askrDocs

Docs/Models

Models

Every model on askr, what it costs, and where it runs.

Checked against the code on

This list is the live catalog, read when the page loads and cached for five minutes. Ids are exact and are what you pass as model. Prices are per million tokens for chat, per picture or per clip for media.

317 chat models on the API, 3 of them make pictures. 21 video models in the workspace. 153 listed but not routable.

AllChatMakes picturesVideo
All providersQwen 53OpenAI 48Google 26Anthropic 18Mistral 18Z.ai 17DeepSeek 16Meta 12ByteDance 10MoonshotAI 9MiniMax 9xAI 8
50
ModelIdRuns onIn / out, $ per 1MTurnContext
Qwen 50
Qwen3.7 Flashqwen/qwen3.7-flashAPI, workspace0.032 / 0.1370.1 cr1000K
Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507API, workspace0.051 / 0.2040.15 cr262K
Qwen3.5-9Bqwen/qwen3.5-9bAPI, workspace0.105 / 0.1580.18 cr262K
Qwen3.5-Flashqwen/qwen3.5-flash-02-23API, workspace0.069 / 0.2740.21 cr1000K
Qwen2.5 7B Instructqwen/qwen-2.5-7b-instructAPI, workspace0.105 / 0.2110.21 cr33K
Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instructAPI, workspace0.074 / 0.2950.22 cr262K
Qwen3 32Bqwen/qwen3-32bAPI, workspace0.084 / 0.2950.23 cr131K
Qwen3 14Bqwen/qwen3-14bAPI, workspace0.127 / 0.2530.25 cr131K
Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507API, workspace0.092 / 0.3690.28 cr262K
Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instructAPI, workspace0.11 / 0.4390.33 cr131K
Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instructAPI, workspace0.123 / 0.480.36 cr262K
Qwen3 30B A3Bqwen/qwen3-30b-a3bAPI, workspace0.127 / 0.5270.39 cr131K
Qwen3.8 Flashqwen/qwen3.8-flashAPI, workspace0.158 / 0.4960.41 cr1000K
Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instructAPI, workspace0.137 / 0.5490.41 cr262K
Qwen3 Coder Nextqwen/qwen3-coder-nextAPI, workspace0.127 / 0.8440.55 cr262K
Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bAPI, workspace0.105 / 0.950.58 cr262K
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instructAPI, workspace0.38 / 0.4220.59 cr33K
Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instructAPI, workspace0.095 / 1.160.68 cr262K
Qwen-Plusqwen/qwen-plusAPI, workspace0.274 / 0.8230.69 cr1000K
Qwen Plus 0728qwen/qwen-plus-2025-07-28API, workspace0.274 / 0.8230.69 cr1000K
Qwen3 Coder Flashqwen/qwen3-coder-flashAPI, workspace0.206 / 1.030.72 cr1000K
Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinkingAPI, workspace0.158 / 1.270.79 cr262K
Qwen3.6 Flashqwen/qwen3.6-flashAPI, workspace0.198 / 1.190.79 cr1000K
Qwen3 Coder 480B A35Bqwen/qwen3-coderAPI, workspace0.317 / 1.050.84 cr262K
Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3bAPI, workspace0.171 / 1.370.86 cr262K
Qwen3.7 Plusqwen/qwen3.7-plusAPI, workspace0.338 / 1.351 cr1000K
Qwen3.5-27Bqwen/qwen3.5-27bAPI, workspace0.206 / 1.651 cr262K
Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15API, workspace0.274 / 1.651.1 cr1000K
Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instructAPI, workspace0.696 / 1.051.2 cr33K
Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instructAPI, workspace0.222 / 2.001.2 cr262K
Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420API, workspace0.317 / 1.901.3 cr1000K
Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinkingAPI, workspace0.19 / 2.221.3 cr131K
Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instructAPI, workspace0.844 / 1.051.4 cr128K
Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10bAPI, workspace0.274 / 2.191.4 cr262K
Qwen3.6 27Bqwen/qwen3.6-27bAPI, workspace0.317 / 2.111.4 cr262K
Qwen3.6 Plusqwen/qwen3.6-plusAPI, workspace0.343 / 2.061.4 cr1000K
Qwen3 235B A22Bqwen/qwen3-235b-a22bAPI, workspace0.48 / 1.921.4 cr131K
Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507API, workspace0.243 / 2.431.5 cr131K
Qwen3 30B A3B Thinking 2507qwen/qwen3-30b-a3b-thinking-2507API, workspace0.211 / 2.531.5 cr82K
Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinkingAPI, workspace0.211 / 2.531.5 cr262K
Qwen3.8 27Bqwen/qwen3.8-27bAPI, workspace0.226 / 2.691.6 cr1000K
Qwen3 Coder Plusqwen/qwen3-coder-plusAPI, workspace0.686 / 3.432.4 cr1000K
Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17bAPI, workspace0.58 / 3.692.4 cr262K
Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinkingAPI, workspace0.422 / 4.222.5 cr131K
Qwen3 Maxqwen/qwen3-maxAPI, workspace0.823 / 4.112.9 cr262K
Qwen3 Max Thinkingqwen/qwen3-max-thinkingAPI, workspace0.823 / 4.112.9 cr262K
Qwen3.7 Maxqwen/qwen3.7-maxAPI, workspace1.56 / 4.673.9 cr1000K
Qwen3.6 Max Previewqwen/qwen3.6-max-previewAPI, workspace1.08 / 6.504.3 cr262K
Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95bAPI, workspace2.11 / 6.335.3 cr1049K
Qwen3.8 Max (0902)qwen/qwen3.8-max-0902API, workspace2.11 / 6.335.3 cr1000K
Listed but not routable (153)

Audio and embedding models, image models that are not chat models, models with no published rate, and the ids their provider is not serving. None of these can be called. Why.

  • amazon/nova-premier-v1 refused
  • anthropic/claude-opus-4 refused
  • aura-sr image
  • auto chat
  • autoclaw chat
  • baai/bge-base-en-v1.5 embedding
  • baai/bge-large-en-v1.5 embedding
  • baai/bge-m3 embedding
  • birefnet-v2 image
  • cohere/north-mini-code refused
  • crystal-upscaler image
  • deepgram-nova-3 audio
  • deepseek/deepseek-v4-pro-0813 refused
  • eleven_flash_v2_5 audio
  • eleven_v3 audio
  • elevenlabs-music-v1 audio
  • fast-sdxl image
  • flux-2-flex image
  • flux-2-pro image
  • flux-2-pro-i2i image
  • flux-2-pro-outpaint image
  • flux-3-i2v image
  • flux-kontext-max image
  • flux-kontext-pro image
  • flux-pro image
  • gemini-omni-flash-i2v image
  • gemini-omni-flash-r2v image
  • gemini-omni-flash-v2v image
  • google/gemini-3-pro-image refused
  • google/gemini-embedding-001 embedding
  • google/gemini-embedding-2 embedding
  • google/lyria-3-clip-preview chat
  • google/lyria-3-pro-preview chat
  • gpt-image-1 image
  • gpt-image-1.5 image
  • gpt-image-2 image
  • gpt-image-2.5-flare image
  • gpt-image-2.5-sunburst image
  • grok-imagine image
  • grok-imagine-edit image
  • grok-imagine-image-2 image
  • grok-imagine-image-2-edit image
  • grok-imagine-video-1.5-i2v image
  • grok-imagine-video-i2v image
  • grok-imagine-video-v2v image
  • happy-horse-1.1-i2v image
  • happy-horse-1.1-r2v image
  • ideogram-v3 image
  • ideogram-v3-remix image
  • intfloat/e5-base-v2 embedding
  • intfloat/e5-large-v2 embedding
  • intfloat/multilingual-e5-large embedding
  • kling-2.5-turbo-i2v image
  • kling-o3-pro-i2v image
  • kling-o3-pro-v2v image
  • kling-o3-standard-i2v image
  • kling-o3-standard-v2v image
  • kling-v3-image image
  • kling-v3-image-edit image
  • kling-v3-pro-i2v image
  • kling-v3-standard-i2v image
  • krea-2-turbo image
  • liquid/lfm-2.5-2.6b refused
  • liquid/lfm-2.5-embedding-350m:free embedding
  • mancer/weaver refused
  • meta/muse-spark-1.1 refused
  • meta/muse-spark-1.2 refused
  • minimax-h3-i2v image
  • minimax-h3-r2v image
  • mistralai/codestral-embed-2505 embedding
  • mistralai/mistral-embed-2312 embedding
  • nano-banana-2 image
  • nano-banana-2-edit image
  • nano-banana-pro image
  • nano-banana-pro-direct image
  • nano-banana-pro-direct-edit image
  • nvidia/llama-nemotron-embed-vl-1b-v2:free embedding
  • nvidia/nemotron-3-embed-1b:free embedding
  • nvidia/nemotron-3-nano-omni-30b-a3b-reasoning refused
  • nvidia/nemotron-3.5-content-safety refused
  • openai/gpt-5-image refused
  • openai/gpt-5-image-mini refused
  • openai/gpt-5-pro refused
  • openai/gpt-5.2-chat refused
  • openai/gpt-5.2-pro refused
  • openai/gpt-5.4-image-2 refused
  • openai/gpt-audio refused
  • openai/gpt-audio-mini refused
  • openai/o1 refused
  • openai/o1-pro refused
  • openai/o3 refused
  • openai/o3-mini refused
  • openai/o3-mini-high refused
  • openai/o3-pro refused
  • openai/o4-mini refused
  • openai/o4-mini-high refused
  • openai/text-embedding-3-large embedding
  • openai/text-embedding-3-small embedding
  • openai/text-embedding-ada-002 embedding
  • perplexity/pplx-embed-v1-0.6b embedding
  • perplexity/pplx-embed-v1-4b embedding
  • perplexity/sonar refused
  • perplexity/sonar-deep-research refused
  • perplexity/sonar-pro refused
  • perplexity/sonar-pro-search refused
  • perplexity/sonar-reasoning-pro refused
  • pika-i2v image
  • private/gemma4-31b refused
  • private/gpt-oss-120b refused
  • private/kimi-k3 refused
  • private/llama3-3-70b refused
  • qwen-image-2 image
  • qwen-image-2-edit image
  • qwen-image-3 image
  • qwen-image-3-edit image
  • qwen/qwen3-8b refused
  • qwen/qwen3-embedding-4b embedding
  • qwen/qwen3-embedding-8b embedding
  • recraft-v4.1 image
  • recraft-v4.1-svg image
  • relace/relace-apply-3 refused
  • sakana/fugu-ultra refused
  • sakana/sakana-namazu refused
  • seedance-2-5-i2v image
  • seedance-2-fast-i2v image
  • seedance-2-i2v image
  • seedream-4.5 image
  • seedream-4.5-edit image
  • seedream-v5-lite image
  • seedream-v5-lite-edit image
  • seedream-v5-pro image
  • seedream-v5-pro-edit image
  • sentence-transformers/all-minilm-l12-v2 embedding
  • sentence-transformers/all-minilm-l6-v2 embedding
  • sentence-transformers/all-mpnet-base-v2 embedding
  • sentence-transformers/multi-qa-mpnet-base-dot-v1 embedding
  • sentence-transformers/paraphrase-minilm-l6-v2 embedding
  • thedrummer/cydonia-24b-v4.1 refused
  • thenlper/gte-base embedding
  • thenlper/gte-large embedding
  • topaz-upscale image
  • veo3-fast-i2v image
  • veo3-i2v image
  • voyageai/voyage-4 embedding
  • voyageai/voyage-4-large embedding
  • voyageai/voyage-4-lite embedding
  • voyageai/voyage-code-4 embedding
  • voyageai/voyage-multimodal-3.5 embedding
  • wan-3.0-i2v image
  • wan-3.0-prime-i2v image
  • wan-3.0-prime-r2v image
  • wan-3.0-r2v image
  • xai-realtime-voice audio

Reading the table

Runs on
API means POST /v1/chat/completions accepts it. Workspace means the browser can run it. Video is workspace only.
Turn
Credits for a typical chat turn: 1,000 tokens in, 500 out. Thinking models run above this because reasoning is billed as output.
Picture
The measured credits per image where we have measured it; the reservation otherwise.
Clip
The cheapest published shape and length. Longer and larger cost more; the workspace shows the exact price before you render.

Ids that the catalog lists but the provider is not currently serving are left out. Listed but refused explains.