OpenAI

AkashML implements the OpenAI HTTP API over its open source model catalog. Set the OpenAI client's base URL to https://api.akashml.com/v1 and authenticate with your AkashML API key — everything else works unchanged.

Create chat completion

Generate a model response for a conversation — the primary chat endpoint, with streaming and tool calling.

Create completion

Legacy text completion endpoint for prompt-in, text-out generation.

List models

Lists the currently available models with pricing and capability metadata.

Create chat completion

Creates a model response for the given chat conversation. Supports streaming via SSE when `stream: true`. **Response headers** - `Inference-Id` — Unique ID for this request. Include this when contacting support. **Error codes** | Status | Meaning | |--------|---------| | `402` | Insufficient credits | | `429` | Rate limited | | `504` | No backend available | | `529` | No healthy backends are available for the requested model |