deepinfra.com
DeepInfra provides hosted inference for open-source AI models, including LLMs, embeddings, image generation, speech, and other model types. It also offers APIs for batch processing and deploying private or dedicated models.
DeepInfra exposes three documented developer-facing HTTP APIs: an OpenAI-compatible API, a native inference API, and an Anthropic-compatible Messages API; all require a DeepInfra-issued token, with scoped JWTs also supported for inference access.
- DeepInfra OpenAI-compatible APIdiscovered
- DeepInfra Native APIdiscovered
Go to the DeepInfra API keys dashboard and create an API key. Use it as a bearer token in the Authorization header: Authorization: Bearer $DEEPINFRA_TOKEN.
First create or use a parent API key from the DeepInfra API keys dashboard. Then create a scoped JWT by calling POST https://api.deepinfra.com/v1/scoped-jwt with your API key in Authorization: Bearer ..., as shown in Authentication. The returned token is prefixed like jwt:... and is then used in the same bearer Authorization header as a normal API key.
conventions · 0/7 published
- integrations.json——
- llms.txt✗
/llms.txt - API catalog✗
/.well-known/api-catalog - OpenAPI document✗
/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json - MCP server card✗
/.well-known/mcp/server-card.json - OAuth protected resource✗
/.well-known/oauth-protected-resource - Agent card✗
/.well-known/agent-card.json - Agent skills✗
/.well-known/agent-skills/index.json
Publish these signals → /publishing