GPU Network

Models

One branded OpenAI-compatible endpoint. Pricing shown per million tokens.

● live chain data
  • Atlas Flashfeatured● available
    Atlas · api/atlas-flash · 128K ctx · text, tools
    $0.15/M in
    $0.6/M out
    Run
  • Atlas Largefeatured● available
    Atlas · api/atlas-large · 200K ctx · text, tools, reasoning
    $3/M in
    $15/M out
    Run
  • Nova Minifeatured● available
    Nova · api/nova-mini · 64K ctx · text
    $0.05/M in
    $0.2/M out
    Run
  • Orion Coderfeatured● available
    Orion · api/orion-coder · 160K ctx · text, tools, code
    $1.2/M in
    $4.8/M out
    Run
  • Orion Reasonfeatured● available
    Orion · api/orion-reason · 256K ctx · text, reasoning
    $2.5/M in
    $12/M out
    Run
  • Vega Visionfeatured● available
    Vega · api/vega-vision · 128K ctx · text, vision
    $1/M in
    $4/M out
    Run
  • Aion 3.5● available
    GPU Network · aion-labs/aion-3.5 · 262K ctx · text
    $3/M in
    $6/M out
    Run
  • Aion 3.5 Mini● available
    GPU Network · aion-labs/aion-3.5-mini · 262K ctx · text
    $0.7/M in
    $1.4/M out
    Run
  • Aion-2.0● available
    GPU Network · aion-labs/aion-2.0 · 131K ctx · text
    $0.8/M in
    $1.6/M out
    Run
  • Aion-3.0● available
    GPU Network · aion-labs/aion-3.0 · 131K ctx · text
    $3/M in
    $6/M out
    Run
  • Aion-3.0-Mini● available
    GPU Network · aion-labs/aion-3.0-mini · 131K ctx · text
    $0.7/M in
    $1.4/M out
    Run
  • Aion-RP 1.0 (8B)● available
    GPU Network · aion-labs/aion-rp-llama-3.1-8b · 33K ctx · text
    $0.8/M in
    $1.6/M out
    Run
  • Auto Router● available
    GPU Network · openrouter/auto · 2000K ctx · text, vision, audio
    $0/M in
    $0/M out
    Run
  • Auto Router (Beta)● available
    GPU Network · openrouter/auto-beta · 2000K ctx · text, vision, audio
    $0/M in
    $0/M out
    Run
  • Beam 1.0 501B A23B● available
    GPU Network · reflection/beam-1.0-501b-a23b · 1049K ctx · text
    $0.25/M in
    $1/M out
    Run
  • Body Builder (beta)● available
    GPU Network · openrouter/bodybuilder · 128K ctx · text
    $0/M in
    $0/M out
    Run
  • Claude Fable 5● available
    GPU Network · anthropic/claude-fable-5 · 1000K ctx · text, vision
    $10/M in
    $50/M out
    Run
  • Claude Fable 5 (batch)● available
    GPU Network · anthropic/claude-fable-5:batch · 1000K ctx · text, vision
    $5/M in
    $25/M out
    Run
  • Claude Fable 5.1● available
    GPU Network · anthropic/claude-fable-5.1 · 1000K ctx · text, vision
    $10/M in
    $50/M out
    Run
  • Claude Fable 5.1 (batch)● available
    GPU Network · anthropic/claude-fable-5.1:batch · 1000K ctx · text, vision
    $5/M in
    $25/M out
    Run
  • Claude Fable Latest● available
    GPU Network · ~anthropic/claude-fable-latest · 1000K ctx · text, vision
    $10/M in
    $50/M out
    Run
  • Claude Haiku 4.5● available
    GPU Network · anthropic/claude-haiku-4.5 · 200K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • Claude Haiku 4.5 (batch)● available
    GPU Network · anthropic/claude-haiku-4.5:batch · 200K ctx · text, vision
    $0.5/M in
    $2.5/M out
    Run
  • Claude Haiku 5.5● available
    GPU Network · anthropic/claude-haiku-5.5 · 1000K ctx · text, vision
    $0.1/M in
    $0.5/M out
    Run
  • Claude Haiku 5.5 (batch)● available
    GPU Network · anthropic/claude-haiku-5.5:batch · 1000K ctx · text, vision
    $0.05/M in
    $0.25/M out
    Run
  • Claude Haiku Latest● available
    GPU Network · ~anthropic/claude-haiku-latest · 1000K ctx · text, vision
    $0.1/M in
    $0.5/M out
    Run
  • Claude Opus 4.1● available
    GPU Network · anthropic/claude-opus-4.1 · 200K ctx · text, vision
    $15/M in
    $75/M out
    Run
  • Claude Opus 4.1 (batch)● available
    GPU Network · anthropic/claude-opus-4.1:batch · 200K ctx · text, vision
    $7.5/M in
    $37.5/M out
    Run
  • Claude Opus 4.5● available
    GPU Network · anthropic/claude-opus-4.5 · 200K ctx · text, vision
    $5/M in
    $25/M out
    Run
  • Claude Opus 4.5 (batch)● available
    GPU Network · anthropic/claude-opus-4.5:batch · 200K ctx · text, vision
    $2.5/M in
    $12.5/M out
    Run
  • Claude Opus 4.6● available
    GPU Network · anthropic/claude-opus-4.6 · 1000K ctx · text, vision
    $5/M in
    $25/M out
    Run
  • Claude Opus 4.6 (batch)● available
    GPU Network · anthropic/claude-opus-4.6:batch · 1000K ctx · text, vision
    $2.5/M in
    $12.5/M out
    Run
  • Claude Opus 4.7● available
    GPU Network · anthropic/claude-opus-4.7 · 1000K ctx · text, vision
    $5/M in
    $25/M out
    Run
  • Claude Opus 4.7 (batch)● available
    GPU Network · anthropic/claude-opus-4.7:batch · 1000K ctx · text, vision
    $2.5/M in
    $12.5/M out
    Run
  • Claude Opus 4.8● available
    GPU Network · anthropic/claude-opus-4.8 · 1000K ctx · text, vision
    $5/M in
    $25/M out
    Run
  • Claude Opus 4.8 (batch)● available
    GPU Network · anthropic/claude-opus-4.8:batch · 1000K ctx · text, vision
    $2.5/M in
    $12.5/M out
    Run
  • Claude Opus 5● available
    GPU Network · anthropic/claude-opus-5 · 1000K ctx · text, vision
    $5/M in
    $25/M out
    Run
  • Claude Opus 5 (batch)● available
    GPU Network · anthropic/claude-opus-5:batch · 1000K ctx · text, vision
    $2.5/M in
    $12.5/M out
    Run
  • Claude Opus 5.5● available
    GPU Network · anthropic/claude-opus-5.5 · 1000K ctx · text, vision
    $4/M in
    $20/M out
    Run
  • Claude Opus 5.5 (batch)● available
    GPU Network · anthropic/claude-opus-5.5:batch · 1000K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • Claude Opus Latest● available
    GPU Network · ~anthropic/claude-opus-latest · 1000K ctx · text, vision
    $4/M in
    $20/M out
    Run
  • Claude Sonnet 4.5● available
    GPU Network · anthropic/claude-sonnet-4.5 · 1000K ctx · text, vision
    $3/M in
    $15/M out
    Run
  • Claude Sonnet 4.5 (batch)● available
    GPU Network · anthropic/claude-sonnet-4.5:batch · 1000K ctx · text, vision
    $1.5/M in
    $7.5/M out
    Run
  • Claude Sonnet 4.6● available
    GPU Network · anthropic/claude-sonnet-4.6 · 1000K ctx · text, vision
    $3/M in
    $15/M out
    Run
  • Claude Sonnet 4.6 (batch)● available
    GPU Network · anthropic/claude-sonnet-4.6:batch · 1000K ctx · text, vision
    $1.5/M in
    $7.5/M out
    Run
  • Claude Sonnet 5● available
    GPU Network · anthropic/claude-sonnet-5 · 1000K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • Claude Sonnet 5 (batch)● available
    GPU Network · anthropic/claude-sonnet-5:batch · 1000K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • Claude Sonnet 5.5● available
    GPU Network · anthropic/claude-sonnet-5.5 · 1000K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • Claude Sonnet 5.5 (batch)● available
    GPU Network · anthropic/claude-sonnet-5.5:batch · 1000K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • Claude Sonnet Latest● available
    GPU Network · ~anthropic/claude-sonnet-latest · 1000K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • Codestral 2508● available
    GPU Network · mistralai/codestral-2508 · 256K ctx · text
    $0.3/M in
    $0.9/M out
    Run
  • Command A● available
    GPU Network · cohere/command-a · 256K ctx · text
    $2.5/M in
    $10/M out
    Run
  • Command A+● available
    GPU Network · cohere/command-a-plus · 192K ctx · text, vision
    $0.3/M in
    $1.5/M out
    Run
  • Command R (08-2024)● available
    GPU Network · cohere/command-r-08-2024 · 128K ctx · text
    $0.15/M in
    $0.6/M out
    Run
  • Command R+ (08-2024)● available
    GPU Network · cohere/command-r-plus-08-2024 · 128K ctx · text
    $2.5/M in
    $10/M out
    Run
  • Command R7B (12-2024)● available
    GPU Network · cohere/command-r7b-12-2024 · 128K ctx · text
    $0.0375/M in
    $0.15/M out
    Run
  • Cydonia 24B V4.1● available
    GPU Network · thedrummer/cydonia-24b-v4.1 · 131K ctx · text
    $0.3/M in
    $0.5/M out
    Run
  • DeepSeek Flash Latest● available
    GPU Network · ~deepseek/deepseek-flash-latest · 1049K ctx · text, vision
    $0.022/M in
    $0.192/M out
    Run
  • DeepSeek Pro Latest● available
    GPU Network · ~deepseek/deepseek-pro-latest · 1049K ctx · text
    $0.1035/M in
    $4/M out
    Run
  • DeepSeek V3● available
    GPU Network · deepseek/deepseek-chat · 164K ctx · text
    $0.2574/M in
    $1.0287/M out
    Run
  • DeepSeek V3 0324● available
    GPU Network · deepseek/deepseek-chat-v3-0324 · 164K ctx · text
    $0.29/M in
    $1.14/M out
    Run
  • DeepSeek V3.1● available
    GPU Network · deepseek/deepseek-chat-v3.1 · 164K ctx · text
    $0.25/M in
    $0.95/M out
    Run
  • DeepSeek V3.1 Terminus● available
    GPU Network · deepseek/deepseek-v3.1-terminus · 164K ctx · text
    $0.27/M in
    $1/M out
    Run
  • DeepSeek V3.2● available
    GPU Network · deepseek/deepseek-v3.2 · 164K ctx · text
    $0.26/M in
    $0.38/M out
    Run
  • DeepSeek V3.2 Exp● available
    GPU Network · deepseek/deepseek-v3.2-exp · 164K ctx · text
    $0.27/M in
    $0.41/M out
    Run
  • DeepSeek V4 Flash 0423● available
    GPU Network · deepseek/deepseek-v4-flash · 1049K ctx · text
    $0.091/M in
    $0.182/M out
    Run
  • DeepSeek V4 Flash 0731● available
    GPU Network · deepseek/deepseek-v4-flash-0731 · 1049K ctx · text
    $0.119/M in
    $0.238/M out
    Run
  • DeepSeek V4 Flash Latest● available
    GPU Network · ~deepseek/deepseek-v4-flash-latest · 1049K ctx · text
    $0.0532/M in
    $0.1951/M out
    Run
  • DeepSeek V4 Flash Vision Exp● available
    GPU Network · deepseek/deepseek-v4-flash-vision-exp · 1049K ctx · text, vision
    $0.2156/M in
    $0.6468/M out
    Run
  • DeepSeek V4 Pro 0423● available
    GPU Network · deepseek/deepseek-v4-pro · 1049K ctx · text
    $1.6/M in
    $3.2/M out
    Run
  • DeepSeek V4 Pro 0813● available
    GPU Network · deepseek/deepseek-v4-pro-0813 · 1049K ctx · text
    $0.66/M in
    $1.98/M out
    Run
  • DeepSeek V4.1 Flash● available
    GPU Network · deepseek/deepseek-v4.1-flash · 1049K ctx · text, vision
    $0.045/M in
    $0.5/M out
    Run
  • DeepSeek V4.1 Flash (batch)● available
    GPU Network · deepseek/deepseek-v4.1-flash:batch · 1049K ctx · text, vision
    $0.05/M in
    $0.15/M out
    Run
  • DeepSeek V4.1 Flash 1017● available
    GPU Network · deepseek/deepseek-v4.1-flash-1017 · 1049K ctx · text, vision
    $0.15/M in
    $0.6/M out
    Run
  • Devstral 2 2512● available
    GPU Network · mistralai/devstral-2512 · 262K ctx · text
    $0.4/M in
    $2/M out
    Run
  • Dots3-Note Preview (free)● available
    GPU Network · dots-studio/dots-3-note-preview:free · 512K ctx · text, vision
    $0/M in
    $0/M out
    Run
  • Ember-1● available
    GPU Network · fireworks/ember-1 · 1049K ctx · text, vision
    $3/M in
    $15/M out
    Run
  • Extract● available
    GPU Network · scaledown/extract · 1000K ctx · text, vision
    $0.04/M in
    $0/M out
    Run
  • Flint (free)● available
    GPU Network · recursive/flint-v1.0:free · 262K ctx · text
    $0/M in
    $0/M out
    Run
  • Free Models Router● available
    GPU Network · openrouter/free · 200K ctx · text, vision
    $0/M in
    $0/M out
    Run
  • Fugu Max● available
    GPU Network · sakana/fugu-max · 1000K ctx · text, vision
    $2/M in
    $6/M out
    Run
  • Fugu Ultra● available
    GPU Network · sakana/fugu-ultra · 1000K ctx · text, vision
    $5/M in
    $30/M out
    Run
  • Fugu Ultra v2● available
    GPU Network · sakana/fugu-ultra-v2 · 1000K ctx · text, vision
    $5/M in
    $30/M out
    Run
  • Fusion● available
    GPU Network · openrouter/fusion · 1000K ctx · text
    $0/M in
    $0/M out
    Run
  • Gemini 2.5 Flash● available
    GPU Network · google/gemini-2.5-flash · 1049K ctx · text, vision, audio
    $0.3/M in
    $2.5/M out
    Run
  • Gemini 2.5 Flash Lite● available
    GPU Network · google/gemini-2.5-flash-lite · 1049K ctx · text, vision, audio
    $0.1/M in
    $0.4/M out
    Run
  • Gemini 2.5 Pro● available
    GPU Network · google/gemini-2.5-pro · 1049K ctx · text, vision, audio
    $1.25/M in
    $10/M out
    Run
  • Gemini 2.5 Pro Preview 06-05● available
    GPU Network · google/gemini-2.5-pro-preview · 1049K ctx · text, vision, audio
    $1.25/M in
    $10/M out
    Run
  • Gemini 3 Flash Preview● available
    GPU Network · google/gemini-3-flash-preview · 1049K ctx · text, vision, audio
    $0.5/M in
    $3/M out
    Run
  • Gemini 3 Flash Preview (batch)● available
    GPU Network · google/gemini-3-flash-preview:batch · 1049K ctx · text, vision, audio
    $0.25/M in
    $1.5/M out
    Run
  • Gemini 3.1 Flash Lite● available
    GPU Network · google/gemini-3.1-flash-lite · 1049K ctx · text, vision, audio
    $0.25/M in
    $1.5/M out
    Run
  • Gemini 3.1 Flash Lite (batch)● available
    GPU Network · google/gemini-3.1-flash-lite:batch · 1049K ctx · text, vision, audio
    $0.125/M in
    $0.75/M out
    Run
  • Gemini 3.1 Flash Lite Preview● available
    GPU Network · google/gemini-3.1-flash-lite-preview · 1049K ctx · text, vision, audio
    $0.25/M in
    $1.5/M out
    Run
  • Gemini 3.1 Pro Preview● available
    GPU Network · google/gemini-3.1-pro-preview · 1049K ctx · text, vision, audio
    $2/M in
    $12/M out
    Run
  • Gemini 3.1 Pro Preview (batch)● available
    GPU Network · google/gemini-3.1-pro-preview:batch · 1049K ctx · text, vision, audio
    $1/M in
    $6/M out
    Run
  • Gemini 3.1 Pro Preview Custom Tools● available
    GPU Network · google/gemini-3.1-pro-preview-customtools · 1049K ctx · text, vision, audio
    $2/M in
    $12/M out
    Run
  • Gemini 3.5 Flash● available
    GPU Network · google/gemini-3.5-flash · 1049K ctx · text, vision, audio
    $1.5/M in
    $9/M out
    Run
  • Gemini 3.5 Flash (batch)● available
    GPU Network · google/gemini-3.5-flash:batch · 1049K ctx · text, vision, audio
    $0.75/M in
    $4.5/M out
    Run
  • Gemini 3.5 Flash Lite● available
    GPU Network · google/gemini-3.5-flash-lite · 1049K ctx · text, vision, audio
    $0.3/M in
    $2.5/M out
    Run
  • Gemini 3.5 Flash Lite (batch)● available
    GPU Network · google/gemini-3.5-flash-lite:batch · 1049K ctx · text, vision, audio
    $0.15/M in
    $1.25/M out
    Run
  • Gemini 3.6 Flash● available
    GPU Network · google/gemini-3.6-flash · 1049K ctx · text, vision, audio
    $0.75/M in
    $3.75/M out
    Run
  • Gemini 3.6 Flash (batch)● available
    GPU Network · google/gemini-3.6-flash:batch · 1049K ctx · text, vision, audio
    $0.375/M in
    $1.875/M out
    Run
  • Gemini 3.7 Flash● available
    GPU Network · google/gemini-3.7-flash · 1049K ctx · text, vision, audio
    $0.75/M in
    $3.75/M out
    Run
  • Gemini 3.7 Flash (batch)● available
    GPU Network · google/gemini-3.7-flash:batch · 1049K ctx · text, vision, audio
    $0.375/M in
    $1.875/M out
    Run
  • Gemini 3.8 Flash● available
    GPU Network · google/gemini-3.8-flash · 1049K ctx · text, vision, audio
    $0.825/M in
    $4.125/M out
    Run
  • Gemini 3.8 Flash (batch)● available
    GPU Network · google/gemini-3.8-flash:batch · 1049K ctx · text, vision, audio
    $0.375/M in
    $1.875/M out
    Run
  • Gemini 4 Argon● available
    GPU Network · google/gemini-4-argon · 1049K ctx · text, vision, audio
    $2/M in
    $10/M out
    Run
  • Gemini 4 Argon (batch)● available
    GPU Network · google/gemini-4-argon:batch · 1049K ctx · text, vision, audio
    $1/M in
    $5/M out
    Run
  • Gemini Flash Latest● available
    GPU Network · ~google/gemini-flash-latest · 1049K ctx · text, vision, audio
    $0.75/M in
    $3.75/M out
    Run
  • Gemini Pro Latest● available
    GPU Network · ~google/gemini-pro-latest · 1049K ctx · text, vision, audio
    $2/M in
    $10/M out
    Run
  • Gemma 2 27B● available
    GPU Network · google/gemma-2-27b-it · 8K ctx · text
    $0.65/M in
    $0.65/M out
    Run
  • Gemma 3 12B● available
    GPU Network · google/gemma-3-12b-it · 131K ctx · text, vision
    $0.05/M in
    $0.15/M out
    Run
  • Gemma 3 27B● available
    GPU Network · google/gemma-3-27b-it · 131K ctx · text, vision
    $0.08/M in
    $0.35/M out
    Run
  • Gemma 3 4B● available
    GPU Network · google/gemma-3-4b-it · 131K ctx · text, vision
    $0.05/M in
    $0.1/M out
    Run
  • Gemma 4 26B A4B● available
    GPU Network · google/gemma-4-26b-a4b-it · 262K ctx · text, vision
    $0.0675/M in
    $0.225/M out
    Run
  • Gemma 4 26B A4B (free)● available
    GPU Network · google/gemma-4-26b-a4b-it:free · 262K ctx · text, vision
    $0/M in
    $0/M out
    Run
  • Gemma 4 31B● available
    GPU Network · google/gemma-4-31b-it · 262K ctx · text, vision
    $0.2/M in
    $0.4/M out
    Run
  • Gemma 4 31B (free)● available
    GPU Network · google/gemma-4-31b-it:free · 262K ctx · text, vision
    $0/M in
    $0/M out
    Run
  • Glimpse● available
    GPU Network · elorian/glimpse · 262K ctx · text, vision
    $0.6/M in
    $3/M out
    Run
  • GLM 4.5● available
    GPU Network · z-ai/glm-4.5 · 131K ctx · text
    $0.6/M in
    $2.2/M out
    Run
  • GLM 4.5 Air● available
    GPU Network · z-ai/glm-4.5-air · 131K ctx · text
    $0.13/M in
    $0.85/M out
    Run
  • GLM 4.5V● available
    GPU Network · z-ai/glm-4.5v · 66K ctx · text, vision
    $0.6/M in
    $1.8/M out
    Run
  • GLM 4.6● available
    GPU Network · z-ai/glm-4.6 · 205K ctx · text
    $0.5/M in
    $2/M out
    Run
  • GLM 4.6V● available
    GPU Network · z-ai/glm-4.6v · 131K ctx · text, vision
    $0.3/M in
    $0.9/M out
    Run
  • GLM 4.7● available
    GPU Network · z-ai/glm-4.7 · 205K ctx · text
    $0.54/M in
    $1.98/M out
    Run
  • GLM 4.7 Flash● available
    GPU Network · z-ai/glm-4.7-flash · 200K ctx · text
    $0.0605/M in
    $0.4/M out
    Run
  • GLM 5● available
    GPU Network · z-ai/glm-5 · 205K ctx · text
    $1/M in
    $3.2/M out
    Run
  • GLM 5 Turbo● available
    GPU Network · z-ai/glm-5-turbo · 203K ctx · text
    $1.2/M in
    $4/M out
    Run
  • GLM 5.1● available
    GPU Network · z-ai/glm-5.1 · 205K ctx · text
    $1.4/M in
    $4.4/M out
    Run
  • GLM 5.2● available
    GPU Network · z-ai/glm-5.2 · 1049K ctx · text
    $0.006/M in
    $7/M out
    Run
  • GLM 5.3● available
    GPU Network · z-ai/glm-5.3 · 1049K ctx · text
    $0.0699/M in
    $1.4/M out
    Run
  • GLM 5.3 (batch)● available
    GPU Network · z-ai/glm-5.3:batch · 1049K ctx · text
    $0.45/M in
    $2/M out
    Run
  • GLM 5.3 Flash● available
    GPU Network · z-ai/glm-5.3-flash · 1049K ctx · text, vision
    $0.0216/M in
    $0.1238/M out
    Run
  • GLM 5.3 Flash (batch)● available
    GPU Network · z-ai/glm-5.3-flash:batch · 1049K ctx · text, vision
    $0.05/M in
    $0.18/M out
    Run
  • GLM 5.3 FlashX● available
    GPU Network · z-ai/glm-5.3-flashx · 1049K ctx · text, vision
    $0.37/M in
    $1.25/M out
    Run
  • GLM 5.3 Prime● available
    GPU Network · z-ai/glm-5.3-prime · 1000K ctx · text
    $2.8/M in
    $8.8/M out
    Run
  • GLM 5V Turbo● available
    GPU Network · z-ai/glm-5v-turbo · 203K ctx · text, vision
    $1.2/M in
    $4/M out
    Run
  • GLM Flash Latest● available
    GPU Network · ~z-ai/glm-flash-latest · 1049K ctx · text, vision
    $0.0216/M in
    $0.1238/M out
    Run
  • GLM Latest● available
    GPU Network · ~z-ai/glm-latest · 1049K ctx · text
    $0.0699/M in
    $1.4/M out
    Run
  • GPT Astra Latest● available
    GPU Network · ~openai/gpt-astra-latest · 1050K ctx · text, vision
    $10/M in
    $50/M out
    Run
  • GPT Audio● available
    GPU Network · openai/gpt-audio · 128K ctx · text, audio
    $2.5/M in
    $10/M out
    Run
  • GPT Audio Mini● available
    GPU Network · openai/gpt-audio-mini · 128K ctx · text, audio
    $0.6/M in
    $2.4/M out
    Run
  • GPT Chat Latest● available
    GPU Network · openai/gpt-chat-latest · 400K ctx · text, vision
    $5/M in
    $30/M out
    Run
  • GPT Luna Latest● available
    GPU Network · ~openai/gpt-luna-latest · 1050K ctx · text, vision
    $0.1/M in
    $0.5/M out
    Run
  • GPT Mini Latest● available
    GPU Network · ~openai/gpt-mini-latest · 400K ctx · text, vision
    $0.75/M in
    $4.5/M out
    Run
  • GPT Sol Latest● available
    GPU Network · ~openai/gpt-sol-latest · 1050K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • GPT Terra Latest● available
    GPU Network · ~openai/gpt-terra-latest · 1050K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • GPT-3.5 Turbo (older v0613)● available
    GPU Network · openai/gpt-3.5-turbo-0613 · 4K ctx · text
    $1/M in
    $2/M out
    Run
  • GPT-3.5 Turbo 16k● available
    GPU Network · openai/gpt-3.5-turbo-16k · 16K ctx · text
    $3/M in
    $4/M out
    Run
  • GPT-4● available
    GPU Network · openai/gpt-4 · 8K ctx · text
    $30/M in
    $60/M out
    Run
  • GPT-4 Turbo (batch)● available
    GPU Network · openai/gpt-4-turbo:batch · 128K ctx · text, vision
    $5/M in
    $15/M out
    Run
  • GPT-4.1● available
    GPU Network · openai/gpt-4.1 · 1048K ctx · text, vision
    $2/M in
    $8/M out
    Run
  • GPT-4.1 (batch)● available
    GPU Network · openai/gpt-4.1:batch · 1048K ctx · text, vision
    $1/M in
    $4/M out
    Run
  • GPT-4.1 Mini● available
    GPU Network · openai/gpt-4.1-mini · 1048K ctx · text, vision
    $0.4/M in
    $1.6/M out
    Run
  • GPT-4.1 Mini (batch)● available
    GPU Network · openai/gpt-4.1-mini:batch · 1048K ctx · text, vision
    $0.2/M in
    $0.8/M out
    Run
  • GPT-4.1 Nano● available
    GPU Network · openai/gpt-4.1-nano · 1048K ctx · text, vision
    $0.1/M in
    $0.4/M out
    Run
  • GPT-4.1 Nano (batch)● available
    GPU Network · openai/gpt-4.1-nano:batch · 1048K ctx · text, vision
    $0.05/M in
    $0.2/M out
    Run
  • GPT-4o● available
    GPU Network · openai/gpt-4o · 128K ctx · text, vision
    $2.5/M in
    $10/M out
    Run
  • GPT-4o (2024-05-13)● available
    GPU Network · openai/gpt-4o-2024-05-13 · 128K ctx · text, vision
    $5/M in
    $15/M out
    Run
  • GPT-4o (2024-08-06)● available
    GPU Network · openai/gpt-4o-2024-08-06 · 128K ctx · text, vision
    $2.5/M in
    $10/M out
    Run
  • GPT-4o (2024-11-20)● available
    GPU Network · openai/gpt-4o-2024-11-20 · 128K ctx · text, vision
    $2.5/M in
    $10/M out
    Run
  • GPT-4o (batch)● available
    GPU Network · openai/gpt-4o:batch · 128K ctx · text, vision
    $1.25/M in
    $5/M out
    Run
  • GPT-4o-mini● available
    GPU Network · openai/gpt-4o-mini · 128K ctx · text, vision
    $0.15/M in
    $0.6/M out
    Run
  • GPT-4o-mini (2024-07-18)● available
    GPU Network · openai/gpt-4o-mini-2024-07-18 · 128K ctx · text, vision
    $0.15/M in
    $0.6/M out
    Run
  • GPT-4o-mini (batch)● available
    GPU Network · openai/gpt-4o-mini:batch · 128K ctx · text, vision
    $0.075/M in
    $0.3/M out
    Run
  • GPT-5● available
    GPU Network · openai/gpt-5 · 400K ctx · text, vision
    $1.25/M in
    $10/M out
    Run
  • GPT-5 (batch)● available
    GPU Network · openai/gpt-5:batch · 400K ctx · text, vision
    $0.625/M in
    $5/M out
    Run
  • GPT-5 Image● available
    GPU Network · openai/gpt-5-image · 400K ctx · text, vision
    $10/M in
    $10/M out
    Run
  • GPT-5 Image Mini● available
    GPU Network · openai/gpt-5-image-mini · 400K ctx · text, vision
    $2.5/M in
    $2/M out
    Run
  • GPT-5 Mini● available
    GPU Network · openai/gpt-5-mini · 400K ctx · text, vision
    $0.25/M in
    $2/M out
    Run
  • GPT-5 Mini (batch)● available
    GPU Network · openai/gpt-5-mini:batch · 400K ctx · text, vision
    $0.125/M in
    $1/M out
    Run
  • GPT-5 Nano● available
    GPU Network · openai/gpt-5-nano · 400K ctx · text, vision
    $0.05/M in
    $0.4/M out
    Run
  • GPT-5 Nano (batch)● available
    GPU Network · openai/gpt-5-nano:batch · 400K ctx · text, vision
    $0.025/M in
    $0.2/M out
    Run
  • GPT-5 Pro● available
    GPU Network · openai/gpt-5-pro · 400K ctx · text, vision
    $15/M in
    $120/M out
    Run
  • GPT-5 Pro (batch)● available
    GPU Network · openai/gpt-5-pro:batch · 400K ctx · text, vision
    $7.5/M in
    $60/M out
    Run
  • GPT-5.1● available
    GPU Network · openai/gpt-5.1 · 400K ctx · text, vision
    $1.25/M in
    $10/M out
    Run
  • GPT-5.1 (batch)● available
    GPU Network · openai/gpt-5.1:batch · 400K ctx · text, vision
    $0.625/M in
    $5/M out
    Run
  • GPT-5.1-Codex● available
    GPU Network · openai/gpt-5.1-codex · 400K ctx · text, vision
    $1.25/M in
    $10/M out
    Run
  • GPT-5.1-Codex-Max● available
    GPU Network · openai/gpt-5.1-codex-max · 400K ctx · text, vision
    $1.25/M in
    $10/M out
    Run
  • GPT-5.1-Codex-Mini● available
    GPU Network · openai/gpt-5.1-codex-mini · 400K ctx · text, vision
    $0.25/M in
    $2/M out
    Run
  • GPT-5.2● available
    GPU Network · openai/gpt-5.2 · 400K ctx · text, vision
    $1.75/M in
    $14/M out
    Run
  • GPT-5.2 (batch)● available
    GPU Network · openai/gpt-5.2:batch · 400K ctx · text, vision
    $0.875/M in
    $7/M out
    Run
  • GPT-5.2 Chat● available
    GPU Network · openai/gpt-5.2-chat · 128K ctx · text, vision
    $1.75/M in
    $14/M out
    Run
  • GPT-5.2 Pro● available
    GPU Network · openai/gpt-5.2-pro · 400K ctx · text, vision
    $21/M in
    $168/M out
    Run
  • GPT-5.2 Pro (batch)● available
    GPU Network · openai/gpt-5.2-pro:batch · 400K ctx · text, vision
    $10.5/M in
    $84/M out
    Run
  • GPT-5.2-Codex● available
    GPU Network · openai/gpt-5.2-codex · 400K ctx · text, vision
    $1.75/M in
    $14/M out
    Run
  • GPT-5.3-Codex● available
    GPU Network · openai/gpt-5.3-codex · 400K ctx · text, vision
    $1.75/M in
    $14/M out
    Run
  • GPT-5.4● available
    GPU Network · openai/gpt-5.4 · 1050K ctx · text, vision
    $2.5/M in
    $15/M out
    Run
  • GPT-5.4 (batch)● available
    GPU Network · openai/gpt-5.4:batch · 1050K ctx · text, vision
    $1.25/M in
    $7.5/M out
    Run
  • GPT-5.4 Image 2● available
    GPU Network · openai/gpt-5.4-image-2 · 272K ctx · text, vision
    $8/M in
    $15/M out
    Run
  • GPT-5.4 Mini● available
    GPU Network · openai/gpt-5.4-mini · 400K ctx · text, vision
    $0.75/M in
    $4.5/M out
    Run
  • GPT-5.4 Mini (batch)● available
    GPU Network · openai/gpt-5.4-mini:batch · 400K ctx · text, vision
    $0.375/M in
    $2.25/M out
    Run
  • GPT-5.4 Nano● available
    GPU Network · openai/gpt-5.4-nano · 400K ctx · text, vision
    $0.2/M in
    $1.25/M out
    Run
  • GPT-5.4 Nano (batch)● available
    GPU Network · openai/gpt-5.4-nano:batch · 400K ctx · text, vision
    $0.1/M in
    $0.625/M out
    Run
  • GPT-5.4 Pro● available
    GPU Network · openai/gpt-5.4-pro · 1050K ctx · text, vision
    $30/M in
    $180/M out
    Run
  • GPT-5.4 Pro (batch)● available
    GPU Network · openai/gpt-5.4-pro:batch · 1050K ctx · text, vision
    $15/M in
    $90/M out
    Run
  • GPT-5.5● available
    GPU Network · openai/gpt-5.5 · 1050K ctx · text, vision
    $5/M in
    $30/M out
    Run
  • GPT-5.5 (batch)● available
    GPU Network · openai/gpt-5.5:batch · 1050K ctx · text, vision
    $2.5/M in
    $15/M out
    Run
  • GPT-5.5 Pro● available
    GPU Network · openai/gpt-5.5-pro · 1050K ctx · text, vision
    $30/M in
    $180/M out
    Run
  • GPT-5.5 Pro (batch)● available
    GPU Network · openai/gpt-5.5-pro:batch · 1050K ctx · text, vision
    $15/M in
    $90/M out
    Run
  • GPT-5.6 Luna● available
    GPU Network · openai/gpt-5.6-luna · 1050K ctx · text, vision
    $0.2/M in
    $1.2/M out
    Run
  • GPT-5.6 Luna (batch)● available
    GPU Network · openai/gpt-5.6-luna:batch · 1050K ctx · text, vision
    $0.1/M in
    $0.6/M out
    Run
  • GPT-5.6 Luna Pro● available
    GPU Network · openai/gpt-5.6-luna-pro · 1050K ctx · text, vision
    $0.2/M in
    $1.2/M out
    Run
  • GPT-5.6 Luna Pro (batch)● available
    GPU Network · openai/gpt-5.6-luna-pro:batch · 1050K ctx · text, vision
    $0.1/M in
    $0.6/M out
    Run
  • GPT-5.6 Sol● available
    GPU Network · openai/gpt-5.6-sol · 1050K ctx · text, vision
    $4/M in
    $20/M out
    Run
  • GPT-5.6 Sol (batch)● available
    GPU Network · openai/gpt-5.6-sol:batch · 1050K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • GPT-5.6 Sol Pro● available
    GPU Network · openai/gpt-5.6-sol-pro · 1050K ctx · text, vision
    $4/M in
    $20/M out
    Run
  • GPT-5.6 Sol Pro (batch)● available
    GPU Network · openai/gpt-5.6-sol-pro:batch · 1050K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • GPT-5.6 Terra● available
    GPU Network · openai/gpt-5.6-terra · 1050K ctx · text, vision
    $2/M in
    $12/M out
    Run
  • GPT-5.6 Terra (batch)● available
    GPU Network · openai/gpt-5.6-terra:batch · 1050K ctx · text, vision
    $1/M in
    $6/M out
    Run
  • GPT-5.6 Terra Pro● available
    GPU Network · openai/gpt-5.6-terra-pro · 1050K ctx · text, vision
    $2/M in
    $12/M out
    Run
  • GPT-5.6 Terra Pro (batch)● available
    GPU Network · openai/gpt-5.6-terra-pro:batch · 1050K ctx · text, vision
    $1/M in
    $6/M out
    Run
  • GPT-6 Astra● available
    GPU Network · openai/gpt-6-astra · 1050K ctx · text, vision
    $10/M in
    $50/M out
    Run
  • GPT-6 Astra (batch)● available
    GPU Network · openai/gpt-6-astra:batch · 1050K ctx · text, vision
    $5/M in
    $25/M out
    Run
  • GPT-6 Astra Pro● available
    GPU Network · openai/gpt-6-astra-pro · 1050K ctx · text, vision
    $10/M in
    $50/M out
    Run
  • GPT-6 Astra Pro (batch)● available
    GPU Network · openai/gpt-6-astra-pro:batch · 1050K ctx · text, vision
    $5/M in
    $25/M out
    Run
  • GPT-6 Luna● available
    GPU Network · openai/gpt-6-luna · 1050K ctx · text, vision
    $0.1/M in
    $0.5/M out
    Run
  • GPT-6 Luna (batch)● available
    GPU Network · openai/gpt-6-luna:batch · 1050K ctx · text, vision
    $0.05/M in
    $0.25/M out
    Run
  • GPT-6 Luna Pro● available
    GPU Network · openai/gpt-6-luna-pro · 1050K ctx · text, vision
    $0.1/M in
    $0.5/M out
    Run
  • GPT-6 Luna Pro (batch)● available
    GPU Network · openai/gpt-6-luna-pro:batch · 1050K ctx · text, vision
    $0.05/M in
    $0.25/M out
    Run
  • GPT-6 Sol● available
    GPU Network · openai/gpt-6-sol · 1050K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • GPT-6 Sol (batch)● available
    GPU Network · openai/gpt-6-sol:batch · 1050K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • GPT-6 Sol Pro● available
    GPU Network · openai/gpt-6-sol-pro · 1050K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • GPT-6 Sol Pro (batch)● available
    GPU Network · openai/gpt-6-sol-pro:batch · 1050K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • GPT-6.1 Sol● available
    GPU Network · openai/gpt-6.1-sol · 1050K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • GPT-6.1 Sol (batch)● available
    GPU Network · openai/gpt-6.1-sol:batch · 1050K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • GPT-6.1 Sol Pro● available
    GPU Network · openai/gpt-6.1-sol-pro · 1050K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • GPT-6.1 Sol Pro (batch)● available
    GPU Network · openai/gpt-6.1-sol-pro:batch · 1050K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • GPT-6.1 Terra● available
    GPU Network · openai/gpt-6.1-terra · 1050K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • GPT-6.1 Terra (batch)● available
    GPU Network · openai/gpt-6.1-terra:batch · 1050K ctx · text, vision
    $0.5/M in
    $2.5/M out
    Run
  • GPT-6.1 Terra Pro● available
    GPU Network · openai/gpt-6.1-terra-pro · 1050K ctx · text, vision
    $1/M in
    $5/M out
    Run
  • GPT-6.1 Terra Pro (batch)● available
    GPU Network · openai/gpt-6.1-terra-pro:batch · 1050K ctx · text, vision
    $0.5/M in
    $2.5/M out
    Run
  • gpt-oss-120b● available
    GPU Network · openai/gpt-oss-120b · 131K ctx · text
    $0.15/M in
    $0.6/M out
    Run
  • gpt-oss-120b (batch)● available
    GPU Network · openai/gpt-oss-120b:batch · 131K ctx · text
    $0.0296/M in
    $0.136/M out
    Run
  • gpt-oss-20b● available
    GPU Network · openai/gpt-oss-20b · 131K ctx · text
    $0.018/M in
    $0.09/M out
    Run
  • gpt-oss-20b (batch)● available
    GPU Network · openai/gpt-oss-20b:batch · 131K ctx · text
    $0.024/M in
    $0.112/M out
    Run
  • gpt-oss-safeguard-20b● available
    GPU Network · openai/gpt-oss-safeguard-20b · 131K ctx · text
    $0.075/M in
    $0.3/M out
    Run
  • Granite 4.2 8B● available
    GPU Network · ibm-granite/granite-4.2-8b · 131K ctx · text
    $0.06/M in
    $0.15/M out
    Run
  • Grok 4.20● available
    GPU Network · x-ai/grok-4.20 · 2000K ctx · text, vision
    $1.25/M in
    $2.5/M out
    Run
  • Grok 4.20 Multi-Agent● available
    GPU Network · x-ai/grok-4.20-multi-agent · 2000K ctx · text, vision
    $1.25/M in
    $2.5/M out
    Run
  • Grok 4.3● available
    GPU Network · x-ai/grok-4.3 · 1000K ctx · text, vision
    $1.25/M in
    $2.5/M out
    Run
  • Grok 4.3 (batch)● available
    GPU Network · x-ai/grok-4.3:batch · 1000K ctx · text, vision
    $1/M in
    $2/M out
    Run
  • Grok 4.5● available
    GPU Network · x-ai/grok-4.5 · 500K ctx · text, vision
    $2/M in
    $6/M out
    Run
  • Grok 4.6● available
    GPU Network · x-ai/grok-4.6 · 500K ctx · text, vision
    $2/M in
    $6/M out
    Run
  • Grok 4.7● available
    GPU Network · x-ai/grok-4.7 · 500K ctx · text, vision
    $2/M in
    $6/M out
    Run
  • Grok Build 0.1● available
    GPU Network · x-ai/grok-build-0.1 · 256K ctx · text, vision
    $1/M in
    $2/M out
    Run
  • Grok Latest● available
    GPU Network · ~x-ai/grok-latest · 500K ctx · text, vision
    $2/M in
    $6/M out
    Run
  • Hermes 3 405B Instruct● available
    GPU Network · nousresearch/hermes-3-llama-3.1-405b · 131K ctx · text
    $1/M in
    $1/M out
    Run
  • Hermes 3 70B Instruct● available
    GPU Network · nousresearch/hermes-3-llama-3.1-70b · 131K ctx · text
    $0.7/M in
    $0.7/M out
    Run
  • Hermes 4 405B● available
    GPU Network · nousresearch/hermes-4-405b · 131K ctx · text
    $1/M in
    $3/M out
    Run
  • Hunyuan A13B Instruct● available
    GPU Network · tencent/hunyuan-a13b-instruct · 131K ctx · text
    $0.14/M in
    $0.57/M out
    Run
  • Hy-MT2-1.8B● available
    GPU Network · tencent/hy-mt2-1.8b · 8K ctx · text
    $0.044/M in
    $0.177/M out
    Run
  • Hy-MT2-30B-A3B● available
    GPU Network · tencent/hy-mt2-30b-a3b · 8K ctx · text
    $0.074/M in
    $0.295/M out
    Run
  • Hy-MT2-7B● available
    GPU Network · tencent/hy-mt2-7b · 8K ctx · text
    $0.074/M in
    $0.295/M out
    Run
  • Hy3● available
    GPU Network · tencent/hy3 · 262K ctx · text
    $0.132/M in
    $0.528/M out
    Run
  • Hy3 preview● available
    GPU Network · tencent/hy3-preview · 262K ctx · text
    $0.18/M in
    $0.6/M out
    Run
  • Hy4 preview● available
    GPU Network · tencent/hy4-preview · 1049K ctx · text
    $0.834/M in
    $2.501/M out
    Run
  • Inkling● available
    GPU Network · thinkingmachines/inkling · 524K ctx · text, vision, audio
    $1/M in
    $4.05/M out
    Run
  • Inkling (free)● available
    GPU Network · thinkingmachines/inkling:free · 1049K ctx · text, vision, audio
    $0/M in
    $0/M out
    Run
  • Inkling Small● available
    GPU Network · thinkingmachines/inkling-small · 524K ctx · text, vision, audio
    $0.45/M in
    $1.2/M out
    Run
  • Inkling Small (free)● available
    GPU Network · thinkingmachines/inkling-small:free · 1049K ctx · text, vision, audio
    $0/M in
    $0/M out
    Run
  • Jev Router● available
    GPU Network · typesafe/jev-router · 1000K ctx · text, vision, audio
    $0/M in
    $0/M out
    Run
  • Kimi K2 0711● available
    GPU Network · moonshotai/kimi-k2 · 131K ctx · text
    $0.57/M in
    $2.3/M out
    Run
  • Kimi K2 0905● available
    GPU Network · moonshotai/kimi-k2-0905 · 262K ctx · text
    $0.6/M in
    $2.5/M out
    Run
  • Kimi K2 Thinking● available
    GPU Network · moonshotai/kimi-k2-thinking · 262K ctx · text
    $0.6/M in
    $2.5/M out
    Run
  • Kimi K2.5● available
    GPU Network · moonshotai/kimi-k2.5 · 262K ctx · text, vision
    $0.5/M in
    $2.5/M out
    Run
  • Kimi K2.6● available
    GPU Network · moonshotai/kimi-k2.6 · 262K ctx · text, vision
    $0.65/M in
    $3.41/M out
    Run
  • Kimi K2.7 Code● available
    GPU Network · moonshotai/kimi-k2.7-code · 262K ctx · text, vision
    $0.6/M in
    $3.5/M out
    Run
  • Kimi K3● available
    GPU Network · moonshotai/kimi-k3 · 1049K ctx · text, vision
    $0.192/M in
    $15/M out
    Run
  • Kimi K3 (batch)● available
    GPU Network · moonshotai/kimi-k3:batch · 1049K ctx · text, vision
    $2.28/M in
    $11.4/M out
    Run
  • Kimi K3.1 Pro● available
    GPU Network · moonshotai/kimi-k3.1-pro · 1049K ctx · text, vision
    $2/M in
    $10/M out
    Run
  • Kimi Latest● available
    GPU Network · ~moonshotai/kimi-latest · 1049K ctx · text, vision
    $0.1529/M in
    $10.5572/M out
    Run
  • Laguna S 2.1● available
    GPU Network · poolside/laguna-s-2.1 · 1049K ctx · text
    $0.09/M in
    $0.18/M out
    Run
  • Laguna S 2.1 (free)● available
    GPU Network · poolside/laguna-s-2.1:free · 262K ctx · text
    $0/M in
    $0/M out
    Run
  • Laguna XS 2.1● available
    GPU Network · poolside/laguna-xs-2.1 · 262K ctx · text
    $0.06/M in
    $0.12/M out
    Run
  • Laguna XS 2.1 (free)● available
    GPU Network · poolside/laguna-xs-2.1:free · 262K ctx · text
    $0/M in
    $0/M out
    Run
  • LFM2.5-2.6B● available
    GPU Network · liquid/lfm-2.5-2.6b · 128K ctx · text
    $0.35/M in
    $0.5/M out
    Run
  • LFM2.5-2.6B (free)● available
    GPU Network · liquid/lfm-2.5-2.6b:free · 66K ctx · text
    $0/M in
    $0/M out
    Run
  • LFM2.5-24B-A2B● available
    GPU Network · liquid/lfm-2.5-24b-a2b · 128K ctx · text
    $0.05/M in
    $0.7/M out
    Run
  • Ling 3.0 Flash● available
    GPU Network · inclusionai/ling-3.0-flash · 262K ctx · text
    $0.021/M in
    $0.063/M out
    Run
  • Ling 3.0 Flash VL● available
    GPU Network · inclusionai/ling-3.0-flash-vl · 131K ctx · text, vision
    $0.06/M in
    $0.18/M out
    Run
  • Ling 3.1 Flash● available
    GPU Network · inclusionai/ling-3.1-flash · 1000K ctx · text
    $0.075/M in
    $0.225/M out
    Run
  • Llama 3 8B Lunaris● available
    GPU Network · sao10k/l3-lunaris-8b · 8K ctx · text
    $0.04/M in
    $0.05/M out
    Run
  • Llama 3.1 70B Instruct● available
    GPU Network · meta-llama/llama-3.1-70b-instruct · 131K ctx · text
    $0.4/M in
    $0.4/M out
    Run
  • Llama 3.1 8B Instruct● available
    GPU Network · meta-llama/llama-3.1-8b-instruct · 131K ctx · text
    $0.05/M in
    $0.08/M out
    Run
  • Llama 3.1 Euryale 70B v2.2● available
    GPU Network · sao10k/l3.1-euryale-70b · 131K ctx · text
    $0.85/M in
    $0.85/M out
    Run
  • Llama 3.2 1B Instruct● available
    GPU Network · meta-llama/llama-3.2-1b-instruct · 60K ctx · text
    $0.027/M in
    $0.201/M out
    Run
  • Llama 3.2 3B Instruct● available
    GPU Network · meta-llama/llama-3.2-3b-instruct · 131K ctx · text
    $0.05/M in
    $0.33/M out
    Run
  • Llama 3.3 70B Instruct● available
    GPU Network · meta-llama/llama-3.3-70b-instruct · 131K ctx · text
    $0.1/M in
    $0.32/M out
    Run
  • Llama 4 Maverick● available
    GPU Network · meta-llama/llama-4-maverick · 524K ctx · text, vision
    $0.1875/M in
    $0.6525/M out
    Run
  • Llama 4 Scout● available
    GPU Network · meta-llama/llama-4-scout · 1311K ctx · text, vision
    $0.1/M in
    $0.3/M out
    Run
  • Llama Guard 4 12B● available
    GPU Network · meta-llama/llama-guard-4-12b · 164K ctx · text, vision
    $0.18/M in
    $0.18/M out
    Run
  • LongCat 2.0● available
    GPU Network · meituan/longcat-2.0 · 1049K ctx · text
    $0.3/M in
    $1.2/M out
    Run
  • Lyria 3 Clip Preview● available
    GPU Network · google/lyria-3-clip-preview · 1049K ctx · text, vision, audio
    $0/M in
    $0/M out
    Run
  • Lyria 3 Pro Preview● available
    GPU Network · google/lyria-3-pro-preview · 1049K ctx · text, vision, audio
    $0/M in
    $0/M out
    Run
  • Magnum v4 72B● available
    GPU Network · anthracite-org/magnum-v4-72b · 33K ctx · text
    $2.5/M in
    $5/M out
    Run
  • Mercury 2● available
    GPU Network · inception/mercury-2 · 128K ctx · text
    $0.25/M in
    $0.75/M out
    Run
  • Mercury 2.5● available
    GPU Network · inception/mercury-2.5 · 260K ctx · text
    $0.04/M in
    $0.15/M out
    Run
  • Mercury 3● available
    GPU Network · inception/mercury-3 · 1000K ctx · text
    $0.1/M in
    $0.35/M out
    Run
  • MiMo-V2.5● available
    GPU Network · xiaomi/mimo-v2.5 · 1050K ctx · text, vision, audio
    $0.4/M in
    $2/M out
    Run
  • MiMo-V2.5-Pro● available
    GPU Network · xiaomi/mimo-v2.5-pro · 1050K ctx · text
    $0.48/M in
    $1.8/M out
    Run
  • MiMo-V2.6-Flash● available
    GPU Network · xiaomi/mimo-v2.6-flash · 1050K ctx · text, vision, audio
    $0.14/M in
    $0.28/M out
    Run
  • MiMo-V2.6-Pro● available
    GPU Network · xiaomi/mimo-v2.6-pro · 1050K ctx · text, vision, audio
    $0.435/M in
    $0.87/M out
    Run
  • MiMo-V2.6-Pro-UltraSpeed● available
    GPU Network · xiaomi/mimo-v2.6-pro-ultraspeed · 1049K ctx · text, vision, audio
    $4.35/M in
    $8.7/M out
    Run
  • MiniMax M1● available
    GPU Network · minimax/minimax-m1 · 1000K ctx · text
    $0.55/M in
    $2.2/M out
    Run
  • MiniMax M2● available
    GPU Network · minimax/minimax-m2 · 205K ctx · text
    $0.255/M in
    $1.02/M out
    Run
  • MiniMax M2-her● available
    GPU Network · minimax/minimax-m2-her · 66K ctx · text
    $0.3/M in
    $1.2/M out
    Run
  • MiniMax M2.1● available
    GPU Network · minimax/minimax-m2.1 · 205K ctx · text
    $0.3/M in
    $1.2/M out
    Run
  • MiniMax M2.5● available
    GPU Network · minimax/minimax-m2.5 · 205K ctx · text
    $0.27/M in
    $0.95/M out
    Run
  • MiniMax M2.7● available
    GPU Network · minimax/minimax-m2.7 · 205K ctx · text
    $0.3/M in
    $1.2/M out
    Run
  • MiniMax M3● available
    GPU Network · minimax/minimax-m3 · 1049K ctx · text, vision
    $0.3/M in
    $1.2/M out
    Run
  • MiniMax M3.1 Flash● available
    GPU Network · minimax/minimax-m3.1-flash · 1049K ctx · text, vision
    $0.075/M in
    $0.3/M out
    Run
  • MiniMax-01● available
    GPU Network · minimax/minimax-01 · 1000K ctx · text, vision
    $0.2/M in
    $1.1/M out
    Run
  • Ministral 3 14B 2512● available
    GPU Network · mistralai/ministral-14b-2512 · 262K ctx · text, vision
    $0.2/M in
    $0.2/M out
    Run
  • Ministral 3 3B 2512● available
    GPU Network · mistralai/ministral-3b-2512 · 131K ctx · text, vision
    $0.1/M in
    $0.1/M out
    Run
  • Ministral 3 8B 2512● available
    GPU Network · mistralai/ministral-8b-2512 · 262K ctx · text, vision
    $0.15/M in
    $0.15/M out
    Run
  • Mistral Large● available
    GPU Network · mistralai/mistral-large · 128K ctx · text
    $2/M in
    $6/M out
    Run
  • Mistral Large 2407● available
    GPU Network · mistralai/mistral-large-2407 · 131K ctx · text
    $2/M in
    $6/M out
    Run
  • Mistral Large 3 2512● available
    GPU Network · mistralai/mistral-large-2512 · 262K ctx · text, vision
    $0.5/M in
    $1.5/M out
    Run
  • Mistral Large 4● available
    GPU Network · mistralai/mistral-large-4-0 · 1049K ctx · text, vision
    $0.7/M in
    $2.1/M out
    Run
  • Mistral Medium 3● available
    GPU Network · mistralai/mistral-medium-3 · 131K ctx · text, vision
    $0.4/M in
    $2/M out
    Run
  • Mistral Medium 3.1● available
    GPU Network · mistralai/mistral-medium-3.1 · 131K ctx · text, vision
    $0.4/M in
    $2/M out
    Run
  • Mistral Medium 3.5● available
    GPU Network · mistralai/mistral-medium-3-5 · 262K ctx · text, vision
    $1.5/M in
    $7.5/M out
    Run
  • Mistral Medium 3.5 (batch)● available
    GPU Network · mistralai/mistral-medium-3-5:batch · 262K ctx · text, vision
    $0.75/M in
    $3.75/M out
    Run
  • Mistral Nemo● available
    GPU Network · mistralai/mistral-nemo · 131K ctx · text
    $0.029/M in
    $0.03/M out
    Run
  • Mistral Small 3● available
    GPU Network · mistralai/mistral-small-24b-instruct-2501 · 33K ctx · text
    $0.05/M in
    $0.08/M out
    Run
  • Mistral Small 3.1 24B● available
    GPU Network · mistralai/mistral-small-3.1-24b-instruct · 128K ctx · text, vision
    $0.351/M in
    $0.555/M out
    Run
  • Mistral Small 3.2 24B● available
    GPU Network · mistralai/mistral-small-3.2-24b-instruct · 256K ctx · text, vision
    $0.075/M in
    $0.2/M out
    Run
  • Mistral Small 4● available
    GPU Network · mistralai/mistral-small-2603 · 262K ctx · text, vision
    $0.15/M in
    $0.6/M out
    Run
  • Mixtral 8x22B Instruct● available
    GPU Network · mistralai/mixtral-8x22b-instruct · 66K ctx · text
    $2/M in
    $6/M out
    Run
  • Moondream 3 Preview● available
    GPU Network · moondream/moondream3-preview · 32K ctx · text, vision
    $0.3/M in
    $2.5/M out
    Run
  • Moondream 3.1● available
    GPU Network · moondream/moondream3.1-9b-a2b · 32K ctx · text, vision
    $0.3/M in
    $2.5/M out
    Run
  • Morph V3 Fast● available
    GPU Network · morph/morph-v3-fast · 262K ctx · text
    $0.8/M in
    $1.2/M out
    Run
  • Morph V3 Large● available
    GPU Network · morph/morph-v3-large · 262K ctx · text
    $0.9/M in
    $1.9/M out
    Run
  • Muse Glimmer 30B● available
    GPU Network · meta/muse-glimmer-30b · 131K ctx · text, vision
    $0.3/M in
    $1.2/M out
    Run
  • Muse Spark 1.1● available
    GPU Network · meta/muse-spark-1.1 · 1049K ctx · text, vision
    $1.25/M in
    $4.25/M out
    Run
  • Muse Spark 1.2● available
    GPU Network · meta/muse-spark-1.2 · 1049K ctx · text, vision
    $1.25/M in
    $4.25/M out
    Run
  • Muse Spark 1.2 Contributor● available
    GPU Network · meta/muse-spark-1.2-contributor · 1049K ctx · text, vision
    $0.1/M in
    $0.2/M out
    Run
  • Muse Spark 1.3● available
    GPU Network · meta/muse-spark-1.3 · 1049K ctx · text, vision
    $1.25/M in
    $4.25/M out
    Run
  • Muse Spark 1.3 Contributor● available
    GPU Network · meta/muse-spark-1.3-contributor · 1049K ctx · text, vision
    $0.1/M in
    $0.2/M out
    Run
  • Muse Spark Open● available
    GPU Network · meta/muse-spark-open · 1049K ctx · text, vision, audio
    $1.25/M in
    $4.25/M out
    Run
  • Muse Wonder● available
    GPU Network · meta/muse-wonder · 1049K ctx · text, vision, audio
    $4/M in
    $20/M out
    Run
  • MythoMax 13B● available
    GPU Network · gryphe/mythomax-l2-13b · 8K ctx · text
    $0.08/M in
    $0.11/M out
    Run
  • Nano Banana (Gemini 2.5 Flash Image)● available
    GPU Network · google/gemini-2.5-flash-image · 33K ctx · text, vision
    $0.3/M in
    $2.5/M out
    Run
  • Nano Banana 2 (Gemini 3.1 Flash Image Preview)● available
    GPU Network · google/gemini-3.1-flash-image-preview · 66K ctx · text, vision
    $0.5/M in
    $3/M out
    Run
  • Nano Banana 2 (Gemini 3.1 Flash Image)● available
    GPU Network · google/gemini-3.1-flash-image · 131K ctx · text, vision
    $0.5/M in
    $3/M out
    Run
  • Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)● available
    GPU Network · google/gemini-3.1-flash-lite-image · 66K ctx · text, vision
    $0.25/M in
    $1.5/M out
    Run
  • Nano Banana 2.1● available
    GPU Network · google/gemini-nano-banana-2.1 · 66K ctx · text, vision
    $1.5/M in
    $7.5/M out
    Run
  • Nano Banana Pro (Gemini 3 Pro Image Preview)● available
    GPU Network · google/gemini-3-pro-image-preview · 66K ctx · text, vision
    $2/M in
    $12/M out
    Run
  • Nano Banana Pro (Gemini 3 Pro Image)● available
    GPU Network · google/gemini-3-pro-image · 131K ctx · text, vision
    $2/M in
    $12/M out
    Run
  • Nemotron 3 Nano 30B A3B● available
    GPU Network · nvidia/nemotron-3-nano-30b-a3b · 262K ctx · text
    $0.06/M in
    $0.24/M out
    Run
  • Nemotron 3 Nano Omni (free)● available
    GPU Network · nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free · 256K ctx · text, vision, audio
    $0/M in
    $0/M out
    Run
  • Nemotron 3 Super● available
    GPU Network · nvidia/nemotron-3-super-120b-a12b · 1049K ctx · text
    $0.3/M in
    $2.4/M out
    Run
  • Nemotron 3 Ultra● available
    GPU Network · nvidia/nemotron-3-ultra-550b-a55b · 262K ctx · text
    $0.6/M in
    $2.4/M out
    Run
  • Nemotron 3 Ultra (free)● available
    GPU Network · nvidia/nemotron-3-ultra-550b-a55b:free · 1000K ctx · text
    $0/M in
    $0/M out
    Run
  • Nemotron 3.5 Content Safety● available
    GPU Network · nvidia/nemotron-3.5-content-safety · 131K ctx · text, vision
    $0.2/M in
    $0.2/M out
    Run
  • Nemotron 3.5 Content Safety (free)● available
    GPU Network · nvidia/nemotron-3.5-content-safety:free · 128K ctx · text, vision
    $0/M in
    $0/M out
    Run
  • Nemotron 3.5 Lightning● available
    GPU Network · nvidia/nemotron-3.5-lightning · 262K ctx · text
    $0.07/M in
    $0.2/M out
    Run
  • Nemotron 3.5 Lightning (free)● available
    GPU Network · nvidia/nemotron-3.5-lightning:free · 1000K ctx · text
    $0/M in
    $0/M out
    Run
  • Nemotron 3.5 Super VL● available
    GPU Network · nvidia/nemotron-3.5-super-vl · 1049K ctx · text, vision
    $0.15/M in
    $0.5/M out
    Run
  • Nemotron 3.5 Super VL (free)● available
    GPU Network · nvidia/nemotron-3.5-super-vl:free · 1000K ctx · text, vision
    $0/M in
    $0/M out
    Run
  • Nex-N2.5-Mini● available
    GPU Network · nex-agi/nex-n2.5-mini · 262K ctx · text, vision
    $0.025/M in
    $0.1/M out
    Run
  • Nex-N2.5-Pro● available
    GPU Network · nex-agi/nex-n2.5-pro · 262K ctx · text, vision
    $0.075/M in
    $0.25/M out
    Run
  • North Mini Code (free)● available
    GPU Network · cohere/north-mini-code:free · 256K ctx · text
    $0/M in
    $0/M out
    Run
  • Nova 2 Lite● available
    GPU Network · amazon/nova-2-lite-v1 · 1000K ctx · text, vision
    $0.3/M in
    $2.5/M out
    Run
  • Nova Lite 1.0● available
    GPU Network · amazon/nova-lite-v1 · 300K ctx · text, vision
    $0.06/M in
    $0.24/M out
    Run
  • Nova Micro 1.0● available
    GPU Network · amazon/nova-micro-v1 · 128K ctx · text
    $0.035/M in
    $0.14/M out
    Run
  • Nova Premier 1.0● available
    GPU Network · amazon/nova-premier-v1 · 1000K ctx · text, vision
    $2.5/M in
    $12.5/M out
    Run
  • Nova Pro 1.0● available
    GPU Network · amazon/nova-pro-v1 · 300K ctx · text, vision
    $0.8/M in
    $3.2/M out
    Run
  • o3● available
    GPU Network · openai/o3 · 200K ctx · text, vision
    $2/M in
    $8/M out
    Run
  • o3 (batch)● available
    GPU Network · openai/o3:batch · 200K ctx · text, vision
    $1/M in
    $4/M out
    Run
  • o3 Mini (batch)● available
    GPU Network · openai/o3-mini:batch · 200K ctx · text
    $0.55/M in
    $2.2/M out
    Run
  • o3 Pro● available
    GPU Network · openai/o3-pro · 200K ctx · text, vision
    $20/M in
    $80/M out
    Run
  • o4 Mini (batch)● available
    GPU Network · openai/o4-mini:batch · 200K ctx · text, vision
    $0.55/M in
    $2.2/M out
    Run
  • OpenWeight 70B● available
    Community · api/openweight-70b · 131K ctx · text, tools
    $0.35/M in
    $0.9/M out
    Run
  • OpenWeight 8B● available
    Community · api/openweight-8b · 66K ctx · text, tools
    $0.06/M in
    $0.12/M out
    Run
  • Palmyra X5● available
    GPU Network · writer/palmyra-x5 · 1040K ctx · text
    $0.6/M in
    $6/M out
    Run
  • Pareto 26.10● available
    GPU Network · unbiased/pareto-26.10 · 1049K ctx · text, vision
    $0.8/M in
    $3.2/M out
    Run
  • Pareto 26.9● available
    GPU Network · unbiased/pareto-26.9 · 262K ctx · text, vision
    $2.5/M in
    $7.5/M out
    Run
  • Pareto Code Router● available
    GPU Network · openrouter/pareto-code · 2000K ctx · text
    $0/M in
    $0/M out
    Run
  • Pareto Latest● available
    GPU Network · ~unbiased/pareto-latest · 1049K ctx · text, vision
    $0.8/M in
    $3.2/M out
    Run
  • Particle-1● available
    GPU Network · particle-ai/particle-1 · 1049K ctx · text, vision
    $0.05/M in
    $0.5/M out
    Run
  • Perceptron Mk1● available
    GPU Network · perceptron/perceptron-mk1 · 33K ctx · text, vision
    $0.15/M in
    $1.5/M out
    Run
  • Perceptron Mk1.5● available
    GPU Network · perceptron/perceptron-mk1.5 · 37K ctx · text, vision, audio
    $0.15/M in
    $1.5/M out
    Run
  • Phi 4● available
    GPU Network · microsoft/phi-4 · 16K ctx · text
    $0.07/M in
    $0.14/M out
    Run
  • Qwen-Plus● available
    GPU Network · qwen/qwen-plus · 1000K ctx · text
    $0.26/M in
    $0.78/M out
    Run
  • Qwen2.5 72B Instruct● available
    GPU Network · qwen/qwen-2.5-72b-instruct · 33K ctx · text
    $0.36/M in
    $0.4/M out
    Run
  • Qwen2.5 7B Instruct● available
    GPU Network · qwen/qwen-2.5-7b-instruct · 33K ctx · text
    $0.1/M in
    $0.2/M out
    Run
  • Qwen2.5 Coder 32B Instruct● available
    GPU Network · qwen/qwen-2.5-coder-32b-instruct · 33K ctx · text
    $0.66/M in
    $1/M out
    Run
  • Qwen2.5 VL 72B Instruct● available
    GPU Network · qwen/qwen2.5-vl-72b-instruct · 128K ctx · text, vision
    $0.8/M in
    $1/M out
    Run
  • Qwen3 14B● available
    GPU Network · qwen/qwen3-14b · 41K ctx · text
    $0.12/M in
    $0.24/M out
    Run
  • Qwen3 235B A22B Instruct 2507● available
    GPU Network · qwen/qwen3-235b-a22b-2507 · 262K ctx · text
    $0.09/M in
    $0.55/M out
    Run
  • Qwen3 235B A22B Thinking 2507● available
    GPU Network · qwen/qwen3-235b-a22b-thinking-2507 · 128K ctx · text
    $0.45/M in
    $3.5/M out
    Run
  • Qwen3 30B A3B● available
    GPU Network · qwen/qwen3-30b-a3b · 41K ctx · text
    $0.12/M in
    $0.5/M out
    Run
  • Qwen3 30B A3B Instruct 2507● available
    GPU Network · qwen/qwen3-30b-a3b-instruct-2507 · 262K ctx · text
    $0.1/M in
    $0.3/M out
    Run
  • Qwen3 32B● available
    GPU Network · qwen/qwen3-32b · 131K ctx · text
    $0.08/M in
    $0.28/M out
    Run
  • Qwen3 Coder 30B A3B Instruct● available
    GPU Network · qwen/qwen3-coder-30b-a3b-instruct · 262K ctx · text
    $0.07/M in
    $0.28/M out
    Run
  • Qwen3 Coder 480B A35B● available
    GPU Network · qwen/qwen3-coder · 262K ctx · text
    $0.3/M in
    $1/M out
    Run
  • Qwen3 Coder Flash● available
    GPU Network · qwen/qwen3-coder-flash · 1000K ctx · text
    $0.195/M in
    $0.975/M out
    Run
  • Qwen3 Coder Next● available
    GPU Network · qwen/qwen3-coder-next · 262K ctx · text
    $0.12/M in
    $0.8/M out
    Run
  • Qwen3 Next 80B A3B Instruct● available
    GPU Network · qwen/qwen3-next-80b-a3b-instruct · 262K ctx · text
    $0.09/M in
    $1.1/M out
    Run
  • Qwen3 VL 235B A22B Instruct● available
    GPU Network · qwen/qwen3-vl-235b-a22b-instruct · 262K ctx · text, vision
    $0.21/M in
    $1.9/M out
    Run
  • Qwen3 VL 30B A3B Instruct● available
    GPU Network · qwen/qwen3-vl-30b-a3b-instruct · 262K ctx · text, vision
    $0.15/M in
    $0.6/M out
    Run
  • Qwen3 VL 30B A3B Thinking● available
    GPU Network · qwen/qwen3-vl-30b-a3b-thinking · 262K ctx · text, vision
    $0.29/M in
    $1/M out
    Run
  • Qwen3 VL 8B Instruct● available
    GPU Network · qwen/qwen3-vl-8b-instruct · 262K ctx · text, vision
    $0.25/M in
    $0.75/M out
    Run
  • Qwen3.5 397B A17B● available
    GPU Network · qwen/qwen3.5-397b-a17b · 262K ctx · text, vision
    $0.5/M in
    $3.6/M out
    Run
  • Qwen3.5 Plus 2026-02-15● available
    GPU Network · qwen/qwen3.5-plus-02-15 · 1000K ctx · text, vision
    $0.26/M in
    $1.56/M out
    Run
  • Qwen3.5 Plus 2026-04-20● available
    GPU Network · qwen/qwen3.5-plus-20260420 · 1000K ctx · text, vision
    $0.3/M in
    $1.8/M out
    Run
  • Qwen3.5-122B-A10B● available
    GPU Network · qwen/qwen3.5-122b-a10b · 262K ctx · text, vision
    $0.26/M in
    $2.08/M out
    Run
  • Qwen3.5-27B● available
    GPU Network · qwen/qwen3.5-27b · 262K ctx · text, vision
    $0.26/M in
    $2.6/M out
    Run
  • Qwen3.5-35B-A3B● available
    GPU Network · qwen/qwen3.5-35b-a3b · 262K ctx · text, vision
    $0.14/M in
    $1/M out
    Run
  • Qwen3.5-9B● available
    GPU Network · qwen/qwen3.5-9b · 262K ctx · text, vision
    $0.17/M in
    $0.25/M out
    Run
  • Qwen3.5-Flash● available
    GPU Network · qwen/qwen3.5-flash-02-23 · 1000K ctx · text, vision
    $0.065/M in
    $0.26/M out
    Run
  • Qwen3.6 27B● available
    GPU Network · qwen/qwen3.6-27b · 262K ctx · text, vision
    $0.45/M in
    $2.7/M out
    Run
  • Qwen3.6 35B A3B● available
    GPU Network · qwen/qwen3.6-35b-a3b · 262K ctx · text, vision
    $0.1/M in
    $0.9/M out
    Run
  • Qwen3.6 Flash● available
    GPU Network · qwen/qwen3.6-flash · 1000K ctx · text, vision
    $0.1875/M in
    $1.125/M out
    Run
  • Qwen3.6 Plus● available
    GPU Network · qwen/qwen3.6-plus · 1000K ctx · text, vision
    $0.325/M in
    $1.95/M out
    Run
  • Qwen3.7 Flash● available
    GPU Network · qwen/qwen3.7-flash · 1000K ctx · text, vision
    $0.03/M in
    $0.13/M out
    Run
  • Qwen3.7 Max● available
    GPU Network · qwen/qwen3.7-max · 1000K ctx · text
    $1.475/M in
    $4.425/M out
    Run
  • Qwen3.7 Plus● available
    GPU Network · qwen/qwen3.7-plus · 1000K ctx · text, vision
    $0.32/M in
    $1.28/M out
    Run
  • Qwen3.7 Plus (batch)● available
    GPU Network · qwen/qwen3.7-plus:batch · 262K ctx · text, vision
    $0.23/M in
    $0.92/M out
    Run
  • Qwen3.8 2.4T A95B● available
    GPU Network · qwen/qwen3.8-2.4t-a95b · 1049K ctx · text
    $2/M in
    $6/M out
    Run
  • Qwen3.8 27B● available
    GPU Network · qwen/qwen3.8-27b · 1000K ctx · text, vision
    $0.15/M in
    $1.875/M out
    Run
  • Qwen3.8 Flash● available
    GPU Network · qwen/qwen3.8-flash · 1000K ctx · text, vision
    $0.15/M in
    $0.47/M out
    Run
  • Qwen3.8 Max (0902)● available
    GPU Network · qwen/qwen3.8-max-0902 · 1000K ctx · text, vision
    $2/M in
    $6/M out
    Run
  • Qwen3.8 Max Prime● available
    GPU Network · qwen/qwen3.8-max-prime · 1000K ctx · text, vision
    $4/M in
    $12/M out
    Run
  • Qwen3.8 Omni Flash● available
    GPU Network · qwen/qwen3.8-omni-flash · 1000K ctx · text, vision, audio
    $0.15/M in
    $0.47/M out
    Run
  • R1 0528● available
    GPU Network · deepseek/deepseek-r1-0528 · 164K ctx · text
    $0.5/M in
    $2.15/M out
    Run
  • Reka Edge● available
    GPU Network · rekaai/reka-edge · 16K ctx · text, vision
    $0.1/M in
    $0.1/M out
    Run
  • Reka Flash 3● available
    GPU Network · rekaai/reka-flash-3 · 66K ctx · text
    $0.1/M in
    $0.2/M out
    Run
  • Relace Apply 3● available
    GPU Network · relace/relace-apply-3 · 256K ctx · text
    $0.85/M in
    $1.25/M out
    Run
  • Relace Search● available
    GPU Network · relace/relace-search · 256K ctx · text
    $1/M in
    $3/M out
    Run
  • ReMM SLERP 13B● available
    GPU Network · undi95/remm-slerp-l2-13b · 6K ctx · text
    $0.35/M in
    $0.65/M out
    Run
  • Saba● available
    GPU Network · mistralai/mistral-saba · 33K ctx · text
    $0.2/M in
    $0.6/M out
    Run
  • Sakana Namazu● available
    GPU Network · sakana/sakana-namazu · 262K ctx · text, vision
    $0.95/M in
    $4/M out
    Run
  • Schematron V2 Small● available
    GPU Network · inference-net/schematron-v2-small · 128K ctx · text
    $0.05/M in
    $0.23/M out
    Run
  • Schematron V2 Turbo● available
    GPU Network · inference-net/schematron-v2-turbo · 128K ctx · text
    $0.03/M in
    $0.15/M out
    Run
  • Seed 1.6● available
    GPU Network · bytedance-seed/seed-1.6 · 262K ctx · text, vision
    $0.25/M in
    $2/M out
    Run
  • Seed 1.6 Flash● available
    GPU Network · bytedance-seed/seed-1.6-flash · 262K ctx · text, vision
    $0.075/M in
    $0.3/M out
    Run
  • Seed 2.1 Turbo● available
    GPU Network · bytedance-seed/seed-2-1-turbo · 262K ctx · text, vision
    $0.5/M in
    $2.5/M out
    Run
  • Seed-2.0-Code● available
    GPU Network · bytedance-seed/seed-2.0-code · 262K ctx · text, vision
    $0.5/M in
    $3/M out
    Run
  • Seed-2.0-Lite● available
    GPU Network · bytedance-seed/seed-2.0-lite · 262K ctx · text, vision
    $0.25/M in
    $2/M out
    Run
  • Seed-2.0-Mini● available
    GPU Network · bytedance-seed/seed-2.0-mini · 262K ctx · text, vision
    $0.1/M in
    $0.4/M out
    Run
  • Skyfall 36B V2● available
    GPU Network · thedrummer/skyfall-36b-v2 · 33K ctx · text
    $0.55/M in
    $0.8/M out
    Run
  • Solar Mini 4● available
    GPU Network · upstage/solar-mini4 · 524K ctx · text
    $0.05/M in
    $0.2/M out
    Run
  • Solar Pro 4● available
    GPU Network · upstage/solar-pro4 · 524K ctx · text
    $0.15/M in
    $0.6/M out
    Run
  • Sonar● available
    GPU Network · perplexity/sonar · 127K ctx · text, vision
    $1/M in
    $1/M out
    Run
  • Sonar Deep Research● available
    GPU Network · perplexity/sonar-deep-research · 128K ctx · text
    $2/M in
    $8/M out
    Run
  • Sonar Pro● available
    GPU Network · perplexity/sonar-pro · 200K ctx · text, vision
    $3/M in
    $15/M out
    Run
  • Sonar Pro Search● available
    GPU Network · perplexity/sonar-pro-search · 200K ctx · text, vision
    $3/M in
    $15/M out
    Run
  • Sonar Reasoning Pro● available
    GPU Network · perplexity/sonar-reasoning-pro · 128K ctx · text, vision
    $2/M in
    $8/M out
    Run
  • Step 3.5 Flash● available
    GPU Network · stepfun/step-3.5-flash · 262K ctx · text
    $0.1/M in
    $0.3/M out
    Run
  • Step 3.7 Flash● available
    GPU Network · stepfun/step-3.7-flash · 262K ctx · text, vision
    $0.2/M in
    $1.15/M out
    Run
  • Step 5 Preview● available
    GPU Network · stepfun/step-5-preview · 1049K ctx · text, vision
    $1/M in
    $2.7/M out
    Run
  • Summarize● available
    GPU Network · scaledown/summarize · 1000K ctx · text, vision
    $0.04/M in
    $0/M out
    Run
  • Switchyard● available
    GPU Network · nvidia/switchyard · 1000K ctx · text
    $0/M in
    $0/M out
    Run
  • Ternary Bonsai 2 27B● available
    GPU Network · prism-ml/ternary-bonsai-2-27b · 262K ctx · text, vision
    $0.075/M in
    $0.5/M out
    Run
  • Ternary Bonsai 2 9B● available
    GPU Network · prism-ml/ternary-bonsai-2-9b · 262K ctx · text, vision
    $0.08/M in
    $0.13/M out
    Run
  • UI-TARS 7B● available
    GPU Network · bytedance/ui-tars-1.5-7b · 128K ctx · text, vision
    $0.1/M in
    $0.2/M out
    Run
  • Uncensored● available
    GPU Network · cognitivecomputations/dolphin-mistral-24b-venice-edition · 128K ctx · text
    $0.2/M in
    $0.9/M out
    Run
  • UnslopNemo 12B● available
    GPU Network · thedrummer/unslopnemo-12b · 1024K ctx · text
    $0.4/M in
    $0.4/M out
    Run
  • Vega Image● available
    Vega · api/vega-image · 8K ctx · image
    $0/M in
    $40/M out
    Run
  • Vega Vision Prodegraded
    Vega · api/vega-vision-pro · 200K ctx · text, vision, tools
    $2/M in
    $8/M out
    Run
  • Voxtral Small 24B 2507● available
    GPU Network · mistralai/voxtral-small-24b-2507 · 33K ctx · text, audio
    $0.1/M in
    $0.3/M out
    Run
  • Weaver (alpha)● available
    GPU Network · mancer/weaver · 8K ctx · text
    $0.4/M in
    $0.75/M out
    Run
  • Xing4.0 29B A4B (free)● available
    GPU Network · xingchen-agi/xing4.0-29b-a4b:free · 262K ctx · text
    $0/M in
    $0/M out
    Run