Install plugin
Get an API key
- Sign in at deepinfra.com
- Go to Dashboard / Keys and generate a key, or use the auto-created one
CLI setup
Config snippet
Supported surfaces
Chat, image generation, and video generation refresh their model catalogs live fromhttps://api.deepinfra.com/v1/openai/models?sort_by=openclaw&filter=with_meta
once DEEPINFRA_API_KEY is configured. Other surfaces use the static
defaults below until they move onto the same live catalog.
| Surface | Default model | OpenClaw config/tool |
|---|---|---|
| Chat / model provider | first chat-tagged entry from live catalog (static fallback deepseek-ai/DeepSeek-V4-Flash) | agents.defaults.model |
| Image generation/editing | first image-gen-tagged entry from live catalog (static fallback black-forest-labs/FLUX-1-schnell) | image_generate, agents.defaults.imageGenerationModel |
| Media understanding | moonshotai/Kimi-K2.5 for images | inbound image understanding |
| Speech-to-text | openai/whisper-large-v3-turbo | inbound audio transcription |
| Text-to-speech | hexgrad/Kokoro-82M | messages.tts.provider: "deepinfra" |
| Video generation | static fallback Pixverse/Pixverse-T2V (no live video-gen rows from DeepInfra today) | video_generate, agents.defaults.videoGenerationModel |
| Memory embeddings | BAAI/bge-m3 | agents.defaults.memorySearch.provider: "deepinfra" |
Available models
OpenClaw discovers DeepInfra models dynamically once a key is configured. Use/models deepinfra or openclaw models list --provider deepinfra to see the
current list.
Any model on deepinfra.com works with the
deepinfra/ prefix:
Notes
- Model refs are
deepinfra/<provider>/<model>(for exampledeepinfra/Qwen/Qwen3-Max). - Default chat model:
deepinfra/deepseek-ai/DeepSeek-V4-Flash - Base URL:
https://api.deepinfra.com/v1/openai - Native video generation uses
https://api.deepinfra.com/v1/inference/<model>.