[ Inception ]

Mercury 3

Mercury 3 from Inception: a text model for chat and completions, with a 1M-token context window and up to 131,072 output tokens. Routed to the cheapest provider. At or below list. Pay per token in USDF, with no subscription and no minimum. Streaming and the OpenAI-compatible request format are supported.

Get an API key Try in Playground

Inceptionmercury-3AvailabletextContext window: 1,000,000 tokens

Input

$0.105

per 1M tokens

Output

$0.3675

per 1M tokens

Cached input

$0.0105

per 1M tokens

Context window

1,000,000

tokens

Model ID: mercury-3
Modality: text
Unit: USD per 1M tokens
Endpoints: /v1/chat/completions
Max output: 131,072 tokens

Data policy

Zero retentionNo training

Make your first request

Use any OpenAI-compatible SDK. Change the base URL, keep everything else. Responses include a receipt with the exact cost. No key yet? Create one.

No account: send the same request to /x402/v1/chat/completions without credentials and the gateway answers 402 with the quote. Pay per request.

POST /v1/chat/completions

curl https://api.usdf.fi/v1/chat/completions \
  -H "Authorization: Bearer $USDF_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mercury-3", "messages": [{"role": "user", "content": "Hello"}]}'