AI models and what they cost in toman

453 models from 65 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

453 models; the first 40 shown

per 1M tokens · toman

Input / 1M

GPT-5
openai/gpt-5400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 432,774
Output / 1M: 3,462,194
Input / 1M432,774Output / 1M3,462,194
Claude Sonnet 4.5
anthropic/claude-sonnet-4.51,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,038,658
Output / 1M: 5,193,290
Input / 1M1,038,658Output / 1M5,193,290
Gemini 2.5 Pro
google/gemini-2.5-pro1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 432,774
Output / 1M: 3,462,194
Input / 1M432,774Output / 1M3,462,194
DeepSeek V3
deepseek/deepseek-chat163,840 ctxTool callingJSON output
Context: 163,840
Input / 1M: 89,117
Output / 1M: 356,156
Input / 1M89,117Output / 1M356,156
Grok 4.20
x-ai/grok-4.202,000,000 ctxReasoningTool callingImage input
Context: 2,000,000
Input / 1M: 432,774
Output / 1M: 865,548
Input / 1M432,774Output / 1M865,548
Qwen3 Coder 480B A35B
qwen/qwen3-coder262,144 ctxTool callingJSON output
Context: 262,144
Input / 1M: 103,866
Output / 1M: 346,219
Input / 1M103,866Output / 1M346,219
GPT-5 Mini
openai/gpt-5-mini400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 86,555
Output / 1M: 692,439
Input / 1M86,555Output / 1M692,439
Gemini 2.5 Flash
google/gemini-2.5-flash1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 103,866
Output / 1M: 865,548
Input / 1M103,866Output / 1M865,548
Claude Opus 4.1
anthropic/claude-opus-4.1200,000 ctxReasoningTool callingImage input
Context: 200,000
Input / 1M: 5,193,290
Output / 1M: 25,966,451
Input / 1M5,193,290Output / 1M25,966,451
Mistral Large
mistralai/mistral-large128,000 ctxTool callingJSON output
Context: 128,000
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Claude Haiku 4.5
anthropic/claude-haiku-4.5200,000 ctxReasoningTool callingImage input
Context: 200,000
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
Mistral Medium 3
mistralai/mistral-medium-3131,072 ctxTool callingImage inputJSON output
Context: 131,072
Input / 1M: 138,488
Output / 1M: 692,439
Input / 1M138,488Output / 1M692,439
Claude Sonnet 5.5
anthropic/claude-sonnet-5.51,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
GPT-6.1 Sol
openai/gpt-6.1-sol1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
Claude Opus 5.5
anthropic/claude-opus-5.51,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,384,877
Output / 1M: 6,924,387
Input / 1M1,384,877Output / 1M6,924,387
GPT-6 Astra
openai/gpt-6-astra1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 3,462,194
Output / 1M: 17,310,968
Input / 1M3,462,194Output / 1M17,310,968
Claude Sonnet 5
anthropic/claude-sonnet-51,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 692,439
Output / 1M: 4,154,632
Input / 1M692,439Output / 1M4,154,632
DeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 553,951
Output / 1M: 1,107,902
Input / 1M553,951Output / 1M1,107,902
DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 31,506
Output / 1M: 63,012
Input / 1M31,506Output / 1M63,012
Gemini 3.8 Flash
google/gemini-3.8-flash1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 259,665
Output / 1M: 1,298,323
Input / 1M259,665Output / 1M1,298,323
GPT-6 Luna
openai/gpt-6-luna1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 34,622
Output / 1M: 173,110
Input / 1M34,622Output / 1M173,110
Grok 4.7
x-ai/grok-4.7500,000 ctxReasoningTool callingImage input
Context: 500,000
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Kimi K3
moonshotai/kimi-k31,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 66,474
Output / 1M: 5,539,510
Input / 1M66,474Output / 1M5,539,510
GPT-6.1 Terra Pro
openai/gpt-6.1-terra-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
Claude Haiku 5.5
anthropic/claude-haiku-5.51,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 34,622
Output / 1M: 173,110
Input / 1M34,622Output / 1M173,110
Gemini 4 Argon
google/gemini-4-argon1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
DeepSeek V4.1 Flash 1017
deepseek/deepseek-v4.1-flash-10171,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 2,077
Output / 1M: 173,110
Input / 1M2,077Output / 1M173,110
Grok 4.6
x-ai/grok-4.6500,000 ctxReasoningTool callingImage input
Context: 500,000
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Qwen3.8 Max Prime
qwen/qwen3.8-max-prime1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,384,877
Output / 1M: 4,154,632
Input / 1M1,384,877Output / 1M4,154,632
Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instruct131,072 ctxTool callingJSON output
Context: 131,072
Input / 1M: 69,244
Output / 1M: 180,034
Input / 1M69,244Output / 1M180,034
Muse Spark Open
meta/muse-spark-open1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 432,774
Output / 1M: 1,471,432
Input / 1M432,774Output / 1M1,471,432
Mistral Large 4
mistralai/mistral-large-4-01,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 242,354
Output / 1M: 727,061
Input / 1M242,354Output / 1M727,061
Kimi K3.1 Pro
moonshotai/kimi-k3.1-pro1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
GLM 5.3 FlashX Legal
z-ai/glm-5.3-flashx-legal1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 128,101
Output / 1M: 432,774
Input / 1M128,101Output / 1M432,774
GPT-6.1 Terra
openai/gpt-6.1-terra1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
Claude Fable 5.1
anthropic/claude-fable-5.11,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 3,462,194
Output / 1M: 17,310,968
Input / 1M3,462,194Output / 1M17,310,968
Nano Banana 2.1
google/gemini-nano-banana-2.165,536 ctxReasoningTool callingImage input
Context: 65,536
Input / 1M: 519,329
Output / 1M: 2,596,645
Input / 1M519,329Output / 1M2,596,645
DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 15,580
Output / 1M: 173,110
Input / 1M15,580Output / 1M173,110
Grok 4.5
x-ai/grok-4.5500,000 ctxReasoningTool callingImage input
Context: 500,000
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Qwen3.8 Omni Flash
qwen/qwen3.8-omni-flash1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 51,933
Output / 1M: 162,723
Input / 1M51,933Output / 1M162,723
Muse Wonder
meta/muse-wonder1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 1,384,877
Output / 1M: 6,924,387
Input / 1M1,384,877Output / 1M6,924,387
Mistral Medium 3.5
mistralai/mistral-medium-3-5262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 519,329
Output / 1M: 2,596,645
Input / 1M519,329Output / 1M2,596,645
Kimi K2.7 Code
moonshotai/kimi-k2.7-code262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 207,732
Output / 1M: 1,211,768
Input / 1M207,732Output / 1M1,211,768
GLM 5.3 Prime
z-ai/glm-5.3-prime1,000,000 ctxReasoningTool callingJSON output
Context: 1,000,000
Input / 1M: 969,414
Output / 1M: 3,046,730
Input / 1M969,414Output / 1M3,046,730
GPT-6.1 Sol Pro
openai/gpt-6.1-sol-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
Claude Opus 5
anthropic/claude-opus-51,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,731,097
Output / 1M: 8,655,484
Input / 1M1,731,097Output / 1M8,655,484
Gemini 3.7 Flash
google/gemini-3.7-flash1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 259,665
Output / 1M: 1,298,323
Input / 1M259,665Output / 1M1,298,323
DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-exp1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 74,645
Output / 1M: 223,935
Input / 1M74,645Output / 1M223,935
Grok Build 0.1
x-ai/grok-build-0.1256,000 ctxReasoningTool callingImage input
Context: 256,000
Input / 1M: 346,219
Output / 1M: 692,439
Input / 1M346,219Output / 1M692,439
Qwen3.8 Max (0902)
qwen/qwen3.8-max-09021,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Muse Spark 1.3
meta/muse-spark-1.31,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 432,774
Output / 1M: 1,471,432
Input / 1M432,774Output / 1M1,471,432
Mistral Small 4
mistralai/mistral-small-2603262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 51,933
Output / 1M: 207,732
Input / 1M51,933Output / 1M207,732
Kimi K2.6
moonshotai/kimi-k2.6262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 225,043
Output / 1M: 1,180,608
Input / 1M225,043Output / 1M1,180,608
GLM 5.3 FlashX
z-ai/glm-5.3-flashx1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 128,101
Output / 1M: 432,774
Input / 1M128,101Output / 1M432,774
GPT-6 Luna Pro
openai/gpt-6-luna-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 34,622
Output / 1M: 173,110
Input / 1M34,622Output / 1M173,110
Claude Fable 5
anthropic/claude-fable-51,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 3,462,194
Output / 1M: 17,310,968
Input / 1M3,462,194Output / 1M17,310,968
Gemini 3.6 Flash
google/gemini-3.6-flash1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 259,665
Output / 1M: 1,298,323
Input / 1M259,665Output / 1M1,298,323
DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-08131,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 35,661
Output / 1M: 1,422,962
Input / 1M35,661Output / 1M1,422,962
Grok 4.3
x-ai/grok-4.31,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 432,774
Output / 1M: 865,548
Input / 1M432,774Output / 1M865,548
Qwen3.8 Flash
qwen/qwen3.8-flash1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 51,933
Output / 1M: 162,723
Input / 1M51,933Output / 1M162,723
Muse Glimmer 30B
meta/muse-glimmer-30b131,072 ctxReasoningTool callingImage input
Context: 131,072
Input / 1M: 103,866
Output / 1M: 415,463
Input / 1M103,866Output / 1M415,463
Devstral 2 2512
mistralai/devstral-2512262,144 ctxTool callingJSON output
Context: 262,144
Input / 1M: 138,488
Output / 1M: 692,439
Input / 1M138,488Output / 1M692,439
Kimi K2.5
moonshotai/kimi-k2.5262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 173,110
Output / 1M: 865,548
Input / 1M173,110Output / 1M865,548
GLM 5.3 Flash
z-ai/glm-5.3-flash1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 51,933
Output / 1M: 173,110
Input / 1M51,933Output / 1M173,110
GPT-6 Sol Pro
openai/gpt-6-sol-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
Claude Opus 4.8
anthropic/claude-opus-4.81,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,731,097
Output / 1M: 8,655,484
Input / 1M1,731,097Output / 1M8,655,484
Gemini 3.5 Flash Lite
google/gemini-3.5-flash-lite1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 103,866
Output / 1M: 865,548
Input / 1M103,866Output / 1M865,548
DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-07311,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 20,427
Output / 1M: 103,866
Input / 1M20,427Output / 1M103,866
Grok 4.20 Multi-Agent
x-ai/grok-4.20-multi-agent2,000,000 ctxReasoningImage inputJSON output
Context: 2,000,000
Input / 1M: 432,774
Output / 1M: 865,548
Input / 1M432,774Output / 1M865,548
Qwen3.8 27B
qwen/qwen3.8-27b1,024,000 ctxReasoningTool callingImage input
Context: 1,024,000
Input / 1M: 51,933
Output / 1M: 649,161
Input / 1M51,933Output / 1M649,161
Muse Spark 1.2
meta/muse-spark-1.21,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 432,774
Output / 1M: 1,471,432
Input / 1M432,774Output / 1M1,471,432
Kimi K2 Thinking
moonshotai/kimi-k2-thinking262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 207,732
Output / 1M: 865,548
Input / 1M207,732Output / 1M865,548
GLM 5.3
z-ai/glm-5.31,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 24,201
Output / 1M: 484,707
Input / 1M24,201Output / 1M484,707
GPT-6 Sol
openai/gpt-6-sol1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
Claude Opus 4.7
anthropic/claude-opus-4.71,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,731,097
Output / 1M: 8,655,484
Input / 1M1,731,097Output / 1M8,655,484
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
google/gemini-3.1-flash-lite-image65,536 ctxReasoningImage inputJSON output
Context: 65,536
Input / 1M: 86,555
Output / 1M: 519,329
Input / 1M86,555Output / 1M519,329
DeepSeek V3.2
deepseek/deepseek-v3.2163,840 ctxReasoningTool callingJSON output
Context: 163,840
Input / 1M: 90,017
Output / 1M: 131,563
Input / 1M90,017Output / 1M131,563
Qwen3.8 2.4T A95B
qwen/qwen3.8-2.4t-a95b1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Muse Spark 1.1
meta/muse-spark-1.11,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 432,774
Output / 1M: 1,471,432
Input / 1M432,774Output / 1M1,471,432
Kimi K2 0711
moonshotai/kimi-k2131,072 ctxTool calling
Context: 131,072
Input / 1M: 197,345
Output / 1M: 796,305
Input / 1M197,345Output / 1M796,305
GLM 5.2
z-ai/glm-5.21,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 2,077
Output / 1M: 2,354,292
Input / 1M2,077Output / 1M2,354,292
GPT-6 Astra Pro
openai/gpt-6-astra-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 3,462,194
Output / 1M: 17,310,968
Input / 1M3,462,194Output / 1M17,310,968
Claude Sonnet 4.6
anthropic/claude-sonnet-4.61,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,038,658
Output / 1M: 5,193,290
Input / 1M1,038,658Output / 1M5,193,290
Nano Banana 2 (Gemini 3.1 Flash Image)
google/gemini-3.1-flash-image131,072 ctxReasoningImage inputJSON output
Context: 131,072
Input / 1M: 173,110
Output / 1M: 1,038,658
Input / 1M173,110Output / 1M1,038,658
DeepSeek V3.1
deepseek/deepseek-chat-v3.1163,840 ctxReasoningTool callingJSON output
Context: 163,840
Input / 1M: 86,555
Output / 1M: 328,908
Input / 1M86,555Output / 1M328,908
Qwen3.7 Flash
qwen/qwen3.7-flash1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 10,387
Output / 1M: 45,009
Input / 1M10,387Output / 1M45,009
GLM 5.1
z-ai/glm-5.1204,800 ctxReasoningTool callingJSON output
Context: 204,800
Input / 1M: 484,707
Output / 1M: 1,523,365
Input / 1M484,707Output / 1M1,523,365
GPT-5.6 Luna Pro
openai/gpt-5.6-luna-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 69,244
Output / 1M: 415,463
Input / 1M69,244Output / 1M415,463
Claude Opus 4.6
anthropic/claude-opus-4.61,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,731,097
Output / 1M: 8,655,484
Input / 1M1,731,097Output / 1M8,655,484
Nano Banana Pro (Gemini 3 Pro Image)
google/gemini-3-pro-image131,072 ctxReasoningTool callingImage input
Context: 131,072
Input / 1M: 692,439
Output / 1M: 4,154,632
Input / 1M692,439Output / 1M4,154,632
Qwen3.7 Plus
qwen/qwen3.7-plus1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 110,790
Output / 1M: 443,161
Input / 1M110,790Output / 1M443,161
GLM 5V Turbo
z-ai/glm-5v-turbo202,752 ctxReasoningTool callingImage input
Context: 202,752
Input / 1M: 415,463
Output / 1M: 1,384,877
Input / 1M415,463Output / 1M1,384,877
GPT-5.6 Luna
openai/gpt-5.6-luna1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 69,244
Output / 1M: 415,463
Input / 1M69,244Output / 1M415,463
Gemini 3.5 Flash
google/gemini-3.5-flash1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 519,329
Output / 1M: 3,115,974
Input / 1M519,329Output / 1M3,115,974
Qwen3.7 Max
qwen/qwen3.7-max1,000,000 ctxReasoningTool callingJSON output
Context: 1,000,000
Input / 1M: 510,674
Output / 1M: 1,532,021
Input / 1M510,674Output / 1M1,532,021
GLM 5 Turbo
z-ai/glm-5-turbo202,752 ctxReasoningTool callingJSON output
Context: 202,752
Input / 1M: 415,463
Output / 1M: 1,384,877
Input / 1M415,463Output / 1M1,384,877
GPT-5.6 Terra Pro
openai/gpt-5.6-terra-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 692,439
Output / 1M: 4,154,632
Input / 1M692,439Output / 1M4,154,632
Gemini 3.1 Flash Lite
google/gemini-3.1-flash-lite1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 86,555
Output / 1M: 519,329
Input / 1M86,555Output / 1M519,329
Qwen3.5 Plus 2026-04-20
qwen/qwen3.5-plus-202604201,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 103,866
Output / 1M: 623,195
Input / 1M103,866Output / 1M623,195
GLM 5
z-ai/glm-5204,800 ctxReasoningTool callingJSON output
Context: 204,800
Input / 1M: 346,219
Output / 1M: 1,107,902
Input / 1M346,219Output / 1M1,107,902
GPT-5.6 Terra
openai/gpt-5.6-terra1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 692,439
Output / 1M: 4,154,632
Input / 1M692,439Output / 1M4,154,632
Gemma 4 26B A4B
google/gemma-4-26b-a4b-it262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 23,197
Output / 1M: 69,244
Input / 1M23,197Output / 1M69,244
Qwen3.6 Flash
qwen/qwen3.6-flash1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 64,916
Output / 1M: 389,497
Input / 1M64,916Output / 1M389,497
GLM 4.7 Flash
z-ai/glm-4.7-flash200,000 ctxReasoningTool callingJSON output
Context: 200,000
Input / 1M: 20,946
Output / 1M: 138,488
Input / 1M20,946Output / 1M138,488
GPT-5.6 Sol Pro
openai/gpt-5.6-sol-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 1,384,877
Output / 1M: 6,924,387
Input / 1M1,384,877Output / 1M6,924,387
Gemma 4 31B
google/gemma-4-31b-it262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 69,244
Output / 1M: 138,488
Input / 1M69,244Output / 1M138,488
Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 34,622
Output / 1M: 311,597
Input / 1M34,622Output / 1M311,597
GLM 4.7
z-ai/glm-4.7204,800 ctxReasoningTool callingJSON output
Context: 204,800
Input / 1M: 207,732
Output / 1M: 761,683
Input / 1M207,732Output / 1M761,683
GPT-5.6 Sol
openai/gpt-5.6-sol1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 1,384,877
Output / 1M: 6,924,387
Input / 1M1,384,877Output / 1M6,924,387
Lyria 3 Pro Preview
google/lyria-3-pro-preview1,048,576 ctxImage inputJSON output
Context: 1,048,576
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Qwen3.6 27B
qwen/qwen3.6-27b262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 155,799
Output / 1M: 934,792
Input / 1M155,799Output / 1M934,792
GLM 4.6V
z-ai/glm-4.6v131,072 ctxReasoningTool callingImage input
Context: 131,072
Input / 1M: 103,866
Output / 1M: 311,597
Input / 1M103,866Output / 1M311,597
GPT Chat Latest
openai/gpt-chat-latest400,000 ctxTool callingImage inputJSON output
Context: 400,000
Input / 1M: 1,731,097
Output / 1M: 10,386,581
Input / 1M1,731,097Output / 1M10,386,581
Lyria 3 Clip Preview
google/lyria-3-clip-preview1,048,576 ctxImage inputJSON output
Context: 1,048,576
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Qwen3.6 Plus
qwen/qwen3.6-plus1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 112,521
Output / 1M: 675,128
Input / 1M112,521Output / 1M675,128
GPT-5.5 Pro
openai/gpt-5.5-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 10,386,581
Output / 1M: 62,319,483
Input / 1M10,386,581Output / 1M62,319,483
Gemini 3.1 Pro Preview Custom Tools
google/gemini-3.1-pro-preview-customtools1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 692,439
Output / 1M: 4,154,632
Input / 1M692,439Output / 1M4,154,632
Qwen3.5-9B
qwen/qwen3.5-9b262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 58,857
Output / 1M: 86,555
Input / 1M58,857Output / 1M86,555
GPT-5.5
openai/gpt-5.51,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 1,731,097
Output / 1M: 10,386,581
Input / 1M1,731,097Output / 1M10,386,581
Gemini 3 Flash Preview
google/gemini-3-flash-preview1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 173,110
Output / 1M: 1,038,658
Input / 1M173,110Output / 1M1,038,658
Qwen3.5-35B-A3B
qwen/qwen3.5-35b-a3b262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 48,471
Output / 1M: 346,219
Input / 1M48,471Output / 1M346,219
GPT-5.4 Image 2
openai/gpt-5.4-image-2272,000 ctxReasoningImage inputJSON output
Context: 272,000
Input / 1M: 2,769,755
Output / 1M: 5,193,290
Input / 1M2,769,755Output / 1M5,193,290
Gemini 2.5 Flash Lite
google/gemini-2.5-flash-lite1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 34,622
Output / 1M: 138,488
Input / 1M34,622Output / 1M138,488
Qwen3.5-27B
qwen/qwen3.5-27b262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 90,017
Output / 1M: 900,170
Input / 1M90,017Output / 1M900,170
GPT-5.4 Nano
openai/gpt-5.4-nano400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 69,244
Output / 1M: 432,774
Input / 1M69,244Output / 1M432,774
Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10b262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 90,017
Output / 1M: 720,136
Input / 1M90,017Output / 1M720,136
GPT-5.4 Mini
openai/gpt-5.4-mini400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 259,665
Output / 1M: 1,557,987
Input / 1M259,665Output / 1M1,557,987
Qwen3.5-Flash
qwen/qwen3.5-flash-02-231,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 22,504
Output / 1M: 90,017
Input / 1M22,504Output / 1M90,017
GPT-5.4 Pro
openai/gpt-5.4-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 10,386,581
Output / 1M: 62,319,483
Input / 1M10,386,581Output / 1M62,319,483
Qwen3.5 Plus 2026-02-15
qwen/qwen3.5-plus-02-151,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 90,017
Output / 1M: 540,102
Input / 1M90,017Output / 1M540,102
GPT-5.4
openai/gpt-5.41,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 865,548
Output / 1M: 5,193,290
Input / 1M865,548Output / 1M5,193,290
Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 173,110
Output / 1M: 1,246,390
Input / 1M173,110Output / 1M1,246,390
GPT-5.3-Codex
openai/gpt-5.3-codex400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 605,884
Output / 1M: 4,847,071
Input / 1M605,884Output / 1M4,847,071
Qwen3 Coder Next
qwen/qwen3-coder-next262,144 ctxTool callingJSON output
Context: 262,144
Input / 1M: 41,546
Output / 1M: 276,975
Input / 1M41,546Output / 1M276,975
GPT Audio
openai/gpt-audio128,000 ctxTool callingJSON outputAudio input
Context: 128,000
Input / 1M: 865,548
Output / 1M: 3,462,194
Input / 1M865,548Output / 1M3,462,194
Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instruct262,144 ctxTool callingImage inputJSON output
Context: 262,144
Input / 1M: 72,706
Output / 1M: 657,817
Input / 1M72,706Output / 1M657,817
GPT Audio Mini
openai/gpt-audio-mini128,000 ctxTool callingJSON outputAudio input
Context: 128,000
Input / 1M: 207,732
Output / 1M: 830,926
Input / 1M207,732Output / 1M830,926
Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507262,144 ctxTool callingJSON output
Context: 262,144
Input / 1M: 34,622
Output / 1M: 103,866
Input / 1M34,622Output / 1M103,866
GPT-5.2-Codex
openai/gpt-5.2-codex400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 605,884
Output / 1M: 4,847,071
Input / 1M605,884Output / 1M4,847,071
GPT-5.2 Pro
openai/gpt-5.2-pro400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 7,270,606
Output / 1M: 58,164,851
Input / 1M7,270,606Output / 1M58,164,851
GPT-5.2
openai/gpt-5.2400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 605,884
Output / 1M: 4,847,071
Input / 1M605,884Output / 1M4,847,071
GPT-5.1-Codex-Max
openai/gpt-5.1-codex-max400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 432,774
Output / 1M: 3,462,194
Input / 1M432,774Output / 1M3,462,194
GPT-5 Nano
openai/gpt-5-nano400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 17,311
Output / 1M: 138,488
Input / 1M17,311Output / 1M138,488
GPT-4.1
openai/gpt-4.11,047,576 ctxTool callingImage inputJSON output
Context: 1,047,576
Input / 1M: 692,439
Output / 1M: 2,769,755
Input / 1M692,439Output / 1M2,769,755
GPT-4o-mini
openai/gpt-4o-mini128,000 ctxTool callingImage inputJSON output
Context: 128,000
Input / 1M: 51,933
Output / 1M: 207,732
Input / 1M51,933Output / 1M207,732
Sonar
perplexity/sonar127,072 ctxImage input
Context: 127,072
Input / 1M: 346,219
Output / 1M: 346,219
Input / 1M346,219Output / 1M346,219
GPT-5.1
openai/gpt-5.1400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 432,774
Output / 1M: 3,462,194
Input / 1M432,774Output / 1M3,462,194
GPT-5.1-Codex
openai/gpt-5.1-codex400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 432,774
Output / 1M: 3,462,194
Input / 1M432,774Output / 1M3,462,194
GPT-5.1-Codex-Mini
openai/gpt-5.1-codex-mini400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 86,555
Output / 1M: 692,439
Input / 1M86,555Output / 1M692,439
gpt-oss-safeguard-20b
openai/gpt-oss-safeguard-20b131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 25,966
Output / 1M: 103,866
Input / 1M25,966Output / 1M103,866
GPT-5 Image Mini
openai/gpt-5-image-mini400,000 ctxReasoningImage inputJSON output
Context: 400,000
Input / 1M: 865,548
Output / 1M: 692,439
Input / 1M865,548Output / 1M692,439
GPT-5 Image
openai/gpt-5-image400,000 ctxReasoningImage inputJSON output
Context: 400,000
Input / 1M: 3,462,194
Output / 1M: 3,462,194
Input / 1M3,462,194Output / 1M3,462,194
GPT-5 Pro
openai/gpt-5-pro400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 5,193,290
Output / 1M: 41,546,322
Input / 1M5,193,290Output / 1M41,546,322
gpt-oss-120b
openai/gpt-oss-120b131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 51,933
Output / 1M: 207,732
Input / 1M51,933Output / 1M207,732
gpt-oss-20b
openai/gpt-oss-20b131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 10,387
Output / 1M: 45,009
Input / 1M10,387Output / 1M45,009
o3 Pro
openai/o3-pro200,000 ctxReasoningTool callingImage input
Context: 200,000
Input / 1M: 6,924,387
Output / 1M: 27,697,548
Input / 1M6,924,387Output / 1M27,697,548
o3
openai/o3200,000 ctxReasoningTool callingImage input
Context: 200,000
Input / 1M: 692,439
Output / 1M: 2,769,755
Input / 1M692,439Output / 1M2,769,755
GPT-4.1 Mini
openai/gpt-4.1-mini1,047,576 ctxTool callingImage inputJSON output
Context: 1,047,576
Input / 1M: 138,488
Output / 1M: 553,951
Input / 1M138,488Output / 1M553,951
GPT-4.1 Nano
openai/gpt-4.1-nano1,047,576 ctxTool callingImage inputJSON output
Context: 1,047,576
Input / 1M: 34,622
Output / 1M: 138,488
Input / 1M34,622Output / 1M138,488
GPT-4o (2024-11-20)
openai/gpt-4o-2024-11-20128,000 ctxTool callingImage inputJSON output
Context: 128,000
Input / 1M: 865,548
Output / 1M: 3,462,194
Input / 1M865,548Output / 1M3,462,194
GPT-4o (2024-08-06)
openai/gpt-4o-2024-08-06128,000 ctxTool callingImage inputJSON output
Context: 128,000
Input / 1M: 865,548
Output / 1M: 3,462,194
Input / 1M865,548Output / 1M3,462,194
GPT-4o
openai/gpt-4o128,000 ctxTool callingImage inputJSON output
Context: 128,000
Input / 1M: 865,548
Output / 1M: 3,462,194
Input / 1M865,548Output / 1M3,462,194
GPT-3.5 Turbo v0613Older version
openai/gpt-3.5-turbo-06134,095 ctxTool callingJSON output
Context: 4,095
Input / 1M: 346,219
Output / 1M: 692,439
Input / 1M346,219Output / 1M692,439
GPT-3.5 Turbo 16k
openai/gpt-3.5-turbo-16k16,385 ctxTool callingJSON output
Context: 16,385
Input / 1M: 1,038,658
Output / 1M: 1,384,877
Input / 1M1,038,658Output / 1M1,384,877
GPT-4
openai/gpt-48,191 ctxTool callingJSON output
Context: 8,191
Input / 1M: 10,386,581
Output / 1M: 20,773,161
Input / 1M10,386,581Output / 1M20,773,161
Claude Opus 4.5
anthropic/claude-opus-4.5200,000 ctxReasoningTool callingImage input
Context: 200,000
Input / 1M: 1,731,097
Output / 1M: 8,655,484
Input / 1M1,731,097Output / 1M8,655,484
Nano Banana (Gemini 2.5 Flash Image)
google/gemini-2.5-flash-image32,768 ctxReasoningImage inputJSON output
Context: 32,768
Input / 1M: 103,866
Output / 1M: 865,548
Input / 1M103,866Output / 1M865,548
Gemma 3 4B
google/gemma-3-4b-it131,072 ctxImage inputJSON output
Context: 131,072
Input / 1M: 17,311
Output / 1M: 34,622
Input / 1M17,311Output / 1M34,622
Gemma 3 12B
google/gemma-3-12b-it131,072 ctxTool callingImage inputJSON output
Context: 131,072
Input / 1M: 17,311
Output / 1M: 51,933
Input / 1M17,311Output / 1M51,933
Gemma 3 27B
google/gemma-3-27b-it131,072 ctxTool callingImage inputJSON output
Context: 131,072
Input / 1M: 27,698
Output / 1M: 121,177
Input / 1M27,698Output / 1M121,177
Gemma 2 27B
google/gemma-2-27b-it8,192 ctxJSON output
Context: 8,192
Input / 1M: 225,043
Output / 1M: 225,043
Input / 1M225,043Output / 1M225,043
DeepSeek V3.2 Exp
deepseek/deepseek-v3.2-exp163,840 ctxReasoningTool callingJSON output
Context: 163,840
Input / 1M: 93,479
Output / 1M: 141,950
Input / 1M93,479Output / 1M141,950
DeepSeek V3.1 Terminus
deepseek/deepseek-v3.1-terminus163,840 ctxReasoningTool callingJSON output
Context: 163,840
Input / 1M: 93,479
Output / 1M: 346,219
Input / 1M93,479Output / 1M346,219
R1 0528
deepseek/deepseek-r1-0528163,840 ctxReasoningTool callingJSON output
Context: 163,840
Input / 1M: 173,110
Output / 1M: 744,372
Input / 1M173,110Output / 1M744,372
DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324163,840 ctxTool callingJSON output
Context: 163,840
Input / 1M: 100,404
Output / 1M: 394,690
Input / 1M100,404Output / 1M394,690
Qwen3 VL 8B Instruct
qwen/qwen3-vl-8b-instruct262,144 ctxTool callingImage inputJSON output
Context: 262,144
Input / 1M: 86,555
Output / 1M: 259,665
Input / 1M86,555Output / 1M259,665
Qwen3 VL 30B A3B Thinking
qwen/qwen3-vl-30b-a3b-thinking262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 100,404
Output / 1M: 346,219
Input / 1M100,404Output / 1M346,219
Qwen3 VL 30B A3B Instruct
qwen/qwen3-vl-30b-a3b-instruct262,144 ctxTool callingImage inputJSON output
Context: 262,144
Input / 1M: 51,933
Output / 1M: 207,732
Input / 1M51,933Output / 1M207,732
Qwen3 Coder Flash
qwen/qwen3-coder-flash1,000,000 ctxTool callingJSON output
Context: 1,000,000
Input / 1M: 67,513
Output / 1M: 337,564
Input / 1M67,513Output / 1M337,564
Qwen3 Next 80B A3B Instruct
qwen/qwen3-next-80b-a3b-instruct262,144 ctxTool callingJSON output
Context: 262,144
Input / 1M: 31,160
Output / 1M: 380,841
Input / 1M31,160Output / 1M380,841
Qwen3 Coder 30B A3B Instruct
qwen/qwen3-coder-30b-a3b-instruct262,144 ctxTool callingJSON output
Context: 262,144
Input / 1M: 51,933
Output / 1M: 207,732
Input / 1M51,933Output / 1M207,732
Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507128,000 ctxReasoningTool calling
Context: 128,000
Input / 1M: 155,799
Output / 1M: 1,211,768
Input / 1M155,799Output / 1M1,211,768
Qwen3 235B A22B Instruct 2507
qwen/qwen3-235b-a22b-2507262,144 ctxTool callingJSON output
Context: 262,144
Input / 1M: 48,471
Output / 1M: 276,975
Input / 1M48,471Output / 1M276,975
Qwen3 30B A3B
qwen/qwen3-30b-a3b40,960 ctxReasoningTool callingJSON output
Context: 40,960
Input / 1M: 41,546
Output / 1M: 173,110
Input / 1M41,546Output / 1M173,110
Qwen3 14B
qwen/qwen3-14b40,960 ctxReasoningTool callingJSON output
Context: 40,960
Input / 1M: 41,546
Output / 1M: 83,093
Input / 1M41,546Output / 1M83,093
Qwen3 32B
qwen/qwen3-32b131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 27,698
Output / 1M: 96,941
Input / 1M27,698Output / 1M96,941
Qwen2.5 VL 72B Instruct
qwen/qwen2.5-vl-72b-instruct128,000 ctxImage inputJSON output
Context: 128,000
Input / 1M: 276,975
Output / 1M: 346,219
Input / 1M276,975Output / 1M346,219
Qwen-Plus
qwen/qwen-plus1,000,000 ctxTool callingJSON output
Context: 1,000,000
Input / 1M: 90,017
Output / 1M: 270,051
Input / 1M90,017Output / 1M270,051
Qwen2.5 Coder 32B Instruct
qwen/qwen-2.5-coder-32b-instruct32,768 ctxJSON output
Context: 32,768
Input / 1M: 228,505
Output / 1M: 346,219
Input / 1M228,505Output / 1M346,219
Qwen2.5 7B Instruct
qwen/qwen-2.5-7b-instruct32,768 ctxTool callingJSON output
Context: 32,768
Input / 1M: 34,622
Output / 1M: 69,244
Input / 1M34,622Output / 1M69,244
Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instruct32,768 ctxTool callingJSON output
Context: 32,768
Input / 1M: 124,639
Output / 1M: 138,488
Input / 1M124,639Output / 1M138,488
Llama Guard 4 12B
meta-llama/llama-guard-4-12b163,840 ctxImage input
Context: 163,840
Input / 1M: 62,319
Output / 1M: 62,319
Input / 1M62,319Output / 1M62,319
Llama 4 Maverick
meta-llama/llama-4-maverick524,288 ctxTool callingImage inputJSON output
Context: 524,288
Input / 1M: 121,177
Output / 1M: 346,219
Input / 1M121,177Output / 1M346,219
Llama 4 Scout
meta-llama/llama-4-scout327,680 ctxTool callingImage inputJSON output
Context: 327,680
Input / 1M: 34,622
Output / 1M: 103,866
Input / 1M34,622Output / 1M103,866
Llama 3.2 1B Instruct
meta-llama/llama-3.2-1b-instruct60,000 ctx
Context: 60,000
Input / 1M: 9,348
Output / 1M: 69,590
Input / 1M9,348Output / 1M69,590
Llama 3.2 3B Instruct
meta-llama/llama-3.2-3b-instruct131,072 ctxJSON output
Context: 131,072
Input / 1M: 17,623
Output / 1M: 115,983
Input / 1M17,623Output / 1M115,983
Llama 3.1 70B Instruct
meta-llama/llama-3.1-70b-instruct131,072 ctx
Context: 131,072
Input / 1M: 249,278
Output / 1M: 249,278
Input / 1M249,278Output / 1M249,278
Llama 3.1 8B Instruct
meta-llama/llama-3.1-8b-instruct131,072 ctxTool callingJSON output
Context: 131,072
Input / 1M: 17,311
Output / 1M: 27,698
Input / 1M17,311Output / 1M27,698
Ministral 3 14B 2512
mistralai/ministral-14b-2512262,144 ctxTool callingImage inputJSON output
Context: 262,144
Input / 1M: 69,244
Output / 1M: 69,244
Input / 1M69,244Output / 1M69,244
Ministral 3 8B 2512
mistralai/ministral-8b-2512262,144 ctxTool callingImage inputJSON output
Context: 262,144
Input / 1M: 51,933
Output / 1M: 51,933
Input / 1M51,933Output / 1M51,933
Ministral 3 3B 2512
mistralai/ministral-3b-2512131,072 ctxTool callingImage inputJSON output
Context: 131,072
Input / 1M: 34,622
Output / 1M: 34,622
Input / 1M34,622Output / 1M34,622
Mistral Large 3 2512
mistralai/mistral-large-2512262,144 ctxTool callingImage inputJSON output
Context: 262,144
Input / 1M: 173,110
Output / 1M: 519,329
Input / 1M173,110Output / 1M519,329
Voxtral Small 24B 2507
mistralai/voxtral-small-24b-250732,768 ctxTool callingJSON outputAudio input
Context: 32,768
Input / 1M: 34,622
Output / 1M: 103,866
Input / 1M34,622Output / 1M103,866
Mistral Medium 3.1
mistralai/mistral-medium-3.1131,072 ctxTool callingImage inputJSON output
Context: 131,072
Input / 1M: 138,488
Output / 1M: 692,439
Input / 1M138,488Output / 1M692,439
Codestral 2508
mistralai/codestral-2508256,000 ctxTool callingJSON output
Context: 256,000
Input / 1M: 103,866
Output / 1M: 311,597
Input / 1M103,866Output / 1M311,597
Mistral Small 3.2 24B
mistralai/mistral-small-3.2-24b-instruct256,000 ctxTool callingImage inputJSON output
Context: 256,000
Input / 1M: 25,966
Output / 1M: 69,244
Input / 1M25,966Output / 1M69,244
Mistral Small 3.1 24B
mistralai/mistral-small-3.1-24b-instruct128,000 ctxTool callingImage inputJSON output
Context: 128,000
Input / 1M: 121,523
Output / 1M: 192,152
Input / 1M121,523Output / 1M192,152
Saba
mistralai/mistral-saba32,768 ctxTool callingJSON output
Context: 32,768
Input / 1M: 69,244
Output / 1M: 207,732
Input / 1M69,244Output / 1M207,732
Mistral Small 3
mistralai/mistral-small-24b-instruct-250132,768 ctxJSON output
Context: 32,768
Input / 1M: 17,311
Output / 1M: 27,698
Input / 1M17,311Output / 1M27,698
Mistral Large 2407
mistralai/mistral-large-2407131,072 ctxTool callingJSON output
Context: 131,072
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Mistral Nemo
mistralai/mistral-nemo131,072 ctxTool callingJSON output
Context: 131,072
Input / 1M: 10,040
Output / 1M: 10,387
Input / 1M10,040Output / 1M10,387
Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct65,536 ctxTool callingJSON output
Context: 65,536
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Kimi K2 0905
moonshotai/kimi-k2-0905262,144 ctxTool callingJSON output
Context: 262,144
Input / 1M: 207,732
Output / 1M: 865,548
Input / 1M207,732Output / 1M865,548
GLM 4.6
z-ai/glm-4.6204,800 ctxReasoningTool callingJSON output
Context: 204,800
Input / 1M: 173,110
Output / 1M: 692,439
Input / 1M173,110Output / 1M692,439
GLM 4.5V
z-ai/glm-4.5v65,536 ctxReasoningTool callingImage input
Context: 65,536
Input / 1M: 207,732
Output / 1M: 623,195
Input / 1M207,732Output / 1M623,195
GLM 4.5
z-ai/glm-4.5131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 207,732
Output / 1M: 761,683
Input / 1M207,732Output / 1M761,683
GLM 4.5 Air
z-ai/glm-4.5-air131,072 ctxReasoningTool calling
Context: 131,072
Input / 1M: 45,009
Output / 1M: 294,286
Input / 1M45,009Output / 1M294,286
ricursiveAI/Ripple-65B-Preview
ricursiveai/ripple-65b-preview1,048,576 ctxTool callingJSON output
Context: 1,048,576
Input / 1M: 69,244
Output / 1M: 207,732
Input / 1M69,244Output / 1M207,732
Hy4
tencent/hy41,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 144,373
Output / 1M: 432,947
Input / 1M144,373Output / 1M432,947
Crouton Alpha
stealth/crouton-alpha1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Particle-1
particle-ai/particle-11,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 17,311
Output / 1M: 173,110
Input / 1M17,311Output / 1M173,110
FlintFree
recursive/flint-v1.0:free262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
MiniMax M3.1 Flash
minimax/minimax-m3.1-flash1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 51,933
Output / 1M: 207,732
Input / 1M51,933Output / 1M207,732
Glimpse
elorian/glimpse262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 207,732
Output / 1M: 1,038,658
Input / 1M207,732Output / 1M1,038,658
Xing4.0 29B A4BFree
xingchen-agi/xing4.0-29b-a4b:free262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Beam 1.0 501B A23B
reflection/beam-1.0-501b-a23b1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 86,555
Output / 1M: 346,219
Input / 1M86,555Output / 1M346,219
Mercury 3
inception/mercury-31,000,000 ctxReasoningTool callingJSON output
Context: 1,000,000
Input / 1M: 34,622
Output / 1M: 121,177
Input / 1M34,622Output / 1M121,177
Ternary Bonsai 2 9B
prism-ml/ternary-bonsai-2-9b262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 27,698
Output / 1M: 45,009
Input / 1M27,698Output / 1M45,009
Moondream 3 Preview
moondream/moondream3-preview32,000 ctxReasoningImage input
Context: 32,000
Input / 1M: 103,866
Output / 1M: 865,548
Input / 1M103,866Output / 1M865,548
Moondream 3.1
moondream/moondream3.1-9b-a2b32,000 ctxReasoningImage input
Context: 32,000
Input / 1M: 103,866
Output / 1M: 865,548
Input / 1M103,866Output / 1M865,548
Nemotron 3.5 Super VL
nvidia/nemotron-3.5-super-vl1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 51,933
Output / 1M: 173,110
Input / 1M51,933Output / 1M173,110
Pareto 26.10
unbiased/pareto-26.101,048,576 ctxTool callingImage input
Context: 1,048,576
Input / 1M: 276,975
Output / 1M: 1,107,902
Input / 1M276,975Output / 1M1,107,902
Pareto 26.9
unbiased/pareto-26.9262,144 ctxTool callingImage inputJSON output
Context: 262,144
Input / 1M: 865,548
Output / 1M: 2,596,645
Input / 1M865,548Output / 1M2,596,645
LFM2.5-24B-A2B
liquid/lfm-2.5-24b-a2b128,000 ctxReasoningTool callingJSON output
Context: 128,000
Input / 1M: 17,311
Output / 1M: 242,354
Input / 1M17,311Output / 1M242,354
Summarize
scaledown/summarize1,000,000 ctxImage input
Context: 1,000,000
Input / 1M: 13,849
Output / 1M: 0
Input / 1M13,849Output / 1M0
Extract
scaledown/extract1,000,000 ctxImage input
Context: 1,000,000
Input / 1M: 13,849
Output / 1M: 0
Input / 1M13,849Output / 1M0
Step 5 Preview
stepfun/step-5-preview1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 346,219
Output / 1M: 934,792
Input / 1M346,219Output / 1M934,792
Ling 3.1 Flash
inclusionai/ling-3.1-flash1,000,000 ctxReasoningTool callingJSON output
Context: 1,000,000
Input / 1M: 25,966
Output / 1M: 77,899
Input / 1M25,966Output / 1M77,899
Jev Router
typesafe/jev-router1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Variable price
Variable price
Perceptron Mk1.5
perceptron/perceptron-mk1.536,864 ctxReasoningTool callingImage input
Context: 36,864
Input / 1M: 51,933
Output / 1M: 519,329
Input / 1M51,933Output / 1M519,329
Ember-1
fireworks/ember-11,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 1,038,658
Output / 1M: 5,193,290
Input / 1M1,038,658Output / 1M5,193,290
Aion 3.5 Mini
aion-labs/aion-3.5-mini262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 242,354
Output / 1M: 484,707
Input / 1M242,354Output / 1M484,707
Aion 3.5
aion-labs/aion-3.5262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 1,038,658
Output / 1M: 2,077,316
Input / 1M1,038,658Output / 1M2,077,316
Solar Mini 4
upstage/solar-mini4524,288 ctxReasoningTool callingJSON output
Context: 524,288
Input / 1M: 17,311
Output / 1M: 69,244
Input / 1M17,311Output / 1M69,244
Command A+
cohere/command-a-plus192,000 ctxReasoningTool callingImage input
Context: 192,000
Input / 1M: 103,866
Output / 1M: 519,329
Input / 1M103,866Output / 1M519,329
Switchyard
nvidia/switchyard1,000,000 ctx
Context: 1,000,000
Variable price
Variable price
MiMo-V2.6-Pro-UltraSpeed
xiaomi/mimo-v2.6-pro-ultraspeed1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 1,506,054
Output / 1M: 3,012,108
Input / 1M1,506,054Output / 1M3,012,108
MiMo-V2.6-Flash
xiaomi/mimo-v2.6-flash1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 48,471
Output / 1M: 96,941
Input / 1M48,471Output / 1M96,941
MiMo-V2.6-Pro
xiaomi/mimo-v2.6-pro1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 150,605
Output / 1M: 301,211
Input / 1M150,605Output / 1M301,211
Ternary Bonsai 2 27B
prism-ml/ternary-bonsai-2-27b262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 25,966
Output / 1M: 173,110
Input / 1M25,966Output / 1M173,110
Schematron V2 Turbo
inference-net/schematron-v2-turbo128,000 ctxJSON output
Context: 128,000
Input / 1M: 10,387
Output / 1M: 51,933
Input / 1M10,387Output / 1M51,933
Schematron V2 Small
inference-net/schematron-v2-small128,000 ctxJSON output
Context: 128,000
Input / 1M: 17,311
Output / 1M: 79,630
Input / 1M17,311Output / 1M79,630
Fugu Ultra v2
sakana/fugu-ultra-v21,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,731,097
Output / 1M: 10,386,581
Input / 1M1,731,097Output / 1M10,386,581
Fugu Max
sakana/fugu-max1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Ling 3.0 Flash VL
inclusionai/ling-3.0-flash-vl131,072 ctxReasoningTool callingImage input
Context: 131,072
Input / 1M: 20,773
Output / 1M: 62,319
Input / 1M20,773Output / 1M62,319
Mercury 2.5
inception/mercury-2.5260,000 ctxReasoningTool callingJSON output
Context: 260,000
Input / 1M: 13,849
Output / 1M: 51,933
Input / 1M13,849Output / 1M51,933
Nex-N2.5-Mini
nex-agi/nex-n2.5-mini262,144 ctxReasoningImage inputJSON output
Context: 262,144
Input / 1M: 8,655
Output / 1M: 34,622
Input / 1M8,655Output / 1M34,622
Nex-N2.5-Pro
nex-agi/nex-n2.5-pro262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 25,966
Output / 1M: 86,555
Input / 1M25,966Output / 1M86,555
Granite 4.2 8B
ibm-granite/granite-4.2-8b131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 20,773
Output / 1M: 86,555
Input / 1M20,773Output / 1M86,555
Hy-MT2-1.8B
tencent/hy-mt2-1.8b8,192 ctx
Context: 8,192
Input / 1M: 15,234
Output / 1M: 61,281
Input / 1M15,234Output / 1M61,281
Hy-MT2-30B-A3B
tencent/hy-mt2-30b-a3b8,192 ctxJSON output
Context: 8,192
Input / 1M: 25,620
Output / 1M: 102,135
Input / 1M25,620Output / 1M102,135
Hy-MT2-7B
tencent/hy-mt2-7b8,192 ctxJSON output
Context: 8,192
Input / 1M: 25,620
Output / 1M: 102,135
Input / 1M25,620Output / 1M102,135
Dots3-Note PreviewFree
dots-studio/dots-3-note-preview:free512,000 ctxReasoningTool callingImage input
Context: 512,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Seed 2.1 Turbo
bytedance-seed/seed-2-1-turbo262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 173,110
Output / 1M: 865,548
Input / 1M173,110Output / 1M865,548
Seed-2.0-Code
bytedance-seed/seed-2.0-code262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 173,110
Output / 1M: 1,038,658
Input / 1M173,110Output / 1M1,038,658
LFM2.5-2.6BFree
liquid/lfm-2.5-2.6b:free65,536 ctxReasoningTool callingJSON output
Context: 65,536
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightning262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 24,235
Output / 1M: 69,244
Input / 1M24,235Output / 1M69,244
Solar Pro 4
upstage/solar-pro4524,288 ctxReasoningTool callingJSON output
Context: 524,288
Input / 1M: 51,933
Output / 1M: 207,732
Input / 1M51,933Output / 1M207,732
Ling 3.0 Tiny
inclusionai/ling-3.0-tiny262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 5,193
Output / 1M: 15,580
Input / 1M5,193Output / 1M15,580
Inkling Small
thinkingmachines/inkling-small524,288 ctxReasoningTool callingImage input
Context: 524,288
Input / 1M: 155,799
Output / 1M: 415,463
Input / 1M155,799Output / 1M415,463
Ling 3.0 Flash
inclusionai/ling-3.0-flash262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 7,271
Output / 1M: 21,812
Input / 1M7,271Output / 1M21,812
LongCat 2.0
meituan/longcat-2.01,048,756 ctxReasoningTool calling
Context: 1,048,756
Input / 1M: 103,866
Output / 1M: 415,463
Input / 1M103,866Output / 1M415,463
Inkling
thinkingmachines/inkling524,288 ctxReasoningTool callingImage input
Context: 524,288
Input / 1M: 346,219
Output / 1M: 1,402,188
Input / 1M346,219Output / 1M1,402,188
Aion-3.0-Mini
aion-labs/aion-3.0-mini131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 242,354
Output / 1M: 484,707
Input / 1M242,354Output / 1M484,707
Aion-3.0
aion-labs/aion-3.0131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 1,038,658
Output / 1M: 2,077,316
Input / 1M1,038,658Output / 1M2,077,316
Hy3
tencent/hy3262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 45,701
Output / 1M: 182,804
Input / 1M45,701Output / 1M182,804
Fugu Ultra
sakana/fugu-ultra1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,731,097
Output / 1M: 10,386,581
Input / 1M1,731,097Output / 1M10,386,581
North Mini CodeFree
cohere/north-mini-code:free256,000 ctxReasoningTool calling
Context: 256,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Nemotron 3.5 Content Safety
nvidia/nemotron-3.5-content-safety131,072 ctxReasoningImage input
Context: 131,072
Input / 1M: 69,244
Output / 1M: 69,244
Input / 1M69,244Output / 1M69,244
Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 207,732
Output / 1M: 830,926
Input / 1M207,732Output / 1M830,926
MiniMax M3
minimax/minimax-m31,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 103,866
Output / 1M: 415,463
Input / 1M103,866Output / 1M415,463
Step 3.7 Flash
stepfun/step-3.7-flash262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 69,244
Output / 1M: 398,152
Input / 1M69,244Output / 1M398,152
Perceptron Mk1
perceptron/perceptron-mk132,768 ctxReasoningImage inputJSON output
Context: 32,768
Input / 1M: 51,933
Output / 1M: 519,329
Input / 1M51,933Output / 1M519,329
Nemotron 3 Nano OmniFree
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free256,000 ctxReasoningTool callingImage input
Context: 256,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
MiMo-V2.5-Pro
xiaomi/mimo-v2.5-pro1,050,000 ctxReasoningTool callingJSON output
Context: 1,050,000
Input / 1M: 166,185
Output / 1M: 623,195
Input / 1M166,185Output / 1M623,195
MiMo-V2.5
xiaomi/mimo-v2.51,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 138,488
Output / 1M: 692,439
Input / 1M138,488Output / 1M692,439
Reka Edge
rekaai/reka-edge16,384 ctxTool callingImage inputJSON output
Context: 16,384
Input / 1M: 34,622
Output / 1M: 34,622
Input / 1M34,622Output / 1M34,622
MiniMax M2.7
minimax/minimax-m2.7204,800 ctxReasoningTool callingJSON output
Context: 204,800
Input / 1M: 103,866
Output / 1M: 415,463
Input / 1M103,866Output / 1M415,463
Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 103,866
Output / 1M: 830,926
Input / 1M103,866Output / 1M830,926
Seed-2.0-Lite
bytedance-seed/seed-2.0-lite262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 86,555
Output / 1M: 692,439
Input / 1M86,555Output / 1M692,439
Mercury 2
inception/mercury-2128,000 ctxReasoningTool callingJSON output
Context: 128,000
Input / 1M: 86,555
Output / 1M: 259,665
Input / 1M86,555Output / 1M259,665
Seed-2.0-Mini
bytedance-seed/seed-2.0-mini262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 34,622
Output / 1M: 138,488
Input / 1M34,622Output / 1M138,488
Aion-2.0
aion-labs/aion-2.0131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 276,975
Output / 1M: 553,951
Input / 1M276,975Output / 1M553,951
MiniMax M2.5
minimax/minimax-m2.5204,800 ctxReasoningTool callingJSON output
Context: 204,800
Input / 1M: 93,479
Output / 1M: 328,908
Input / 1M93,479Output / 1M328,908
Step 3.5 Flash
stepfun/step-3.5-flash262,144 ctxReasoningTool calling
Context: 262,144
Input / 1M: 34,622
Output / 1M: 103,866
Input / 1M34,622Output / 1M103,866
MiniMax M2-her
minimax/minimax-m2-her65,536 ctx
Context: 65,536
Input / 1M: 103,866
Output / 1M: 415,463
Input / 1M103,866Output / 1M415,463
Palmyra X5
writer/palmyra-x51,040,000 ctx
Context: 1,040,000
Input / 1M: 207,732
Output / 1M: 2,077,316
Input / 1M207,732Output / 1M2,077,316
Seed 1.6 Flash
bytedance-seed/seed-1.6-flash262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 25,966
Output / 1M: 103,866
Input / 1M25,966Output / 1M103,866
Seed 1.6
bytedance-seed/seed-1.6262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 86,555
Output / 1M: 692,439
Input / 1M86,555Output / 1M692,439
MiniMax M2.1
minimax/minimax-m2.1204,800 ctxReasoningTool callingJSON output
Context: 204,800
Input / 1M: 103,866
Output / 1M: 415,463
Input / 1M103,866Output / 1M415,463
Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b262,144 ctxReasoningTool callingJSON output
Context: 262,144
Input / 1M: 20,773
Output / 1M: 83,093
Input / 1M20,773Output / 1M83,093
Relace Search
relace/relace-search256,000 ctxTool callingJSON output
Context: 256,000
Input / 1M: 346,219
Output / 1M: 1,038,658
Input / 1M346,219Output / 1M1,038,658
Nova 2 Lite
amazon/nova-2-lite-v11,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 103,866
Output / 1M: 865,548
Input / 1M103,866Output / 1M865,548
Nova Premier 1.0
amazon/nova-premier-v11,000,000 ctxTool callingImage input
Context: 1,000,000
Input / 1M: 865,548
Output / 1M: 4,327,742
Input / 1M865,548Output / 1M4,327,742
Sonar Pro Search
perplexity/sonar-pro-search200,000 ctxReasoningImage inputJSON output
Context: 200,000
Input / 1M: 1,038,658
Output / 1M: 5,193,290
Input / 1M1,038,658Output / 1M5,193,290
MiniMax M2
minimax/minimax-m2204,800 ctxReasoningTool calling
Context: 204,800
Input / 1M: 88,286
Output / 1M: 353,144
Input / 1M88,286Output / 1M353,144
Cydonia 24B V4.1
thedrummer/cydonia-24b-v4.1131,072 ctxJSON output
Context: 131,072
Input / 1M: 103,866
Output / 1M: 173,110
Input / 1M103,866Output / 1M173,110
Relace Apply 3
relace/relace-apply-3256,000 ctx
Context: 256,000
Input / 1M: 294,286
Output / 1M: 432,774
Input / 1M294,286Output / 1M432,774
Hermes 4 405B
nousresearch/hermes-4-405b131,072 ctxReasoningJSON output
Context: 131,072
Input / 1M: 346,219
Output / 1M: 1,038,658
Input / 1M346,219Output / 1M1,038,658
UI-TARS 7B
bytedance/ui-tars-1.5-7b128,000 ctxImage inputJSON output
Context: 128,000
Input / 1M: 34,622
Output / 1M: 69,244
Input / 1M34,622Output / 1M69,244
Uncensored
cognitivecomputations/dolphin-mistral-24b-venice-edition128,000 ctxJSON output
Context: 128,000
Input / 1M: 69,244
Output / 1M: 311,597
Input / 1M69,244Output / 1M311,597
Hunyuan A13B Instruct
tencent/hunyuan-a13b-instruct131,072 ctxReasoningJSON output
Context: 131,072
Input / 1M: 48,471
Output / 1M: 197,345
Input / 1M48,471Output / 1M197,345
Morph V3 Large
morph/morph-v3-large262,144 ctxJSON output
Context: 262,144
Input / 1M: 311,597
Output / 1M: 657,817
Input / 1M311,597Output / 1M657,817
Morph V3 Fast
morph/morph-v3-fast262,144 ctxJSON output
Context: 262,144
Input / 1M: 276,975
Output / 1M: 415,463
Input / 1M276,975Output / 1M415,463
MiniMax M1
minimax/minimax-m11,000,000 ctxReasoningTool calling
Context: 1,000,000
Input / 1M: 190,421
Output / 1M: 761,683
Input / 1M190,421Output / 1M761,683
Command A
cohere/command-a256,000 ctxJSON output
Context: 256,000
Input / 1M: 865,548
Output / 1M: 3,462,194
Input / 1M865,548Output / 1M3,462,194
Reka Flash 3
rekaai/reka-flash-365,536 ctxReasoningJSON output
Context: 65,536
Input / 1M: 34,622
Output / 1M: 69,244
Input / 1M34,622Output / 1M69,244
Skyfall 36B V2
thedrummer/skyfall-36b-v232,768 ctxJSON output
Context: 32,768
Input / 1M: 190,421
Output / 1M: 276,975
Input / 1M190,421Output / 1M276,975
Sonar Reasoning Pro
perplexity/sonar-reasoning-pro128,000 ctxReasoningImage input
Context: 128,000
Input / 1M: 692,439
Output / 1M: 2,769,755
Input / 1M692,439Output / 1M2,769,755
Sonar Pro
perplexity/sonar-pro200,000 ctxImage input
Context: 200,000
Input / 1M: 1,038,658
Output / 1M: 5,193,290
Input / 1M1,038,658Output / 1M5,193,290
Sonar Deep Research
perplexity/sonar-deep-research128,000 ctxReasoning
Context: 128,000
Input / 1M: 692,439
Output / 1M: 2,769,755
Input / 1M692,439Output / 1M2,769,755
Aion-RP 1.0 (8B)
aion-labs/aion-rp-llama-3.1-8b32,768 ctx
Context: 32,768
Input / 1M: 276,975
Output / 1M: 553,951
Input / 1M276,975Output / 1M553,951
MiniMax-01
minimax/minimax-011,000,192 ctxImage input
Context: 1,000,192
Input / 1M: 69,244
Output / 1M: 380,841
Input / 1M69,244Output / 1M380,841
Phi 4
microsoft/phi-416,384 ctxJSON output
Context: 16,384
Input / 1M: 24,235
Output / 1M: 48,471
Input / 1M24,235Output / 1M48,471
Command R7B (12-2024)
cohere/command-r7b-12-2024128,000 ctxJSON output
Context: 128,000
Input / 1M: 12,983
Output / 1M: 51,933
Input / 1M12,983Output / 1M51,933
Nova Lite 1.0
amazon/nova-lite-v1300,000 ctxTool callingImage input
Context: 300,000
Input / 1M: 20,773
Output / 1M: 83,093
Input / 1M20,773Output / 1M83,093
Nova Micro 1.0
amazon/nova-micro-v1128,000 ctxTool calling
Context: 128,000
Input / 1M: 12,118
Output / 1M: 48,471
Input / 1M12,118Output / 1M48,471
Nova Pro 1.0
amazon/nova-pro-v1300,000 ctxTool callingImage input
Context: 300,000
Input / 1M: 276,975
Output / 1M: 1,107,902
Input / 1M276,975Output / 1M1,107,902
UnslopNemo 12B
thedrummer/unslopnemo-12b1,024,000 ctxJSON output
Context: 1,024,000
Input / 1M: 138,488
Output / 1M: 138,488
Input / 1M138,488Output / 1M138,488
Magnum v4 72B
anthracite-org/magnum-v4-72b32,768 ctxJSON output
Context: 32,768
Input / 1M: 865,548
Output / 1M: 1,731,097
Input / 1M865,548Output / 1M1,731,097
Command R (08-2024)
cohere/command-r-08-2024128,000 ctxTool callingJSON output
Context: 128,000
Input / 1M: 51,933
Output / 1M: 207,732
Input / 1M51,933Output / 1M207,732
Command R+ (08-2024)
cohere/command-r-plus-08-2024128,000 ctxTool callingJSON output
Context: 128,000
Input / 1M: 865,548
Output / 1M: 3,462,194
Input / 1M865,548Output / 1M3,462,194
Llama 3.1 Euryale 70B v2.2
sao10k/l3.1-euryale-70b131,072 ctxJSON output
Context: 131,072
Input / 1M: 294,286
Output / 1M: 294,286
Input / 1M294,286Output / 1M294,286
Llama 3 8B Lunaris
sao10k/l3-lunaris-8b8,192 ctxJSON output
Context: 8,192
Input / 1M: 13,849
Output / 1M: 17,311
Input / 1M13,849Output / 1M17,311
Weaver (alpha)
mancer/weaver8,000 ctxJSON output
Context: 8,000
Input / 1M: 138,488
Output / 1M: 259,665
Input / 1M138,488Output / 1M259,665
ReMM SLERP 13B
undi95/remm-slerp-l2-13b6,144 ctxJSON output
Context: 6,144
Input / 1M: 121,177
Output / 1M: 225,043
Input / 1M121,177Output / 1M225,043
MythoMax 13B
gryphe/mythomax-l2-13b8,192 ctxJSON output
Context: 8,192
Input / 1M: 27,698
Output / 1M: 38,084
Input / 1M27,698Output / 1M38,084
Text Embedding Ada 002
openai/text-embedding-ada-0028,192 ctxEmbeddings
Context: 8,192
Input / 1M: 34,622
Output / 1M: —
Input / 1M34,622Output / 1M—
Text Embedding 3 Large
openai/text-embedding-3-large8,192 ctxEmbeddings
Context: 8,192
Input / 1M: 45,009
Output / 1M: —
Input / 1M45,009Output / 1M—
Text Embedding 3 Small
openai/text-embedding-3-small8,192 ctxEmbeddings
Context: 8,192
Input / 1M: 6,924
Output / 1M: —
Input / 1M6,924Output / 1M—
Gemini Embedding 2
google/gemini-embedding-28,192 ctxImage inputAudio inputEmbeddings
Context: 8,192
Input / 1M: 69,244
Output / 1M: —
Input / 1M69,244Output / 1M—
Gemini Embedding 001
google/gemini-embedding-00120,000 ctxEmbeddings
Context: 20,000
Input / 1M: 51,933
Output / 1M: —
Input / 1M51,933Output / 1M—
Qwen3 Embedding 8B
qwen/qwen3-embedding-8b40,960 ctxEmbeddings
Context: 40,960
Input / 1M: 3,462
Output / 1M: —
Input / 1M3,462Output / 1M—
Qwen3 Embedding 4B
qwen/qwen3-embedding-4b32,768 ctxEmbeddings
Context: 32,768
Input / 1M: 6,924
Output / 1M: —
Input / 1M6,924Output / 1M—
Mistral Embed 2312
mistralai/mistral-embed-23128,192 ctxEmbeddings
Context: 8,192
Input / 1M: 34,622
Output / 1M: —
Input / 1M34,622Output / 1M—
Codestral Embed 2505
mistralai/codestral-embed-25058,192 ctxEmbeddings
Context: 8,192
Input / 1M: 51,933
Output / 1M: —
Input / 1M51,933Output / 1M—
Embed 5 Fast
cohere/embed-5-fast128,000 ctxImage inputEmbeddings
Context: 128,000
Input / 1M: 27,698
Output / 1M: —
Input / 1M27,698Output / 1M—
Embed 5 Pro
cohere/embed-5-pro128,000 ctxImage inputEmbeddings
Context: 128,000
Input / 1M: 41,546
Output / 1M: —
Input / 1M41,546Output / 1M—
Titan Multimodal Embeddings G1
amazon/titan-embed-image-v1128 ctxImage inputEmbeddings
Context: 128
Input / 1M: 276,975
Output / 1M: —
Input / 1M276,975Output / 1M—
Titan Embeddings G1 - Text
amazon/titan-embed-text-v18,192 ctxEmbeddings
Context: 8,192
Input / 1M: 34,622
Output / 1M: —
Input / 1M34,622Output / 1M—
Titan Text Embeddings V2
amazon/titan-embed-text-v28,192 ctxEmbeddings
Context: 8,192
Input / 1M: 6,924
Output / 1M: —
Input / 1M6,924Output / 1M—
Nemotron 3.5 Embed 1BFree
nvidia/nemotron-3.5-embed-1b:free32,768 ctxImage inputEmbeddings
Context: 32,768
Input / 1M: 0
Output / 1M: —
Input / 1M0Output / 1M—
Nemotron 3.5 Embed 8BFree
nvidia/nemotron-3.5-embed-8b:free32,768 ctxImage inputEmbeddings
Context: 32,768
Input / 1M: 0
Output / 1M: —
Input / 1M0Output / 1M—
LFM2.5-Embedding-350MFree
liquid/lfm-2.5-embedding-350m:free512 ctxEmbeddings
Context: 512
Input / 1M: 0
Output / 1M: —
Input / 1M0Output / 1M—
voyage-code-4
mongodb/voyage-code-432,000 ctxEmbeddings
Context: 32,000
Input / 1M: 41,546
Output / 1M: —
Input / 1M41,546Output / 1M—
voyage-multimodal-3.5
mongodb/voyage-multimodal-3.532,000 ctxImage inputEmbeddings
Context: 32,000
Input / 1M: 41,546
Output / 1M: —
Input / 1M41,546Output / 1M—
voyage-4-lite
mongodb/voyage-4-lite32,000 ctxEmbeddings
Context: 32,000
Input / 1M: 6,924
Output / 1M: —
Input / 1M6,924Output / 1M—
voyage-4
mongodb/voyage-432,000 ctxEmbeddings
Context: 32,000
Input / 1M: 20,773
Output / 1M: —
Input / 1M20,773Output / 1M—
voyage-4-large
mongodb/voyage-4-large32,000 ctxEmbeddings
Context: 32,000
Input / 1M: 41,546
Output / 1M: —
Input / 1M41,546Output / 1M—
Nemotron 3 Embed 1BFree
nvidia/nemotron-3-embed-1b:free32,768 ctxEmbeddings
Context: 32,768
Input / 1M: 0
Output / 1M: —
Input / 1M0Output / 1M—
Embed V1 4B
perplexity/pplx-embed-v1-4b32,000 ctxEmbeddings
Context: 32,000
Input / 1M: 10,387
Output / 1M: —
Input / 1M10,387Output / 1M—
Embed V1 0.6B
perplexity/pplx-embed-v1-0.6b32,000 ctxEmbeddings
Context: 32,000
Input / 1M: 1,385
Output / 1M: —
Input / 1M1,385Output / 1M—
Llama Nemotron Embed VL 1B V2Free
nvidia/llama-nemotron-embed-vl-1b-v2:free131,072 ctxImage inputEmbeddings
Context: 131,072
Input / 1M: 0
Output / 1M: —
Input / 1M0Output / 1M—
GTE-Base
thenlper/gte-base512 ctxEmbeddings
Context: 512
Input / 1M: 1,731
Output / 1M: —
Input / 1M1,731Output / 1M—
GTE-Large
thenlper/gte-large512 ctxEmbeddings
Context: 512
Input / 1M: 3,462
Output / 1M: —
Input / 1M3,462Output / 1M—
E5-Large-v2
intfloat/e5-large-v2512 ctxEmbeddings
Context: 512
Input / 1M: 3,462
Output / 1M: —
Input / 1M3,462Output / 1M—
E5-Base-v2
intfloat/e5-base-v2512 ctxEmbeddings
Context: 512
Input / 1M: 1,731
Output / 1M: —
Input / 1M1,731Output / 1M—
Multilingual-E5-Large
intfloat/multilingual-e5-large512 ctxEmbeddings
Context: 512
Input / 1M: 3,462
Output / 1M: —
Input / 1M3,462Output / 1M—
paraphrase-MiniLM-L6-v2
sentence-transformers/paraphrase-minilm-l6-v2512 ctxEmbeddings
Context: 512
Input / 1M: 1,731
Output / 1M: —
Input / 1M1,731Output / 1M—
all-MiniLM-L12-v2
sentence-transformers/all-minilm-l12-v2512 ctxEmbeddings
Context: 512
Input / 1M: 1,731
Output / 1M: —
Input / 1M1,731Output / 1M—
bge-base-en-v1.5
baai/bge-base-en-v1.5512 ctxEmbeddings
Context: 512
Input / 1M: 1,731
Output / 1M: —
Input / 1M1,731Output / 1M—
multi-qa-mpnet-base-dot-v1
sentence-transformers/multi-qa-mpnet-base-dot-v1512 ctxEmbeddings
Context: 512
Input / 1M: 1,731
Output / 1M: —
Input / 1M1,731Output / 1M—
bge-large-en-v1.5
baai/bge-large-en-v1.5512 ctxEmbeddings
Context: 512
Input / 1M: 3,462
Output / 1M: —
Input / 1M3,462Output / 1M—
bge-m3
baai/bge-m38,194 ctxEmbeddings
Context: 8,194
Input / 1M: 3,462
Output / 1M: —
Input / 1M3,462Output / 1M—
all-mpnet-base-v2
sentence-transformers/all-mpnet-base-v2512 ctxEmbeddings
Context: 512
Input / 1M: 1,731
Output / 1M: —
Input / 1M1,731Output / 1M—
all-MiniLM-L6-v2
sentence-transformers/all-minilm-l6-v2512 ctxEmbeddings
Context: 512
Input / 1M: 1,731
Output / 1M: —
Input / 1M1,731Output / 1M—
GPT-6.1 Terra ProBatch
openai/gpt-6.1-terra-pro:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 173,110
Output / 1M: 865,548
Input / 1M173,110Output / 1M865,548
GPT-6.1 TerraBatch
openai/gpt-6.1-terra:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 173,110
Output / 1M: 865,548
Input / 1M173,110Output / 1M865,548
GPT-6.1 Sol ProBatch
openai/gpt-6.1-sol-pro:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
GPT-6.1 SolBatch
openai/gpt-6.1-sol:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
GPT-6 Luna ProBatch
openai/gpt-6-luna-pro:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 17,311
Output / 1M: 86,555
Input / 1M17,311Output / 1M86,555
GPT-6 LunaBatch
openai/gpt-6-luna:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 17,311
Output / 1M: 86,555
Input / 1M17,311Output / 1M86,555
GPT-6 Sol ProBatch
openai/gpt-6-sol-pro:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
GPT-6 SolBatch
openai/gpt-6-sol:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
GPT AstraLatest
~openai/gpt-astra-latest1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 3,462,194
Output / 1M: 17,310,968
Input / 1M3,462,194Output / 1M17,310,968
GPT SolLatest
~openai/gpt-sol-latest1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
GPT TerraLatest
~openai/gpt-terra-latest1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
GPT LunaLatest
~openai/gpt-luna-latest1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 34,622
Output / 1M: 173,110
Input / 1M34,622Output / 1M173,110
GPT-6 AstraBatch
openai/gpt-6-astra:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 1,731,097
Output / 1M: 8,655,484
Input / 1M1,731,097Output / 1M8,655,484
GPT-6 Astra ProBatch
openai/gpt-6-astra-pro:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 1,731,097
Output / 1M: 8,655,484
Input / 1M1,731,097Output / 1M8,655,484
GPT-5.6 Luna ProBatch
openai/gpt-5.6-luna-pro:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 34,622
Output / 1M: 207,732
Input / 1M34,622Output / 1M207,732
GPT-5.6 LunaBatch
openai/gpt-5.6-luna:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 34,622
Output / 1M: 207,732
Input / 1M34,622Output / 1M207,732
GPT-5.6 Terra ProBatch
openai/gpt-5.6-terra-pro:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 346,219
Output / 1M: 2,077,316
Input / 1M346,219Output / 1M2,077,316
GPT-5.6 TerraBatch
openai/gpt-5.6-terra:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 346,219
Output / 1M: 2,077,316
Input / 1M346,219Output / 1M2,077,316
GPT-5.6 Sol ProBatch
openai/gpt-5.6-sol-pro:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
GPT-5.6 SolBatch
openai/gpt-5.6-sol:batch1,050,000 ctxReasoningTool callingImage input
Context: 1,050,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
GPT MiniLatest
~openai/gpt-mini-latest400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 259,665
Output / 1M: 1,557,987
Input / 1M259,665Output / 1M1,557,987
GPT-5 NanoBatch
openai/gpt-5-nano:batch400,000 ctxReasoningTool callingImage input
Context: 400,000
Input / 1M: 8,655
Output / 1M: 69,244
Input / 1M8,655Output / 1M69,244
gpt-oss-120bBatch
openai/gpt-oss-120b:batch131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 10,248
Output / 1M: 47,086
Input / 1M10,248Output / 1M47,086
gpt-oss-20bBatch
openai/gpt-oss-20b:batch131,072 ctxReasoningTool callingJSON output
Context: 131,072
Input / 1M: 8,309
Output / 1M: 38,777
Input / 1M8,309Output / 1M38,777
GPT-4o-mini (2024-07-18)
openai/gpt-4o-mini-2024-07-18128,000 ctxTool callingImage inputJSON output
Context: 128,000
Input / 1M: 51,933
Output / 1M: 207,732
Input / 1M51,933Output / 1M207,732
GPT-4o (2024-05-13)
openai/gpt-4o-2024-05-13128,000 ctxTool callingImage inputJSON output
Context: 128,000
Input / 1M: 1,731,097
Output / 1M: 5,193,290
Input / 1M1,731,097Output / 1M5,193,290
Claude Haiku 5.5Batch
anthropic/claude-haiku-5.5:batch1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 17,311
Output / 1M: 86,555
Input / 1M17,311Output / 1M86,555
Claude Sonnet 5.5Batch
anthropic/claude-sonnet-5.5:batch1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
Claude Opus 5.5Batch
anthropic/claude-opus-5.5:batch1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
Claude Fable 5.1Batch
anthropic/claude-fable-5.1:batch1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,731,097
Output / 1M: 8,655,484
Input / 1M1,731,097Output / 1M8,655,484
Claude Opus 5Batch
anthropic/claude-opus-5:batch1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 865,548
Output / 1M: 4,327,742
Input / 1M865,548Output / 1M4,327,742
Claude FableLatest
~anthropic/claude-fable-latest1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 3,462,194
Output / 1M: 17,310,968
Input / 1M3,462,194Output / 1M17,310,968
Claude HaikuLatest
~anthropic/claude-haiku-latest1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 34,622
Output / 1M: 173,110
Input / 1M34,622Output / 1M173,110
Claude SonnetLatest
~anthropic/claude-sonnet-latest1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
Claude OpusLatest
~anthropic/claude-opus-latest1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 1,384,877
Output / 1M: 6,924,387
Input / 1M1,384,877Output / 1M6,924,387
Gemini 4 ArgonBatch
google/gemini-4-argon:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 346,219
Output / 1M: 1,731,097
Input / 1M346,219Output / 1M1,731,097
Gemini 3.8 FlashBatch
google/gemini-3.8-flash:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 129,832
Output / 1M: 649,161
Input / 1M129,832Output / 1M649,161
Gemini 3.7 FlashBatch
google/gemini-3.7-flash:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 129,832
Output / 1M: 649,161
Input / 1M129,832Output / 1M649,161
Gemini 3.6 FlashBatch
google/gemini-3.6-flash:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 129,832
Output / 1M: 649,161
Input / 1M129,832Output / 1M649,161
Gemini 3.5 Flash LiteBatch
google/gemini-3.5-flash-lite:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 51,933
Output / 1M: 432,774
Input / 1M51,933Output / 1M432,774
Gemini 3.5 FlashBatch
google/gemini-3.5-flash:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 259,665
Output / 1M: 1,557,987
Input / 1M259,665Output / 1M1,557,987
Gemini 3.1 Flash LiteBatch
google/gemini-3.1-flash-lite:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 43,277
Output / 1M: 259,665
Input / 1M43,277Output / 1M259,665
Gemini ProLatest
~google/gemini-pro-latest1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 692,439
Output / 1M: 3,462,194
Input / 1M692,439Output / 1M3,462,194
Gemini FlashLatest
~google/gemini-flash-latest1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 259,665
Output / 1M: 1,298,323
Input / 1M259,665Output / 1M1,298,323
Gemini Embedding 2 Preview
google/gemini-embedding-2-preview8,192 ctxImage inputAudio inputEmbeddings
Context: 8,192
Input / 1M: 69,244
Output / 1M: —
Input / 1M69,244Output / 1M—
Gemma 4 26B A4BFree
google/gemma-4-26b-a4b-it:free262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Gemma 4 31BFree
google/gemma-4-31b-it:free262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Gemini 3.1 Flash Lite Preview
google/gemini-3.1-flash-lite-preview1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 86,555
Output / 1M: 519,329
Input / 1M86,555Output / 1M519,329
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
google/gemini-3.1-flash-image-preview65,536 ctxReasoningImage inputJSON output
Context: 65,536
Input / 1M: 173,110
Output / 1M: 1,038,658
Input / 1M173,110Output / 1M1,038,658
Gemini 3.1 Pro PreviewBatch
google/gemini-3.1-pro-preview:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 346,219
Output / 1M: 2,077,316
Input / 1M346,219Output / 1M2,077,316
Gemini 3 Flash PreviewBatch
google/gemini-3-flash-preview:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 86,555
Output / 1M: 519,329
Input / 1M86,555Output / 1M519,329
Nano Banana Pro (Gemini 3 Pro Image Preview)
google/gemini-3-pro-image-preview65,536 ctxReasoningImage inputJSON output
Context: 65,536
Input / 1M: 692,439
Output / 1M: 4,154,632
Input / 1M692,439Output / 1M4,154,632
Gemini 2.5 Pro Preview 06-05
google/gemini-2.5-pro-preview1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 432,774
Output / 1M: 3,462,194
Input / 1M432,774Output / 1M3,462,194
DeepSeek ProLatest
~deepseek/deepseek-pro-latest1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 32,095
Output / 1M: 2,769,755
Input / 1M32,095Output / 1M2,769,755
DeepSeek FlashLatest
~deepseek/deepseek-flash-latest1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 2,077
Output / 1M: 173,110
Input / 1M2,077Output / 1M173,110
DeepSeek V4.1 FlashBatch
deepseek/deepseek-v4.1-flash:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 38,777
Output / 1M: 116,330
Input / 1M38,777Output / 1M116,330
DeepSeek V4 FlashLatest
~deepseek/deepseek-v4-flash-latest1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 20,427
Output / 1M: 103,866
Input / 1M20,427Output / 1M103,866
Grok 4.7Batch
x-ai/grok-4.7:batch500,000 ctxReasoningTool callingImage input
Context: 500,000
Input / 1M: 553,951
Output / 1M: 1,661,853
Input / 1M553,951Output / 1M1,661,853
Grok 4.6Batch
x-ai/grok-4.6:batch500,000 ctxReasoningTool callingImage input
Context: 500,000
Input / 1M: 553,951
Output / 1M: 1,661,853
Input / 1M553,951Output / 1M1,661,853
GrokLatest
~x-ai/grok-latest500,000 ctxReasoningTool callingImage input
Context: 500,000
Input / 1M: 692,439
Output / 1M: 2,077,316
Input / 1M692,439Output / 1M2,077,316
Grok 4.3Batch
x-ai/grok-4.3:batch1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 346,219
Output / 1M: 692,439
Input / 1M346,219Output / 1M692,439
Qwen3.7 PlusBatch
qwen/qwen3.7-plus:batch262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 79,630
Output / 1M: 318,522
Input / 1M79,630Output / 1M318,522
Mistral Medium 3.5Batch
mistralai/mistral-medium-3-5:batch262,144 ctxReasoningTool callingImage input
Context: 262,144
Input / 1M: 259,665
Output / 1M: 1,298,323
Input / 1M259,665Output / 1M1,298,323
Kimi K3Batch
moonshotai/kimi-k3:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 789,380
Output / 1M: 3,946,901
Input / 1M789,380Output / 1M3,946,901
KimiLatest
~moonshotai/kimi-latest1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 53,595
Output / 1M: 3,233,273
Input / 1M53,595Output / 1M3,233,273
GLM FlashLatest
~z-ai/glm-flash-latest1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 9,867
Output / 1M: 31,956
Input / 1M9,867Output / 1M31,956
GLM 5.3 FlashBatch
z-ai/glm-5.3-flash:batch1,048,576 ctxReasoningTool callingImage input
Context: 1,048,576
Input / 1M: 17,311
Output / 1M: 62,319
Input / 1M17,311Output / 1M62,319
GLMLatest
~z-ai/glm-latest1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 24,201
Output / 1M: 484,707
Input / 1M24,201Output / 1M484,707
GLM 5.3Batch
z-ai/glm-5.3:batch1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 155,799
Output / 1M: 692,439
Input / 1M155,799Output / 1M692,439
Nemotron 3.5 Super VLFree
nvidia/nemotron-3.5-super-vl:free1,000,000 ctxReasoningTool callingImage input
Context: 1,000,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
ParetoLatest
~unbiased/pareto-latest1,048,576 ctxTool callingImage input
Context: 1,048,576
Input / 1M: 276,975
Output / 1M: 1,107,902
Input / 1M276,975Output / 1M1,107,902
Hy4 preview
tencent/hy4-preview1,048,576 ctxReasoningTool callingJSON output
Context: 1,048,576
Input / 1M: 288,747
Output / 1M: 865,895
Input / 1M288,747Output / 1M865,895
Nemotron 3.5 LightningFree
nvidia/nemotron-3.5-lightning:free1,000,000 ctxReasoningTool calling
Context: 1,000,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Nemotron 3.5 Content SafetyFree
nvidia/nemotron-3.5-content-safety:free128,000 ctxReasoningImage input
Context: 128,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Nemotron 3 UltraFree
nvidia/nemotron-3-ultra-550b-a55b:free1,000,000 ctxReasoningTool calling
Context: 1,000,000
Input / 1M: 0
Output / 1M: 0
Input / 1M0Output / 1M0
Hy3 preview
tencent/hy3-preview262,144 ctxReasoningTool calling
Context: 262,144
Input / 1M: 62,319
Output / 1M: 207,732
Input / 1M62,319Output / 1M207,732

Showing 40 of 453 models