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.
329 chat models on the API, 3 of them make pictures. 21 video models in the workspace. 165 listed but not routable.
All providersQwen 55OpenAI 49Google 26Z.ai 19Mistral 19Anthropic 18DeepSeek 16Meta 10ByteDance 10xAI 9MoonshotAI 9MiniMax 9
| Model | Id | Runs on | In / out, $ per 1M | Turn | Context |
|---|---|---|---|---|---|
| Meta 10 | |||||
| Llama 3.1 8B Instruct | meta-llama/llama-3.1-8b-instruct | API, workspace | 0.053 / 0.084 | 0.095 cr | 131K |
| Llama 3.2 1B Instruct | meta-llama/llama-3.2-1b-instruct | API, workspace | 0.028 / 0.212 | 0.13 cr | 60K |
| Llama 3.2 3B Instruct | meta-llama/llama-3.2-3b-instruct | API, workspace | 0.053 / 0.348 | 0.23 cr | 131K |
| Llama 4 Scout | meta-llama/llama-4-scout | API, workspace | 0.105 / 0.317 | 0.26 cr | 1311K |
| Llama 3.3 70B Instruct | meta-llama/llama-3.3-70b-instruct | API, workspace | 0.105 / 0.338 | 0.27 cr | 131K |
| Llama Guard 4 12B | meta-llama/llama-guard-4-12b | API, workspace | 0.19 / 0.19 | 0.28 cr | 164K |
| Llama 4 Maverick | meta-llama/llama-4-maverick | API, workspace | 0.198 / 0.688 | 0.54 cr | 1049K |
| Llama 3.1 70B Instruct | meta-llama/llama-3.1-70b-instruct | API, workspace | 0.422 / 0.422 | 0.63 cr | 131K |
| Muse Glimmer 30B | meta/muse-glimmer-30b | API, workspace | 0.317 / 1.27 | 0.95 cr | 131K |
| Muse Spark 1.3 | meta/muse-spark-1.3 | API, workspace | 1.32 / 4.48 | 3.6 cr | 1049K |
Listed but not routable (165)
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.
~openai/gpt-mini-latestrefusedamazon/nova-premier-v1refusedaura-srimageautochatautoclawchatbaai/bge-base-en-v1.5embeddingbaai/bge-large-en-v1.5embeddingbaai/bge-m3embeddingbirefnet-v2imagecohere/north-mini-coderefusedcrystal-upscalerimagedeepgram-nova-3audiodeepseek/deepseek-v4-pro-0813refuseddots-studio/dots-3-note-previewrefusedeleven_flash_v2_5audioeleven_v3audioelevenlabs-music-v1audiofast-sdxlimageflux-2-fleximageflux-2-proimageflux-2-pro-i2iimageflux-2-pro-outpaintimageflux-3-i2vimageflux-kontext-maximageflux-kontext-proimageflux-proimagegemini-omni-flash-i2vimagegemini-omni-flash-r2vimagegemini-omni-flash-v2vimagegoogle/gemini-3-pro-imagerefusedgoogle/gemini-embedding-001embeddinggoogle/gemini-embedding-2embeddinggoogle/lyria-3-clip-previewchatgoogle/lyria-3-pro-previewchatgpt-image-1imagegpt-image-1.5imagegpt-image-2imagegpt-image-2.5-flareimagegpt-image-2.5-sunburstimagegrok-imagineimagegrok-imagine-editimagegrok-imagine-image-2imagegrok-imagine-image-2-editimagegrok-imagine-video-1.5-i2vimagegrok-imagine-video-i2vimagegrok-imagine-video-v2vimagehappy-horse-1.1-i2vimagehappy-horse-1.1-r2vimageideogram-v3imageideogram-v3-remiximageinclusionai/ling-3.0-flash-santerefusedintfloat/e5-base-v2embeddingintfloat/e5-large-v2embeddingintfloat/multilingual-e5-largeembeddingkling-2.5-turbo-i2vimagekling-o3-pro-i2vimagekling-o3-pro-v2vimagekling-o3-standard-i2vimagekling-o3-standard-v2vimagekling-v3-imageimagekling-v3-image-editimagekling-v3-pro-i2vimagekling-v3-standard-i2vimagekrea-2-turboimageliquid/lfm-2.5-2.6brefusedliquid/lfm-2.5-embedding-350m:freeembeddingmancer/weaverrefusedmeta/muse-spark-1.1refusedmeta/muse-spark-1.2refusedmeta/muse-spark-1.2-contributorrefusedmeta/muse-spark-1.3-contributorrefusedmicrosoft/wizardlm-2-8x22brefusedminimax-h3-i2vimageminimax-h3-r2vimagemistralai/codestral-embed-2505embeddingmistralai/mistral-embed-2312embeddingnano-banana-2imagenano-banana-2-editimagenano-banana-proimagenano-banana-pro-directimagenano-banana-pro-direct-editimagenvidia/llama-nemotron-embed-vl-1b-v2:freeembeddingnvidia/nemotron-3-embed-1b:freeembeddingnvidia/nemotron-3-nano-omni-30b-a3b-reasoningrefusednvidia/nemotron-3.5-content-safetyrefusedopenai/gpt-3.5-turbo-0613refusedopenai/gpt-3.5-turbo-16krefusedopenai/gpt-5-imagerefusedopenai/gpt-5-image-minirefusedopenai/gpt-5-prorefusedopenai/gpt-5.2-chatrefusedopenai/gpt-5.2-prorefusedopenai/gpt-5.4-image-2refusedopenai/gpt-audiorefusedopenai/gpt-audio-minirefusedopenai/o1refusedopenai/o1-prorefusedopenai/o3refusedopenai/o3-minirefusedopenai/o3-mini-highrefusedopenai/o3-prorefusedopenai/o4-minirefusedopenai/o4-mini-highrefusedopenai/text-embedding-3-largeembeddingopenai/text-embedding-3-smallembeddingopenai/text-embedding-ada-002embeddingperplexity/pplx-embed-v1-0.6bembeddingperplexity/pplx-embed-v1-4bembeddingperplexity/sonarrefusedperplexity/sonar-deep-researchrefusedperplexity/sonar-prorefusedperplexity/sonar-pro-searchrefusedperplexity/sonar-reasoning-prorefusedpika-i2vimageprivate/deepseek-v4-flashrefusedprivate/gemma4-31brefusedprivate/gpt-oss-120brefusedprivate/kimi-k3refusedprivate/llama3-3-70brefusedqwen-image-2imageqwen-image-2-editimageqwen-image-3imageqwen-image-3-editimageqwen/qwen3-8brefusedqwen/qwen3-embedding-4bembeddingqwen/qwen3-embedding-8bembeddingrecraft-v4.1imagerecraft-v4.1-svgimagerelace/relace-apply-3refusedrespan/span-01-litedecisionrespan/span-01-lite:freedecisionsakana/fugu-ultrarefusedsakana/sakana-namazurefusedseedance-2-5-i2vimageseedance-2-fast-i2vimageseedance-2-i2vimageseedream-4.5imageseedream-4.5-editimageseedream-v5-liteimageseedream-v5-lite-editimageseedream-v5-proimageseedream-v5-pro-editimagesentence-transformers/all-minilm-l12-v2embeddingsentence-transformers/all-minilm-l6-v2embeddingsentence-transformers/all-mpnet-base-v2embeddingsentence-transformers/multi-qa-mpnet-base-dot-v1embeddingsentence-transformers/paraphrase-minilm-l6-v2embeddingstealth/space-bunny-alphachatthedrummer/cydonia-24b-v4.1refusedthenlper/gte-baseembeddingthenlper/gte-largeembeddingtopaz-upscaleimagetypesafe/jev-routerchatveo3-fast-i2vimageveo3-i2vimagevoyageai/voyage-4embeddingvoyageai/voyage-4-largeembeddingvoyageai/voyage-4-liteembeddingvoyageai/voyage-code-4embeddingvoyageai/voyage-multimodal-3.5embeddingwan-3.0-i2vimagewan-3.0-prime-i2vimagewan-3.0-prime-r2vimagewan-3.0-r2vimagexai-realtime-voiceaudio
Reading the table
- Runs on
- API means
POST /v1/chat/completionsaccepts 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.