Quickstart
Create a key and make your first chat completion in under five minutes. Get started →
Inferel Developer Docs
One OpenAI-compatible endpoint for 70+ frontier and open-source models — with transparent per-token pricing and prepaid credits.
Inferel gives you a single API for models from Anthropic, OpenAI, Google, DeepSeek, Qwen,
Moonshot, and more. If your code already speaks the OpenAI API, switching is a two-line
change: point the base URL at https://inference.inferel.ai/v1 and use your Inferel API
key.
API reference
Chat completions, streaming, the Responses API, Anthropic-compatible messages, and error semantics. Browse the API →
Models & pricing
70+ models, priced per million tokens with separate input/output rates. See models →
Billing & credits
Prepaid credits, card top-ups, auto-recharge, and monthly statements. Manage billing →
At a glance
Section titled “At a glance”| Base URL (OpenAI SDKs) | https://inference.inferel.ai/v1 |
| Base URL (Anthropic SDKs) | https://inference.inferel.ai — no /v1, the SDK adds it |
| Console | console.inferel.ai — keys, billing, usage |
| Auth | Authorization: Bearer <INFEREL_API_KEY> (or x-api-key) |
| Compatibility | OpenAI Chat Completions, Completions & Responses; Anthropic Messages |
| Streaming | Server-sent events (stream: true); add stream_options for a usage chunk |
| Model catalog | GET /v1/models — live list with per-token pricing |
| Support | support@inferel.ai |