951
Input / 1M78,334Output / 1M118,951
DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash1,048,576 ctxreasoningtoolsJSON
Context: 1,048,576
Input / 1M: 25,707
Output / 1M: 51,414
Input / 1M25,707Output / 1M51,414
DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-07311,310,720 ctxreasoningtoolsJSON
Context: 1,310,720
Input / 1M: 40,618
Output / 1M: 81,235
Input / 1M40,618Output / 1M81,235
DeepSeek V4 Flash 0731 (batch)
deepseek/deepseek-v4-flash-0731:batch1,048,576 ctxreasoningtoolsJSON
Context: 1,048,576
Input / 1M: 40,618
Output / 1M: 81,235
Input / 1M40,618Output / 1M81,235
DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-exp1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 63,828
Output / 1M: 191,483
Input / 1M63,828Output / 1M191,483
DeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro1,048,576 ctxreasoningtoolsJSON
Context: 1,048,576
Input / 1M: 277,145
Output / 1M: 554,290
Input / 1M277,145Output / 1M554,290
DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-08131,048,576 ctxreasoningtoolsJSON
Context: 1,048,576
Input / 1M: 304,457
Output / 1M: 913,372
Input / 1M304,457Output / 1M913,372
DeepSeek V4 Pro 0813 (batch)
deepseek/deepseek-v4-pro-0813:batch1,048,576 ctxreasoningtoolsJSON
Context: 1,048,576
Input / 1M: 382,965
Output / 1M: 1,148,895
Input / 1M382,965Output / 1M1,148,895
Dots3-Note Preview (free)Free
dots-studio/dots-3-note-preview:free512,000 ctxreasoningtoolsvision
Context: 512,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Gemini 2.5 Flash
google/gemini-2.5-flash1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 87,038
Output / 1M: 725,313
Input / 1M87,038Output / 1M725,313
Nano Banana (Gemini 2.5 Flash Image)
google/gemini-2.5-flash-image32,768 ctxreasoningvisionJSON
Context: 32,768
Input / 1M: 87,038
Output / 1M: 725,313
Input / 1M87,038Output / 1M725,313
Gemini 2.5 Flash Lite
google/gemini-2.5-flash-lite1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 29,013
Output / 1M: 116,050
Input / 1M29,013Output / 1M116,050
Gemini 2.5 Flash Lite (batch)
google/gemini-2.5-flash-lite:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 14,506
Output / 1M: 58,025
Input / 1M14,506Output / 1M58,025
Gemini 2.5 Flash (batch)
google/gemini-2.5-flash:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 43,519
Output / 1M: 362,656
Input / 1M43,519Output / 1M362,656
Gemini 2.5 Pro
google/gemini-2.5-pro1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 362,656
Output / 1M: 2,901,250
Input / 1M362,656Output / 1M2,901,250
Gemini 2.5 Pro Preview 06-05
google/gemini-2.5-pro-preview1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 362,656
Output / 1M: 2,901,250
Input / 1M362,656Output / 1M2,901,250
Gemini 2.5 Pro Preview 05-06
google/gemini-2.5-pro-preview-05-061,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 362,656
Output / 1M: 2,901,250
Input / 1M362,656Output / 1M2,901,250
Gemini 2.5 Pro (batch)
google/gemini-2.5-pro:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 181,328
Output / 1M: 1,450,625
Input / 1M181,328Output / 1M1,450,625
Gemini 3 Flash Preview
google/gemini-3-flash-preview1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 145,063
Output / 1M: 870,375
Input / 1M145,063Output / 1M870,375
Gemini 3 Flash Preview (batch)
google/gemini-3-flash-preview:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 72,531
Output / 1M: 435,188
Input / 1M72,531Output / 1M435,188
Nano Banana Pro (Gemini 3 Pro Image)
google/gemini-3-pro-image131,072 ctxreasoningtoolsvision
Context: 131,072
Input / 1M: 580,250
Output / 1M: 3,481,500
Input / 1M580,250Output / 1M3,481,500
Nano Banana Pro (Gemini 3 Pro Image Preview)
google/gemini-3-pro-image-preview65,536 ctxreasoningvisionJSON
Context: 65,536
Input / 1M: 580,250
Output / 1M: 3,481,500
Input / 1M580,250Output / 1M3,481,500
Nano Banana 2 (Gemini 3.1 Flash Image)
google/gemini-3.1-flash-image131,072 ctxreasoningvisionJSON
Context: 131,072
Input / 1M: 145,063
Output / 1M: 870,375
Input / 1M145,063Output / 1M870,375
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
google/gemini-3.1-flash-image-preview65,536 ctxreasoningvisionJSON
Context: 65,536
Input / 1M: 145,063
Output / 1M: 870,375
Input / 1M145,063Output / 1M870,375
Gemini 3.1 Flash Lite
google/gemini-3.1-flash-lite1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 72,531
Output / 1M: 435,188
Input / 1M72,531Output / 1M435,188
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
google/gemini-3.1-flash-lite-image65,536 ctxreasoningvisionJSON
Context: 65,536
Input / 1M: 72,531
Output / 1M: 435,188
Input / 1M72,531Output / 1M435,188
Gemini 3.1 Flash Lite Preview
google/gemini-3.1-flash-lite-preview1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 72,531
Output / 1M: 435,188
Input / 1M72,531Output / 1M435,188
Gemini 3.1 Flash Lite (batch)
google/gemini-3.1-flash-lite:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 36,266
Output / 1M: 217,594
Input / 1M36,266Output / 1M217,594
Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 580,250
Output / 1M: 3,481,500
Input / 1M580,250Output / 1M3,481,500
Gemini 3.1 Pro Preview Custom Tools
google/gemini-3.1-pro-preview-customtools1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 580,250
Output / 1M: 3,481,500
Input / 1M580,250Output / 1M3,481,500
Gemini 3.1 Pro Preview (batch)
google/gemini-3.1-pro-preview:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 290,125
Output / 1M: 1,740,750
Input / 1M290,125Output / 1M1,740,750
Gemini 3.5 Flash
google/gemini-3.5-flash1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 435,188
Output / 1M: 2,611,125
Input / 1M435,188Output / 1M2,611,125
Gemini 3.5 Flash Lite
google/gemini-3.5-flash-lite1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 87,038
Output / 1M: 725,313
Input / 1M87,038Output / 1M725,313
Gemini 3.5 Flash Lite (batch)
google/gemini-3.5-flash-lite:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 43,519
Output / 1M: 362,656
Input / 1M43,519Output / 1M362,656
Gemini 3.5 Flash (batch)
google/gemini-3.5-flash:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 217,594
Output / 1M: 1,305,563
Input / 1M217,594Output / 1M1,305,563
Gemini 3.6 Flash
google/gemini-3.6-flash1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 217,594
Output / 1M: 1,087,969
Input / 1M217,594Output / 1M1,087,969
Gemini 3.6 Flash (batch)
google/gemini-3.6-flash:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 108,797
Output / 1M: 543,984
Input / 1M108,797Output / 1M543,984
Gemini 3.7 Flash
google/gemini-3.7-flash1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 217,594
Output / 1M: 1,087,969
Input / 1M217,594Output / 1M1,087,969
Gemini 3.7 Flash (batch)
google/gemini-3.7-flash:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 108,797
Output / 1M: 543,984
Input / 1M108,797Output / 1M543,984
Gemini 3.8 Flash
google/gemini-3.8-flash1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 217,594
Output / 1M: 1,087,969
Input / 1M217,594Output / 1M1,087,969
Gemini 3.8 Flash (batch)
google/gemini-3.8-flash:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 108,797
Output / 1M: 543,984
Input / 1M108,797Output / 1M543,984
Gemma 2 27B
google/gemma-2-27b-it8,192 ctxJSON
Context: 8,192
Input / 1M: 188,581
Output / 1M: 188,581
Input / 1M188,581Output / 1M188,581
Gemma 3 12B
google/gemma-3-12b-it131,072 ctxtoolsvisionJSON
Context: 131,072
Input / 1M: 14,506
Output / 1M: 43,519
Input / 1M14,506Output / 1M43,519
Gemma 3 27B
google/gemma-3-27b-it131,072 ctxtoolsvisionJSON
Context: 131,072
Input / 1M: 23,210
Output / 1M: 130,556
Input / 1M23,210Output / 1M130,556
Gemma 3 4B
google/gemma-3-4b-it131,072 ctxvisionJSON
Context: 131,072
Input / 1M: 14,506
Output / 1M: 29,013
Input / 1M14,506Output / 1M29,013
Gemma 4 26B A4B
google/gemma-4-26b-a4b-it262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 20,309
Output / 1M: 98,643
Input / 1M20,309Output / 1M98,643
Gemma 4 26B A4B (free)Free
google/gemma-4-26b-a4b-it:free262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Gemma 4 31B
google/gemma-4-31b-it262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 26,111
Output / 1M: 98,643
Input / 1M26,111Output / 1M98,643
Gemma 4 31B (batch)
google/gemma-4-31b-it:batch262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 113,149
Output / 1M: 281,421
Input / 1M113,149Output / 1M281,421
Gemma 4 31B (free)Free
google/gemma-4-31b-it:free262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Lyria 3 Clip Preview
google/lyria-3-clip-preview1,048,576 ctxvisionJSON
Context: 1,048,576
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Lyria 3 Pro Preview
google/lyria-3-pro-preview1,048,576 ctxvisionJSON
Context: 1,048,576
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
MythoMax 13B
gryphe/mythomax-l2-13b8,192 ctxJSON
Context: 8,192
Input / 1M: 17,408
Output / 1M: 17,408
Input / 1M17,408Output / 1M17,408
Granite 4.0 Micro
ibm-granite/granite-4.0-h-micro131,000 ctxJSON
Context: 131,000
Input / 1M: 4,932
Output / 1M: 32,494
Input / 1M4,932Output / 1M32,494
Granite 4.2 8B
ibm-granite/granite-4.2-8b131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 29,013
Output / 1M: 43,519
Input / 1M29,013Output / 1M43,519
Mercury 2
inception/mercury-2128,000 ctxreasoningtoolsJSON
Context: 128,000
Input / 1M: 72,531
Output / 1M: 217,594
Input / 1M72,531Output / 1M217,594
Mercury 2.5 Preview
inception/mercury-2.5-preview260,000 ctxreasoningtoolsJSON
Context: 260,000
Input / 1M: 11,605
Output / 1M: 43,519
Input / 1M11,605Output / 1M43,519
Ling 3.0 Flash
inclusionai/ling-3.0-flash262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 6,093
Output / 1M: 18,278
Input / 1M6,093Output / 1M18,278
Ling 3.0 Flash Fin
inclusionai/ling-3.0-flash-fin262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 17,408
Output / 1M: 52,223
Input / 1M17,408Output / 1M52,223
Ling 3.0 Flash Fin (free)Free
inclusionai/ling-3.0-flash-fin:free262,144 ctxreasoningtools
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Ling 3.0 Flash Sante (free)Free
inclusionai/ling-3.0-flash-sante:free262,144 ctxreasoningtools
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
KAT-Coder-Pro V2
kwaipilot/kat-coder-pro-v2262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 87,038
Output / 1M: 348,150
Input / 1M87,038Output / 1M348,150
KAT-Coder-Pro V2.5
kwaipilot/kat-coder-pro-v2.5262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 214,693
Output / 1M: 858,770
Input / 1M214,693Output / 1M858,770
LFM2.5-2.6B (free)Free
liquid/lfm-2.5-2.6b:free65,536 ctxreasoningtoolsJSON
Context: 65,536
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Weaver (alpha)
mancer/weaver8,000 ctxJSON
Context: 8,000
Input / 1M: 116,050
Output / 1M: 217,594
Input / 1M116,050Output / 1M217,594
LongCat 2.0
meituan/longcat-2.01,048,756 ctxreasoningtools
Context: 1,048,756
Input / 1M: 87,038
Output / 1M: 348,150
Input / 1M87,038Output / 1M348,150
Llama 3.1 70B Instruct
meta-llama/llama-3.1-70b-instruct131,072 ctxtoolsJSON
Context: 131,072
Input / 1M: 116,050
Output / 1M: 116,050
Input / 1M116,050Output / 1M116,050
Llama 3.1 8B Instruct
meta-llama/llama-3.1-8b-instruct131,072 ctxtoolsJSON
Context: 131,072
Input / 1M: 14,506
Output / 1M: 23,210
Input / 1M14,506Output / 1M23,210
Llama 3.2 1B Instruct
meta-llama/llama-3.2-1b-instruct60,000 ctx
Context: 60,000
Input / 1M: 7,833
Output / 1M: 58,315
Input / 1M7,833Output / 1M58,315
Llama 3.2 3B Instruct
meta-llama/llama-3.2-3b-instruct131,072 ctxJSON
Context: 131,072
Input / 1M: 14,506
Output / 1M: 95,741
Input / 1M14,506Output / 1M95,741
Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instruct131,072 ctxtoolsJSON
Context: 131,072
Input / 1M: 29,013
Output / 1M: 92,840
Input / 1M29,013Output / 1M92,840
Llama 4 Maverick
meta-llama/llama-4-maverick1,048,576 ctxtoolsvisionJSON
Context: 1,048,576
Input / 1M: 58,025
Output / 1M: 201,927
Input / 1M58,025Output / 1M201,927
Llama 4 Scout
meta-llama/llama-4-scout1,310,720 ctxtoolsvisionJSON
Context: 1,310,720
Input / 1M: 29,013
Output / 1M: 87,038
Input / 1M29,013Output / 1M87,038
Llama Guard 4 12B
meta-llama/llama-guard-4-12b163,840 ctxvisionJSON
Context: 163,840
Input / 1M: 52,223
Output / 1M: 52,223
Input / 1M52,223Output / 1M52,223
Muse Glimmer 30B
meta/muse-glimmer-30b131,072 ctxreasoningtoolsvision
Context: 131,072
Input / 1M: 87,038
Output / 1M: 319,138
Input / 1M87,038Output / 1M319,138
Muse Glimmer 30B (batch)
meta/muse-glimmer-30b:batch131,072 ctxreasoningtoolsvision
Context: 131,072
Input / 1M: 101,544
Output / 1M: 435,188
Input / 1M101,544Output / 1M435,188
Muse Spark 1.1
meta/muse-spark-1.11,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 362,656
Output / 1M: 1,233,031
Input / 1M362,656Output / 1M1,233,031
Muse Spark 1.2
meta/muse-spark-1.21,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 362,656
Output / 1M: 1,233,031
Input / 1M362,656Output / 1M1,233,031
Muse Spark 1.2 Contributor
meta/muse-spark-1.2-contributor1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 29,013
Output / 1M: 58,025
Input / 1M29,013Output / 1M58,025
Muse Spark 1.3
meta/muse-spark-1.31,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 362,656
Output / 1M: 1,233,031
Input / 1M362,656Output / 1M1,233,031
Muse Spark 1.3 Contributor
meta/muse-spark-1.3-contributor1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 29,013
Output / 1M: 58,025
Input / 1M29,013Output / 1M58,025
Phi 4
microsoft/phi-416,384 ctxJSON
Context: 16,384
Input / 1M: 20,309
Output / 1M: 40,618
Input / 1M20,309Output / 1M40,618
WizardLM-2 8x22B
microsoft/wizardlm-2-8x22b65,535 ctxJSON
Context: 65,535
Input / 1M: 179,878
Output / 1M: 179,878
Input / 1M179,878Output / 1M179,878
MiniMax-01
minimax/minimax-011,000,192 ctxvision
Context: 1,000,192
Input / 1M: 58,025
Output / 1M: 319,138
Input / 1M58,025Output / 1M319,138
MiniMax M1
minimax/minimax-m11,000,000 ctxreasoningtools
Context: 1,000,000
Input / 1M: 159,569
Output / 1M: 638,275
Input / 1M159,569Output / 1M638,275
MiniMax M2
minimax/minimax-m2204,800 ctxreasoningtoolsJSON
Context: 204,800
Input / 1M: 73,982
Output / 1M: 295,928
Input / 1M73,982Output / 1M295,928
MiniMax M2-her
minimax/minimax-m2-her65,536 ctx
Context: 65,536
Input / 1M: 87,038
Output / 1M: 348,150
Input / 1M87,038Output / 1M348,150
MiniMax M2.1
minimax/minimax-m2.1204,800 ctxreasoningtoolsJSON
Context: 204,800
Input / 1M: 87,038
Output / 1M: 348,150
Input / 1M87,038Output / 1M348,150
MiniMax M2.5
minimax/minimax-m2.5204,800 ctxreasoningtoolsJSON
Context: 204,800
Input / 1M: 78,334
Output / 1M: 313,335
Input / 1M78,334Output / 1M313,335
MiniMax M2.7
minimax/minimax-m2.7204,800 ctxreasoningtoolsJSON
Context: 204,800
Input / 1M: 87,038
Output / 1M: 348,150
Input / 1M87,038Output / 1M348,150
MiniMax M2.7 (free)Free
minimax/minimax-m2.7:free196,608 ctxreasoningtoolsJSON
Context: 196,608
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
MiniMax M3
minimax/minimax-m31,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 87,038
Output / 1M: 348,150
Input / 1M87,038Output / 1M348,150
MiniMax M3 (batch)
minimax/minimax-m3:batch524,288 ctxreasoningtoolsvision
Context: 524,288
Input / 1M: 87,038
Output / 1M: 348,150
Input / 1M87,038Output / 1M348,150
MiniMax M3 (free)Free
minimax/minimax-m3:free1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Codestral 2508
mistralai/codestral-2508256,000 ctxtoolsJSON
Context: 256,000
Input / 1M: 87,038
Output / 1M: 261,113
Input / 1M87,038Output / 1M261,113
Devstral 2 2512
mistralai/devstral-2512262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 116,050
Output / 1M: 580,250
Input / 1M116,050Output / 1M580,250
Ministral 3 14B 2512
mistralai/ministral-14b-2512262,144 ctxtoolsvisionJSON
Context: 262,144
Input / 1M: 58,025
Output / 1M: 58,025
Input / 1M58,025Output / 1M58,025
Ministral 3 3B 2512
mistralai/ministral-3b-2512131,072 ctxtoolsvisionJSON
Context: 131,072
Input / 1M: 29,013
Output / 1M: 29,013
Input / 1M29,013Output / 1M29,013
Ministral 3 8B 2512
mistralai/ministral-8b-2512262,144 ctxtoolsvisionJSON
Context: 262,144
Input / 1M: 43,519
Output / 1M: 43,519
Input / 1M43,519Output / 1M43,519
Mistral Large
mistralai/mistral-large128,000 ctxtoolsJSON
Context: 128,000
Input / 1M: 580,250
Output / 1M: 1,740,750
Input / 1M580,250Output / 1M1,740,750
Mistral Large 2407
mistralai/mistral-large-2407131,072 ctxtoolsJSON
Context: 131,072
Input / 1M: 580,250
Output / 1M: 1,740,750
Input / 1M580,250Output / 1M1,740,750
Mistral Large 3 2512
mistralai/mistral-large-2512262,144 ctxtoolsvisionJSON
Context: 262,144
Input / 1M: 145,063
Output / 1M: 435,188
Input / 1M145,063Output / 1M435,188
Mistral Medium 3
mistralai/mistral-medium-3131,072 ctxtoolsvisionJSON
Context: 131,072
Input / 1M: 116,050
Output / 1M: 580,250
Input / 1M116,050Output / 1M580,250
Mistral Medium 3.5
mistralai/mistral-medium-3-5262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 435,188
Output / 1M: 2,175,938
Input / 1M435,188Output / 1M2,175,938
Mistral Medium 3.5 (batch)
mistralai/mistral-medium-3-5:batch262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 217,594
Output / 1M: 1,087,969
Input / 1M217,594Output / 1M1,087,969
Mistral Medium 3.1
mistralai/mistral-medium-3.1131,072 ctxtoolsvisionJSON
Context: 131,072
Input / 1M: 116,050
Output / 1M: 580,250
Input / 1M116,050Output / 1M580,250
Mistral Nemo
mistralai/mistral-nemo131,072 ctxtoolsJSON
Context: 131,072
Input / 1M: 5,512
Output / 1M: 8,704
Input / 1M5,512Output / 1M8,704
Saba
mistralai/mistral-saba32,768 ctxtoolsJSON
Context: 32,768
Input / 1M: 58,025
Output / 1M: 174,075
Input / 1M58,025Output / 1M174,075
Mistral Small 3
mistralai/mistral-small-24b-instruct-250132,768 ctxJSON
Context: 32,768
Input / 1M: 14,506
Output / 1M: 23,210
Input / 1M14,506Output / 1M23,210
Mistral Small 4
mistralai/mistral-small-2603262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 43,519
Output / 1M: 174,075
Input / 1M43,519Output / 1M174,075
Mistral Small 3.1 24B
mistralai/mistral-small-3.1-24b-instruct128,000 ctxvision
Context: 128,000
Input / 1M: 101,834
Output / 1M: 161,019
Input / 1M101,834Output / 1M161,019
Mistral Small 3.2 24B
mistralai/mistral-small-3.2-24b-instruct131,072 ctxtoolsvisionJSON
Context: 131,072
Input / 1M: 21,759
Output / 1M: 58,025
Input / 1M21,759Output / 1M58,025
Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct65,536 ctxtoolsJSON
Context: 65,536
Input / 1M: 580,250
Output / 1M: 1,740,750
Input / 1M580,250Output / 1M1,740,750
Voxtral Small 24B 2507
mistralai/voxtral-small-24b-250732,768 ctxtoolsJSONaudio
Context: 32,768
Input / 1M: 29,013
Output / 1M: 87,038
Input / 1M29,013Output / 1M87,038
Kimi K2 0711
moonshotai/kimi-k2131,072 ctxtools
Context: 131,072
Input / 1M: 165,371
Output / 1M: 667,288
Input / 1M165,371Output / 1M667,288
Kimi K2 0905
moonshotai/kimi-k2-0905262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 174,075
Output / 1M: 725,313
Input / 1M174,075Output / 1M725,313
Kimi K2 Thinking
moonshotai/kimi-k2-thinking262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 174,075
Output / 1M: 725,313
Input / 1M174,075Output / 1M725,313
Kimi K2.5
moonshotai/kimi-k2.5262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 130,556
Output / 1M: 652,781
Input / 1M130,556Output / 1M652,781
Kimi K2.6
moonshotai/kimi-k2.6262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 275,619
Output / 1M: 1,160,500
Input / 1M275,619Output / 1M1,160,500
Kimi K2.7 Code
moonshotai/kimi-k2.7-code262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 191,483
Output / 1M: 986,425
Input / 1M191,483Output / 1M986,425
Kimi K3
moonshotai/kimi-k31,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 870,375
Output / 1M: 4,351,875
Input / 1M870,375Output / 1M4,351,875
Kimi K3 (batch)
moonshotai/kimi-k3:batch1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 870,375
Output / 1M: 4,351,875
Input / 1M870,375Output / 1M4,351,875
Morph V3 Fast
morph/morph-v3-fast81,920 ctx
Context: 81,920
Input / 1M: 232,100
Output / 1M: 348,150
Input / 1M232,100Output / 1M348,150
Morph V3 Large
morph/morph-v3-large262,144 ctxJSON
Context: 262,144
Input / 1M: 261,113
Output / 1M: 551,238
Input / 1M261,113Output / 1M551,238
Nex-N2-Mini
nex-agi/nex-n2-mini262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 7,253
Output / 1M: 29,013
Input / 1M7,253Output / 1M29,013
Nex-N2-Pro
nex-agi/nex-n2-pro262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 72,531
Output / 1M: 290,125
Input / 1M72,531Output / 1M290,125
Hermes 3 405B Instruct
nousresearch/hermes-3-llama-3.1-405b131,072 ctxJSON
Context: 131,072
Input / 1M: 290,125
Output / 1M: 290,125
Input / 1M290,125Output / 1M290,125
Hermes 3 70B Instruct
nousresearch/hermes-3-llama-3.1-70b131,072 ctxJSON
Context: 131,072
Input / 1M: 203,088
Output / 1M: 203,088
Input / 1M203,088Output / 1M203,088
Hermes 4 405B
nousresearch/hermes-4-405b131,072 ctxreasoningJSON
Context: 131,072
Input / 1M: 290,125
Output / 1M: 870,375
Input / 1M290,125Output / 1M870,375
Hermes 4 70B
nousresearch/hermes-4-70b131,072 ctxreasoningJSON
Context: 131,072
Input / 1M: 37,716
Output / 1M: 116,050
Input / 1M37,716Output / 1M116,050
Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 14,506
Output / 1M: 58,025
Input / 1M14,506Output / 1M58,025
Nemotron 3 Nano Omni (free)Free
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free256,000 ctxreasoningtoolsvision
Context: 256,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b1,000,000 ctxreasoningtoolsJSON
Context: 1,000,000
Input / 1M: 24,661
Output / 1M: 116,050
Input / 1M24,661Output / 1M116,050
Nemotron 3 Super (free)Free
nvidia/nemotron-3-super-120b-a12b:free262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 181,328
Output / 1M: 906,641
Input / 1M181,328Output / 1M906,641
Nemotron 3 Ultra (free)Free
nvidia/nemotron-3-ultra-550b-a55b:free1,000,000 ctxreasoningtools
Context: 1,000,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Nemotron 3.5 Content Safety
nvidia/nemotron-3.5-content-safety131,072 ctxreasoningvisionJSON
Context: 131,072
Input / 1M: 58,025
Output / 1M: 58,025
Input / 1M58,025Output / 1M58,025
Nemotron 3.5 Content Safety (free)Free
nvidia/nemotron-3.5-content-safety:free128,000 ctxreasoningvision
Context: 128,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightning262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 23,210
Output / 1M: 58,025
Input / 1M23,210Output / 1M58,025
Nemotron 3.5 Lightning (free)Free
nvidia/nemotron-3.5-lightning:free1,000,000 ctxreasoningtools
Context: 1,000,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
GPT-3.5 Turbo
openai/gpt-3.5-turbo16,385 ctxtoolsJSON
Context: 16,385
Input / 1M: 145,063
Output / 1M: 435,188
Input / 1M145,063Output / 1M435,188
GPT-3.5 Turbo (older v0613)
openai/gpt-3.5-turbo-06134,095 ctxtoolsJSON
Context: 4,095
Input / 1M: 290,125
Output / 1M: 580,250
Input / 1M290,125Output / 1M580,250
GPT-3.5 Turbo 16k
openai/gpt-3.5-turbo-16k16,385 ctxtoolsJSON
Context: 16,385
Input / 1M: 870,375
Output / 1M: 1,160,500
Input / 1M870,375Output / 1M1,160,500
GPT-3.5 Turbo Instruct
openai/gpt-3.5-turbo-instruct4,095 ctxJSON
Context: 4,095
Input / 1M: 435,188
Output / 1M: 580,250
Input / 1M435,188Output / 1M580,250
GPT-3.5 Turbo (batch)
openai/gpt-3.5-turbo:batch16,385 ctxtoolsJSON
Context: 16,385
Input / 1M: 72,531
Output / 1M: 217,594
Input / 1M72,531Output / 1M217,594
GPT-4
openai/gpt-48,191 ctxtoolsJSON
Context: 8,191
Input / 1M: 8,703,750
Output / 1M: 17,407,500
Input / 1M8,703,750Output / 1M17,407,500
GPT-4 Turbo
openai/gpt-4-turbo128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 2,901,250
Output / 1M: 8,703,750
Input / 1M2,901,250Output / 1M8,703,750
GPT-4 Turbo Preview
openai/gpt-4-turbo-preview128,000 ctxtoolsJSON
Context: 128,000
Input / 1M: 2,901,250
Output / 1M: 8,703,750
Input / 1M2,901,250Output / 1M8,703,750
GPT-4 Turbo (batch)
openai/gpt-4-turbo:batch128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 1,450,625
Output / 1M: 4,351,875
Input / 1M1,450,625Output / 1M4,351,875
GPT-4.1
openai/gpt-4.11,047,576 ctxtoolsvisionJSON
Context: 1,047,576
Input / 1M: 580,250
Output / 1M: 2,321,000
Input / 1M580,250Output / 1M2,321,000
GPT-4.1 Mini
openai/gpt-4.1-mini1,047,576 ctxtoolsvisionJSON
Context: 1,047,576
Input / 1M: 116,050
Output / 1M: 464,200
Input / 1M116,050Output / 1M464,200
GPT-4.1 Mini (batch)
openai/gpt-4.1-mini:batch1,047,576 ctxtoolsvisionJSON
Context: 1,047,576
Input / 1M: 58,025
Output / 1M: 232,100
Input / 1M58,025Output / 1M232,100
GPT-4.1 Nano
openai/gpt-4.1-nano1,047,576 ctxtoolsvisionJSON
Context: 1,047,576
Input / 1M: 29,013
Output / 1M: 116,050
Input / 1M29,013Output / 1M116,050
GPT-4.1 Nano (batch)
openai/gpt-4.1-nano:batch1,047,576 ctxtoolsvisionJSON
Context: 1,047,576
Input / 1M: 14,506
Output / 1M: 58,025
Input / 1M14,506Output / 1M58,025
GPT-4.1 (batch)
openai/gpt-4.1:batch1,047,576 ctxtoolsvisionJSON
Context: 1,047,576
Input / 1M: 290,125
Output / 1M: 1,160,500
Input / 1M290,125Output / 1M1,160,500
GPT-4o
openai/gpt-4o128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 725,313
Output / 1M: 2,901,250
Input / 1M725,313Output / 1M2,901,250
GPT-4o (2024-05-13)
openai/gpt-4o-2024-05-13128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 1,450,625
Output / 1M: 4,351,875
Input / 1M1,450,625Output / 1M4,351,875
GPT-4o (2024-08-06)
openai/gpt-4o-2024-08-06128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 725,313
Output / 1M: 2,901,250
Input / 1M725,313Output / 1M2,901,250
GPT-4o (2024-11-20)
openai/gpt-4o-2024-11-20128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 725,313
Output / 1M: 2,901,250
Input / 1M725,313Output / 1M2,901,250
GPT-4o-mini
openai/gpt-4o-mini128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 43,519
Output / 1M: 174,075
Input / 1M43,519Output / 1M174,075
GPT-4o-mini (2024-07-18)
openai/gpt-4o-mini-2024-07-18128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 43,519
Output / 1M: 174,075
Input / 1M43,519Output / 1M174,075
GPT-4o-mini (batch)
openai/gpt-4o-mini:batch128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 21,759
Output / 1M: 87,038
Input / 1M21,759Output / 1M87,038
GPT-4o (batch)
openai/gpt-4o:batch128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 362,656
Output / 1M: 1,450,625
Input / 1M362,656Output / 1M1,450,625
GPT-5
openai/gpt-5400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 362,656
Output / 1M: 2,901,250
Input / 1M362,656Output / 1M2,901,250
GPT-5 Image
openai/gpt-5-image400,000 ctxreasoningvisionJSON
Context: 400,000
Input / 1M: 2,901,250
Output / 1M: 2,901,250
Input / 1M2,901,250Output / 1M2,901,250
GPT-5 Image Mini
openai/gpt-5-image-mini400,000 ctxreasoningvisionJSON
Context: 400,000
Input / 1M: 725,313
Output / 1M: 580,250
Input / 1M725,313Output / 1M580,250
GPT-5 Mini
openai/gpt-5-mini400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 72,531
Output / 1M: 580,250
Input / 1M72,531Output / 1M580,250
GPT-5 Mini (batch)
openai/gpt-5-mini:batch400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 36,266
Output / 1M: 290,125
Input / 1M36,266Output / 1M290,125
GPT-5 Nano
openai/gpt-5-nano400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 14,506
Output / 1M: 116,050
Input / 1M14,506Output / 1M116,050
GPT-5 Nano (batch)
openai/gpt-5-nano:batch400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 7,253
Output / 1M: 58,025
Input / 1M7,253Output / 1M58,025
GPT-5 Pro
openai/gpt-5-pro400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 4,351,875
Output / 1M: 34,815,000
Input / 1M4,351,875Output / 1M34,815,000
GPT-5 Pro (batch)
openai/gpt-5-pro:batch400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 2,175,938
Output / 1M: 17,407,500
Input / 1M2,175,938Output / 1M17,407,500
GPT-5.1
openai/gpt-5.1400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 362,656
Output / 1M: 2,901,250
Input / 1M362,656Output / 1M2,901,250
GPT-5.1-Codex
openai/gpt-5.1-codex400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 362,656
Output / 1M: 2,901,250
Input / 1M362,656Output / 1M2,901,250
GPT-5.1-Codex-Max
openai/gpt-5.1-codex-max400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 362,656
Output / 1M: 2,901,250
Input / 1M362,656Output / 1M2,901,250
GPT-5.1-Codex-Mini
openai/gpt-5.1-codex-mini400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 72,531
Output / 1M: 580,250
Input / 1M72,531Output / 1M580,250
GPT-5.1 (batch)
openai/gpt-5.1:batch400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 181,328
Output / 1M: 1,450,625
Input / 1M181,328Output / 1M1,450,625
GPT-5.2
openai/gpt-5.2400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 507,719
Output / 1M: 4,061,750
Input / 1M507,719Output / 1M4,061,750
GPT-5.2 Chat
openai/gpt-5.2-chat128,000 ctxtoolsvisionJSON
Context: 128,000
Input / 1M: 507,719
Output / 1M: 4,061,750
Input / 1M507,719Output / 1M4,061,750
GPT-5.2-Codex
openai/gpt-5.2-codex400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 507,719
Output / 1M: 4,061,750
Input / 1M507,719Output / 1M4,061,750
GPT-5.2 Pro
openai/gpt-5.2-pro400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 6,092,625
Output / 1M: 48,741,000
Input / 1M6,092,625Output / 1M48,741,000
GPT-5.2 Pro (batch)
openai/gpt-5.2-pro:batch400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 3,046,313
Output / 1M: 24,370,500
Input / 1M3,046,313Output / 1M24,370,500
GPT-5.2 (batch)
openai/gpt-5.2:batch400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 253,859
Output / 1M: 2,030,875
Input / 1M253,859Output / 1M2,030,875
GPT-5.3-Codex
openai/gpt-5.3-codex400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 507,719
Output / 1M: 4,061,750
Input / 1M507,719Output / 1M4,061,750
GPT-5.4
openai/gpt-5.41,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 725,313
Output / 1M: 4,351,875
Input / 1M725,313Output / 1M4,351,875
GPT-5.4 Image 2
openai/gpt-5.4-image-2272,000 ctxreasoningvisionJSON
Context: 272,000
Input / 1M: 2,321,000
Output / 1M: 4,351,875
Input / 1M2,321,000Output / 1M4,351,875
GPT-5.4 Mini
openai/gpt-5.4-mini400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 217,594
Output / 1M: 1,305,563
Input / 1M217,594Output / 1M1,305,563
GPT-5.4 Mini (batch)
openai/gpt-5.4-mini:batch400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 108,797
Output / 1M: 652,781
Input / 1M108,797Output / 1M652,781
GPT-5.4 Nano
openai/gpt-5.4-nano400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 58,025
Output / 1M: 362,656
Input / 1M58,025Output / 1M362,656
GPT-5.4 Nano (batch)
openai/gpt-5.4-nano:batch400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 29,013
Output / 1M: 181,328
Input / 1M29,013Output / 1M181,328
GPT-5.4 Pro
openai/gpt-5.4-pro1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 8,703,750
Output / 1M: 52,222,500
Input / 1M8,703,750Output / 1M52,222,500
GPT-5.4 Pro (batch)
openai/gpt-5.4-pro:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 4,351,875
Output / 1M: 26,111,250
Input / 1M4,351,875Output / 1M26,111,250
GPT-5.4 (batch)
openai/gpt-5.4:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 362,656
Output / 1M: 2,175,938
Input / 1M362,656Output / 1M2,175,938
GPT-5.5
openai/gpt-5.51,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 1,450,625
Output / 1M: 8,703,750
Input / 1M1,450,625Output / 1M8,703,750
GPT-5.5 Pro
openai/gpt-5.5-pro1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 8,703,750
Output / 1M: 52,222,500
Input / 1M8,703,750Output / 1M52,222,500
GPT-5.5 Pro (batch)
openai/gpt-5.5-pro:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 4,351,875
Output / 1M: 26,111,250
Input / 1M4,351,875Output / 1M26,111,250
GPT-5.5 (batch)
openai/gpt-5.5:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 725,313
Output / 1M: 4,351,875
Input / 1M725,313Output / 1M4,351,875
GPT-5.6 Luna
openai/gpt-5.6-luna1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 58,025
Output / 1M: 348,150
Input / 1M58,025Output / 1M348,150
GPT-5.6 Luna Pro
openai/gpt-5.6-luna-pro1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 58,025
Output / 1M: 348,150
Input / 1M58,025Output / 1M348,150
GPT-5.6 Luna Pro (batch)
openai/gpt-5.6-luna-pro:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 29,013
Output / 1M: 174,075
Input / 1M29,013Output / 1M174,075
GPT-5.6 Luna (batch)
openai/gpt-5.6-luna:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 29,013
Output / 1M: 174,075
Input / 1M29,013Output / 1M174,075
GPT-5.6 Sol
openai/gpt-5.6-sol1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 580,250
Output / 1M: 2,901,250
Input / 1M580,250Output / 1M2,901,250
GPT-5.6 Sol Pro
openai/gpt-5.6-sol-pro1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 580,250
Output / 1M: 2,901,250
Input / 1M580,250Output / 1M2,901,250
GPT-5.6 Sol Pro (batch)
openai/gpt-5.6-sol-pro:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 290,125
Output / 1M: 1,450,625
Input / 1M290,125Output / 1M1,450,625
GPT-5.6 Sol (batch)
openai/gpt-5.6-sol:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 290,125
Output / 1M: 1,450,625
Input / 1M290,125Output / 1M1,450,625
GPT-5.6 Terra
openai/gpt-5.6-terra1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 580,250
Output / 1M: 3,481,500
Input / 1M580,250Output / 1M3,481,500
GPT-5.6 Terra Pro
openai/gpt-5.6-terra-pro1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 580,250
Output / 1M: 3,481,500
Input / 1M580,250Output / 1M3,481,500
GPT-5.6 Terra Pro (batch)
openai/gpt-5.6-terra-pro:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 290,125
Output / 1M: 1,740,750
Input / 1M290,125Output / 1M1,740,750
GPT-5.6 Terra (batch)
openai/gpt-5.6-terra:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 290,125
Output / 1M: 1,740,750
Input / 1M290,125Output / 1M1,740,750
GPT-5 (batch)
openai/gpt-5:batch400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 181,328
Output / 1M: 1,450,625
Input / 1M181,328Output / 1M1,450,625
GPT-6 Astra
openai/gpt-6-astra1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 2,901,250
Output / 1M: 14,506,250
Input / 1M2,901,250Output / 1M14,506,250
GPT-6 Astra Pro
openai/gpt-6-astra-pro1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 2,901,250
Output / 1M: 14,506,250
Input / 1M2,901,250Output / 1M14,506,250
GPT-6 Astra Pro (batch)
openai/gpt-6-astra-pro:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
GPT-6 Astra (batch)
openai/gpt-6-astra:batch1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
GPT Audio
openai/gpt-audio128,000 ctxtoolsJSONaudio
Context: 128,000
Input / 1M: 725,313
Output / 1M: 2,901,250
Input / 1M725,313Output / 1M2,901,250
GPT Audio Mini
openai/gpt-audio-mini128,000 ctxtoolsJSONaudio
Context: 128,000
Input / 1M: 174,075
Output / 1M: 696,300
Input / 1M174,075Output / 1M696,300
GPT Chat Latest
openai/gpt-chat-latest400,000 ctxtoolsvisionJSON
Context: 400,000
Input / 1M: 1,450,625
Output / 1M: 8,703,750
Input / 1M1,450,625Output / 1M8,703,750
gpt-oss-120b
openai/gpt-oss-120b131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 10,735
Output / 1M: 49,321
Input / 1M10,735Output / 1M49,321
gpt-oss-120b (batch)
openai/gpt-oss-120b:batch131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 43,519
Output / 1M: 174,075
Input / 1M43,519Output / 1M174,075
gpt-oss-20b
openai/gpt-oss-20b131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 8,704
Output / 1M: 37,716
Input / 1M8,704Output / 1M37,716
gpt-oss-20b (batch)
openai/gpt-oss-20b:batch131,072 ctxreasoningJSON
Context: 131,072
Input / 1M: 14,506
Output / 1M: 58,025
Input / 1M14,506Output / 1M58,025
gpt-oss-safeguard-20b
openai/gpt-oss-safeguard-20b131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 21,759
Output / 1M: 87,038
Input / 1M21,759Output / 1M87,038
o1
openai/o1200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 4,351,875
Output / 1M: 17,407,500
Input / 1M4,351,875Output / 1M17,407,500
o1-pro
openai/o1-pro200,000 ctxreasoningvisionJSON
Context: 200,000
Input / 1M: 43,518,750
Output / 1M: 174,075,000
Input / 1M43,518,750Output / 1M174,075,000
o3
openai/o3200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 580,250
Output / 1M: 2,321,000
Input / 1M580,250Output / 1M2,321,000
o3 Mini
openai/o3-mini200,000 ctxreasoningtoolsJSON
Context: 200,000
Input / 1M: 319,138
Output / 1M: 1,276,550
Input / 1M319,138Output / 1M1,276,550
o3 Mini High
openai/o3-mini-high200,000 ctxreasoningtoolsJSON
Context: 200,000
Input / 1M: 319,138
Output / 1M: 1,276,550
Input / 1M319,138Output / 1M1,276,550
o3 Mini (batch)
openai/o3-mini:batch200,000 ctxreasoningtoolsJSON
Context: 200,000
Input / 1M: 159,569
Output / 1M: 638,275
Input / 1M159,569Output / 1M638,275
o3 Pro
openai/o3-pro200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 5,802,500
Output / 1M: 23,210,000
Input / 1M5,802,500Output / 1M23,210,000
o3 (batch)
openai/o3:batch200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 290,125
Output / 1M: 1,160,500
Input / 1M290,125Output / 1M1,160,500
o4 Mini
openai/o4-mini200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 319,138
Output / 1M: 1,276,550
Input / 1M319,138Output / 1M1,276,550
o4 Mini High
openai/o4-mini-high200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 319,138
Output / 1M: 1,276,550
Input / 1M319,138Output / 1M1,276,550
o4 Mini (batch)
openai/o4-mini:batch200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 159,569
Output / 1M: 638,275
Input / 1M159,569Output / 1M638,275
Auto Router
openrouter/auto2,000,000 ctxreasoningtoolsvision
Context: 2,000,000
Input / 1M: —
Output / 1M: —
Input / 1M—Output / 1M—
Auto Router (Beta)
openrouter/auto-beta2,000,000 ctxreasoningtoolsvision
Context: 2,000,000
Input / 1M: —
Output / 1M: —
Input / 1M—Output / 1M—
Body Builder (beta)
openrouter/bodybuilder128,000 ctx
Context: 128,000
Input / 1M: —
Output / 1M: —
Input / 1M—Output / 1M—
Free Models RouterFree
openrouter/free200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Fusion
openrouter/fusion1,000,000 ctx
Context: 1,000,000
Input / 1M: —
Output / 1M: —
Input / 1M—Output / 1M—
Pareto Code Router
openrouter/pareto-code2,000,000 ctx
Context: 2,000,000
Input / 1M: —
Output / 1M: —
Input / 1M—Output / 1M—
Perceptron Mk1
perceptron/perceptron-mk132,768 ctxreasoningvisionJSON
Context: 32,768
Input / 1M: 43,519
Output / 1M: 435,188
Input / 1M43,519Output / 1M435,188
Sonar
perplexity/sonar127,072 ctxvision
Context: 127,072
Input / 1M: 290,125
Output / 1M: 290,125
Input / 1M290,125Output / 1M290,125
Sonar Deep Research
perplexity/sonar-deep-research128,000 ctxreasoning
Context: 128,000
Input / 1M: 580,250
Output / 1M: 2,321,000
Input / 1M580,250Output / 1M2,321,000
Sonar Pro
perplexity/sonar-pro200,000 ctxvision
Context: 200,000
Input / 1M: 870,375
Output / 1M: 4,351,875
Input / 1M870,375Output / 1M4,351,875
Sonar Pro Search
perplexity/sonar-pro-search200,000 ctxreasoningvisionJSON
Context: 200,000
Input / 1M: 870,375
Output / 1M: 4,351,875
Input / 1M870,375Output / 1M4,351,875
Sonar Reasoning Pro
perplexity/sonar-reasoning-pro128,000 ctxreasoningvision
Context: 128,000
Input / 1M: 580,250
Output / 1M: 2,321,000
Input / 1M580,250Output / 1M2,321,000
Laguna S 2.1
poolside/laguna-s-2.11,048,576 ctxreasoningtools
Context: 1,048,576
Input / 1M: 26,111
Output / 1M: 52,223
Input / 1M26,111Output / 1M52,223
Laguna S 2.1 (free)Free
poolside/laguna-s-2.1:free262,144 ctxreasoningtools
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Laguna XS 2.1
poolside/laguna-xs-2.1262,144 ctxreasoningtools
Context: 262,144
Input / 1M: 17,408
Output / 1M: 34,815
Input / 1M17,408Output / 1M34,815
Laguna XS 2.1 (free)Free
poolside/laguna-xs-2.1:free262,144 ctxreasoningtools
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instruct32,768 ctxtoolsJSON
Context: 32,768
Input / 1M: 104,445
Output / 1M: 116,050
Input / 1M104,445Output / 1M116,050
Qwen2.5 7B Instruct
qwen/qwen-2.5-7b-instruct32,768 ctxtoolsJSON
Context: 32,768
Input / 1M: 29,013
Output / 1M: 58,025
Input / 1M29,013Output / 1M58,025
Qwen2.5 Coder 32B Instruct
qwen/qwen-2.5-coder-32b-instruct32,768 ctx
Context: 32,768
Input / 1M: 191,483
Output / 1M: 290,125
Input / 1M191,483Output / 1M290,125
Qwen-Plus
qwen/qwen-plus1,000,000 ctxtoolsJSON
Context: 1,000,000
Input / 1M: 75,433
Output / 1M: 226,298
Input / 1M75,433Output / 1M226,298
Qwen Plus 0728
qwen/qwen-plus-2025-07-281,000,000 ctxtoolsJSON
Context: 1,000,000
Input / 1M: 75,433
Output / 1M: 226,298
Input / 1M75,433Output / 1M226,298
Qwen2.5 VL 72B Instruct
qwen/qwen2.5-vl-72b-instruct128,000 ctxvisionJSON
Context: 128,000
Input / 1M: 232,100
Output / 1M: 290,125
Input / 1M232,100Output / 1M290,125
Qwen3 14B
qwen/qwen3-14b131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 34,815
Output / 1M: 69,630
Input / 1M34,815Output / 1M69,630
Qwen3 235B A22B
qwen/qwen3-235b-a22b131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 132,007
Output / 1M: 528,028
Input / 1M132,007Output / 1M528,028
Qwen3 235B A22B Instruct 2507
qwen/qwen3-235b-a22b-2507262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 26,111
Output / 1M: 159,569
Input / 1M26,111Output / 1M159,569
Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 66,729
Output / 1M: 667,288
Input / 1M66,729Output / 1M667,288
Qwen3 30B A3B
qwen/qwen3-30b-a3b131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 34,815
Output / 1M: 145,063
Input / 1M34,815Output / 1M145,063
Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 13,970
Output / 1M: 56,009
Input / 1M13,970Output / 1M56,009
Qwen3 30B A3B Thinking 2507
qwen/qwen3-30b-a3b-thinking-250781,920 ctxreasoningtoolsJSON
Context: 81,920
Input / 1M: 58,025
Output / 1M: 696,300
Input / 1M58,025Output / 1M696,300
Qwen3 32B
qwen/qwen3-32b131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 23,210
Output / 1M: 81,235
Input / 1M23,210Output / 1M81,235
Qwen3 8B
qwen/qwen3-8b131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 33,945
Output / 1M: 132,007
Input / 1M33,945Output / 1M132,007
Qwen3 Coder 480B A35B
qwen/qwen3-coder262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 87,038
Output / 1M: 290,125
Input / 1M87,038Output / 1M290,125
Qwen3 Coder 30B A3B Instruct
qwen/qwen3-coder-30b-a3b-instruct262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 20,309
Output / 1M: 81,235
Input / 1M20,309Output / 1M81,235
Qwen3 Coder Flash
qwen/qwen3-coder-flash1,000,000 ctxtoolsJSON
Context: 1,000,000
Input / 1M: 56,574
Output / 1M: 282,872
Input / 1M56,574Output / 1M282,872
Qwen3 Coder Next
qwen/qwen3-coder-next262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 34,815
Output / 1M: 232,100
Input / 1M34,815Output / 1M232,100
Qwen3 Coder Plus
qwen/qwen3-coder-plus1,000,000 ctxtoolsJSON
Context: 1,000,000
Input / 1M: 188,581
Output / 1M: 942,906
Input / 1M188,581Output / 1M942,906
Qwen3 Max
qwen/qwen3-max262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 226,298
Output / 1M: 1,131,488
Input / 1M226,298Output / 1M1,131,488
Qwen3 Max Thinking
qwen/qwen3-max-thinking262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 226,298
Output / 1M: 1,131,488
Input / 1M226,298Output / 1M1,131,488
Qwen3 Next 80B A3B Instruct
qwen/qwen3-next-80b-a3b-instruct262,144 ctxtoolsJSON
Context: 262,144
Input / 1M: 29,013
Output / 1M: 319,138
Input / 1M29,013Output / 1M319,138
Qwen3 Next 80B A3B Thinking
qwen/qwen3-next-80b-a3b-thinking262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 43,519
Output / 1M: 348,150
Input / 1M43,519Output / 1M348,150
Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instruct262,144 ctxtoolsvisionJSON
Context: 262,144
Input / 1M: 60,926
Output / 1M: 551,238
Input / 1M60,926Output / 1M551,238
Qwen3 VL 235B A22B Thinking
qwen/qwen3-vl-235b-a22b-thinking131,072 ctxreasoningtoolsvision
Context: 131,072
Input / 1M: 116,050
Output / 1M: 1,160,500
Input / 1M116,050Output / 1M1,160,500
Qwen3 VL 30B A3B Instruct
qwen/qwen3-vl-30b-a3b-instruct262,144 ctxtoolsvisionJSON
Context: 262,144
Input / 1M: 43,519
Output / 1M: 174,075
Input / 1M43,519Output / 1M174,075
Qwen3 VL 30B A3B Thinking
qwen/qwen3-vl-30b-a3b-thinking262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 58,025
Output / 1M: 696,300
Input / 1M58,025Output / 1M696,300
Qwen3 VL 32B Instruct
qwen/qwen3-vl-32b-instruct131,072 ctxtoolsvisionJSON
Context: 131,072
Input / 1M: 30,173
Output / 1M: 120,692
Input / 1M30,173Output / 1M120,692
Qwen3 VL 8B Instruct
qwen/qwen3-vl-8b-instruct262,144 ctxtoolsvisionJSON
Context: 262,144
Input / 1M: 33,945
Output / 1M: 132,007
Input / 1M33,945Output / 1M132,007
Qwen3 VL 8B Thinking
qwen/qwen3-vl-8b-thinking131,072 ctxreasoningtoolsvision
Context: 131,072
Input / 1M: 52,223
Output / 1M: 609,263
Input / 1M52,223Output / 1M609,263
Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10b262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 84,136
Output / 1M: 696,300
Input / 1M84,136Output / 1M696,300
Qwen3.5-27B
qwen/qwen3.5-27b262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 56,574
Output / 1M: 452,595
Input / 1M56,574Output / 1M452,595
Qwen3.5-35B-A3B
qwen/qwen3.5-35b-a3b262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 90,664
Output / 1M: 362,656
Input / 1M90,664Output / 1M362,656
Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 113,149
Output / 1M: 678,893
Input / 1M113,149Output / 1M678,893
Qwen3.5-9B
qwen/qwen3.5-9b262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 29,013
Output / 1M: 43,519
Input / 1M29,013Output / 1M43,519
Qwen3.5-9B (batch)
qwen/qwen3.5-9b:batch262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 49,321
Output / 1M: 72,531
Input / 1M49,321Output / 1M72,531
Qwen3.5-Flash
qwen/qwen3.5-flash-02-231,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 18,858
Output / 1M: 75,433
Input / 1M18,858Output / 1M75,433
Qwen3.5 Plus 2026-02-15
qwen/qwen3.5-plus-02-151,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 75,433
Output / 1M: 452,595
Input / 1M75,433Output / 1M452,595
Qwen3.5 Plus 2026-04-20
qwen/qwen3.5-plus-202604201,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 87,038
Output / 1M: 522,225
Input / 1M87,038Output / 1M522,225
Qwen3.6 27B
qwen/qwen3.6-27b262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 87,038
Output / 1M: 580,250
Input / 1M87,038Output / 1M580,250
Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 29,013
Output / 1M: 261,113
Input / 1M29,013Output / 1M261,113
Qwen3.6 Flash
qwen/qwen3.6-flash1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 54,398
Output / 1M: 326,391
Input / 1M54,398Output / 1M326,391
Qwen3.6 Max Preview
qwen/qwen3.6-max-preview262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 297,958
Output / 1M: 1,787,750
Input / 1M297,958Output / 1M1,787,750
Qwen3.6 Plus
qwen/qwen3.6-plus1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 94,291
Output / 1M: 565,744
Input / 1M94,291Output / 1M565,744
Qwen3.7 Flash
qwen/qwen3.7-flash1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 8,704
Output / 1M: 37,716
Input / 1M8,704Output / 1M37,716
Qwen3.7 Max
qwen/qwen3.7-max1,000,000 ctxreasoningtoolsJSON
Context: 1,000,000
Input / 1M: 427,934
Output / 1M: 1,283,803
Input / 1M427,934Output / 1M1,283,803
Qwen3.7 Plus
qwen/qwen3.7-plus1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 92,840
Output / 1M: 371,360
Input / 1M92,840Output / 1M371,360
Qwen3.8 2.4T A95B
qwen/qwen3.8-2.4t-a95b1,048,576 ctxreasoningtoolsJSON
Context: 1,048,576
Input / 1M: 580,250
Output / 1M: 1,740,750
Input / 1M580,250Output / 1M1,740,750
Qwen3.8 2.4T A95B (batch)
qwen/qwen3.8-2.4t-a95b:batch1,010,000 ctxreasoningtoolsJSON
Context: 1,010,000
Input / 1M: 580,250
Output / 1M: 1,740,750
Input / 1M580,250Output / 1M1,740,750
Qwen3.8 27B
qwen/qwen3.8-27b1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 121,853
Output / 1M: 870,375
Input / 1M121,853Output / 1M870,375
Qwen3.8 Flash
qwen/qwen3.8-flash1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 43,519
Output / 1M: 136,359
Input / 1M43,519Output / 1M136,359
Qwen3.8 Max (0902)
qwen/qwen3.8-max-09021,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 580,250
Output / 1M: 1,740,750
Input / 1M580,250Output / 1M1,740,750
Reka Edge
rekaai/reka-edge16,384 ctxtoolsvisionJSON
Context: 16,384
Input / 1M: 29,013
Output / 1M: 29,013
Input / 1M29,013Output / 1M29,013
Reka Flash 3
rekaai/reka-flash-365,536 ctxreasoningJSON
Context: 65,536
Input / 1M: 29,013
Output / 1M: 58,025
Input / 1M29,013Output / 1M58,025
Relace Apply 3
relace/relace-apply-3256,000 ctx
Context: 256,000
Input / 1M: 246,606
Output / 1M: 362,656
Input / 1M246,606Output / 1M362,656
Relace Search
relace/relace-search256,000 ctxtoolsJSON
Context: 256,000
Input / 1M: 290,125
Output / 1M: 870,375
Input / 1M290,125Output / 1M870,375
Fugu Ultra
sakana/fugu-ultra1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 1,450,625
Output / 1M: 8,703,750
Input / 1M1,450,625Output / 1M8,703,750
Sakana Namazu
sakana/sakana-namazu262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 275,619
Output / 1M: 1,160,500
Input / 1M275,619Output / 1M1,160,500
Llama 3 8B Lunaris
sao10k/l3-lunaris-8b8,192 ctxJSON
Context: 8,192
Input / 1M: 11,605
Output / 1M: 14,506
Input / 1M11,605Output / 1M14,506
Llama 3.1 Euryale 70B v2.2
sao10k/l3.1-euryale-70b131,072 ctxtoolsJSON
Context: 131,072
Input / 1M: 246,606
Output / 1M: 246,606
Input / 1M246,606Output / 1M246,606
Llama 3.3 Euryale 70B
sao10k/l3.3-euryale-70b131,072 ctxJSON
Context: 131,072
Input / 1M: 188,581
Output / 1M: 217,594
Input / 1M188,581Output / 1M217,594
Step 3.5 Flash
stepfun/step-3.5-flash262,144 ctxreasoningtools
Context: 262,144
Input / 1M: 29,013
Output / 1M: 87,038
Input / 1M29,013Output / 1M87,038
Step 3.7 Flash
stepfun/step-3.7-flash262,144 ctxreasoningtoolsvision
Context: 262,144
Input / 1M: 58,025
Output / 1M: 333,644
Input / 1M58,025Output / 1M333,644
Hunyuan A13B Instruct
tencent/hunyuan-a13b-instruct131,072 ctxreasoningJSON
Context: 131,072
Input / 1M: 40,618
Output / 1M: 165,371
Input / 1M40,618Output / 1M165,371
Hy-MT2-1.8B
tencent/hy-mt2-1.8b8,192 ctx
Context: 8,192
Input / 1M: 12,766
Output / 1M: 51,352
Input / 1M12,766Output / 1M51,352
Hy-MT2-30B-A3B
tencent/hy-mt2-30b-a3b8,192 ctxJSON
Context: 8,192
Input / 1M: 21,469
Output / 1M: 85,587
Input / 1M21,469Output / 1M85,587
Hy-MT2-7B
tencent/hy-mt2-7b8,192 ctxJSON
Context: 8,192
Input / 1M: 21,469
Output / 1M: 85,587
Input / 1M21,469Output / 1M85,587
Hy3
tencent/hy3262,144 ctxreasoningtoolsJSON
Context: 262,144
Input / 1M: 38,297
Output / 1M: 153,186
Input / 1M38,297Output / 1M153,186
Hy3 preview
tencent/hy3-preview262,144 ctxreasoningtools
Context: 262,144
Input / 1M: 52,223
Output / 1M: 174,075
Input / 1M52,223Output / 1M174,075
Hy4 preview
tencent/hy4-preview1,048,576 ctxreasoningtoolsJSON
Context: 1,048,576
Input / 1M: 241,964
Output / 1M: 725,603
Input / 1M241,964Output / 1M725,603
Cydonia 24B V4.1
thedrummer/cydonia-24b-v4.1131,072 ctxJSON
Context: 131,072
Input / 1M: 87,038
Output / 1M: 145,063
Input / 1M87,038Output / 1M145,063
Skyfall 36B V2
thedrummer/skyfall-36b-v232,768 ctxJSON
Context: 32,768
Input / 1M: 159,569
Output / 1M: 232,100
Input / 1M159,569Output / 1M232,100
UnslopNemo 12B
thedrummer/unslopnemo-12b1,024,000 ctxtoolsJSON
Context: 1,024,000
Input / 1M: 116,050
Output / 1M: 116,050
Input / 1M116,050Output / 1M116,050
Inkling
thinkingmachines/inkling1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 290,125
Output / 1M: 1,175,006
Input / 1M290,125Output / 1M1,175,006
Inkling Small
thinkingmachines/inkling-small1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 130,556
Output / 1M: 348,150
Input / 1M130,556Output / 1M348,150
Inkling Small (batch)
thinkingmachines/inkling-small:batch524,288 ctxreasoningtoolsvision
Context: 524,288
Input / 1M: 145,063
Output / 1M: 348,150
Input / 1M145,063Output / 1M348,150
Inkling Small (free)Free
thinkingmachines/inkling-small:free1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Inkling (batch)
thinkingmachines/inkling:batch524,288 ctxreasoningtoolsvision
Context: 524,288
Input / 1M: 290,125
Output / 1M: 1,175,006
Input / 1M290,125Output / 1M1,175,006
Inkling (free)Free
thinkingmachines/inkling:free1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
ReMM SLERP 13B
undi95/remm-slerp-l2-13b6,144 ctxJSON
Context: 6,144
Input / 1M: 101,544
Output / 1M: 188,581
Input / 1M101,544Output / 1M188,581
Solar Pro 3
upstage/solar-pro-3131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 43,519
Output / 1M: 174,075
Input / 1M43,519Output / 1M174,075
Solar Pro 4
upstage/solar-pro4524,288 ctxreasoningtoolsJSON
Context: 524,288
Input / 1M: 8,704
Output / 1M: 34,815
Input / 1M8,704Output / 1M34,815
Palmyra X5
writer/palmyra-x51,040,000 ctx
Context: 1,040,000
Input / 1M: 174,075
Output / 1M: 1,740,750
Input / 1M174,075Output / 1M1,740,750
Grok 4.20
x-ai/grok-4.202,000,000 ctxreasoningtoolsvision
Context: 2,000,000
Input / 1M: 362,656
Output / 1M: 725,313
Input / 1M362,656Output / 1M725,313
Grok 4.20 Multi-Agent
x-ai/grok-4.20-multi-agent2,000,000 ctxreasoningvisionJSON
Context: 2,000,000
Input / 1M: 362,656
Output / 1M: 725,313
Input / 1M362,656Output / 1M725,313
Grok 4.3
x-ai/grok-4.31,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 362,656
Output / 1M: 725,313
Input / 1M362,656Output / 1M725,313
Grok 4.3 (batch)
x-ai/grok-4.3:batch1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 290,125
Output / 1M: 580,250
Input / 1M290,125Output / 1M580,250
Grok 4.5
x-ai/grok-4.5500,000 ctxreasoningtoolsvision
Context: 500,000
Input / 1M: 580,250
Output / 1M: 1,740,750
Input / 1M580,250Output / 1M1,740,750
Grok 4.6
x-ai/grok-4.6500,000 ctxreasoningtoolsvision
Context: 500,000
Input / 1M: 580,250
Output / 1M: 1,740,750
Input / 1M580,250Output / 1M1,740,750
Grok Build 0.1
x-ai/grok-build-0.1256,000 ctxreasoningtoolsvision
Context: 256,000
Input / 1M: 290,125
Output / 1M: 580,250
Input / 1M290,125Output / 1M580,250
MiMo-V2.5
xiaomi/mimo-v2.51,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 40,618
Output / 1M: 81,235
Input / 1M40,618Output / 1M81,235
MiMo-V2.5-Pro
xiaomi/mimo-v2.5-pro1,050,000 ctxreasoningtoolsJSON
Context: 1,050,000
Input / 1M: 126,204
Output / 1M: 252,409
Input / 1M126,204Output / 1M252,409
GLM 4.5
z-ai/glm-4.5131,072 ctxreasoningtoolsJSON
Context: 131,072
Input / 1M: 174,075
Output / 1M: 638,275
Input / 1M174,075Output / 1M638,275
GLM 4.5 Air
z-ai/glm-4.5-air131,072 ctxreasoningtools
Context: 131,072
Input / 1M: 37,716
Output / 1M: 246,606
Input / 1M37,716Output / 1M246,606
GLM 4.5V
z-ai/glm-4.5v65,536 ctxreasoningtoolsvision
Context: 65,536
Input / 1M: 174,075
Output / 1M: 522,225
Input / 1M174,075Output / 1M522,225
GLM 4.6
z-ai/glm-4.6204,800 ctxreasoningtoolsJSON
Context: 204,800
Input / 1M: 124,754
Output / 1M: 507,719
Input / 1M124,754Output / 1M507,719
GLM 4.6V
z-ai/glm-4.6v131,072 ctxreasoningtoolsvision
Context: 131,072
Input / 1M: 87,038
Output / 1M: 261,113
Input / 1M87,038Output / 1M261,113
GLM 4.7
z-ai/glm-4.7204,800 ctxreasoningtoolsJSON
Context: 204,800
Input / 1M: 116,050
Output / 1M: 507,719
Input / 1M116,050Output / 1M507,719
GLM 4.7 Flash
z-ai/glm-4.7-flash202,752 ctxreasoningtoolsJSON
Context: 202,752
Input / 1M: 17,408
Output / 1M: 116,050
Input / 1M17,408Output / 1M116,050
GLM 5
z-ai/glm-5204,800 ctxreasoningtoolsJSON
Context: 204,800
Input / 1M: 174,075
Output / 1M: 557,040
Input / 1M174,075Output / 1M557,040
GLM 5 Turbo
z-ai/glm-5-turbo202,752 ctxreasoningtoolsJSON
Context: 202,752
Input / 1M: 348,150
Output / 1M: 1,160,500
Input / 1M348,150Output / 1M1,160,500
GLM 5.1
z-ai/glm-5.1204,800 ctxreasoningtoolsJSON
Context: 204,800
Input / 1M: 280,261
Output / 1M: 880,820
Input / 1M280,261Output / 1M880,820
GLM 5.2
z-ai/glm-5.21,048,576 ctxreasoningtoolsJSON
Context: 1,048,576
Input / 1M: 280,261
Output / 1M: 880,820
Input / 1M280,261Output / 1M880,820
GLM 5.3
z-ai/glm-5.31,310,720 ctxreasoningtoolsJSON
Context: 1,310,720
Input / 1M: 406,175
Output / 1M: 1,276,550
Input / 1M406,175Output / 1M1,276,550
GLM 5.3 Flash
z-ai/glm-5.3-flash1,310,720 ctxreasoningtoolsvision
Context: 1,310,720
Input / 1M: 21,759
Output / 1M: 72,531
Input / 1M21,759Output / 1M72,531
GLM 5.3 Flash (batch)
z-ai/glm-5.3-flash:batch1,048,575 ctxreasoningtoolsvision
Context: 1,048,575
Input / 1M: 43,519
Output / 1M: 145,063
Input / 1M43,519Output / 1M145,063
GLM 5V Turbo
z-ai/glm-5v-turbo202,752 ctxreasoningtoolsvision
Context: 202,752
Input / 1M: 348,150
Output / 1M: 1,160,500
Input / 1M348,150Output / 1M1,160,500
Claude Fable Latest
~anthropic/claude-fable-latest1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 2,901,250
Output / 1M: 14,506,250
Input / 1M2,901,250Output / 1M14,506,250
Anthropic Claude Haiku Latest
~anthropic/claude-haiku-latest200,000 ctxreasoningtoolsvision
Context: 200,000
Input / 1M: 290,125
Output / 1M: 1,450,625
Input / 1M290,125Output / 1M1,450,625
Claude Opus Latest
~anthropic/claude-opus-latest1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 1,450,625
Output / 1M: 7,253,125
Input / 1M1,450,625Output / 1M7,253,125
Anthropic Claude Sonnet Latest
~anthropic/claude-sonnet-latest1,000,000 ctxreasoningtoolsvision
Context: 1,000,000
Input / 1M: 580,250
Output / 1M: 2,901,250
Input / 1M580,250Output / 1M2,901,250
DeepSeek V4 Flash Latest
~deepseek/deepseek-v4-flash-latest1,310,720 ctxreasoningtoolsJSON
Context: 1,310,720
Input / 1M: 14,506
Output / 1M: 46,420
Input / 1M14,506Output / 1M46,420
Google Gemini Flash Latest
~google/gemini-flash-latest1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 217,594
Output / 1M: 1,087,969
Input / 1M217,594Output / 1M1,087,969
Google Gemini Pro Latest
~google/gemini-pro-latest1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 580,250
Output / 1M: 3,481,500
Input / 1M580,250Output / 1M3,481,500
MoonshotAI Kimi Latest
~moonshotai/kimi-latest1,048,576 ctxreasoningtoolsvision
Context: 1,048,576
Input / 1M: 739,819
Output / 1M: 3,699,094
Input / 1M739,819Output / 1M3,699,094
OpenAI GPT Latest
~openai/gpt-latest1,050,000 ctxreasoningtoolsvision
Context: 1,050,000
Input / 1M: 580,250
Output / 1M: 2,901,250
Input / 1M580,250Output / 1M2,901,250
OpenAI GPT Mini Latest
~openai/gpt-mini-latest400,000 ctxreasoningtoolsvision
Context: 400,000
Input / 1M: 217,594
Output / 1M: 1,305,563
Input / 1M217,594Output / 1M1,305,563
Grok Latest
~x-ai/grok-latest500,000 ctxreasoningtoolsvision
Context: 500,000
Input / 1M: 580,250
Output / 1M: 1,740,750
Input / 1M580,250Output / 1M1,740,750
GLM Flash Latest
~z-ai/glm-flash-latest1,310,720 ctxreasoningtoolsvision
Context: 1,310,720
Input / 1M: 20,671
Output / 1M: 68,905
Input / 1M20,671Output / 1M68,905
GLM Latest
~z-ai/glm-latest1,310,720 ctxreasoningtoolsJSON
Context: 1,310,720
Input / 1M: 324,940
Output / 1M: 1,021,240
Input / 1M324,940Output / 1M1,021,240