DINGJIAI
DINGJIAI
Quick start in 5 minutesWhat is DINGJIAI?

Online use

Online chatOpens in a new windowImage generationOpens in a new window

Popular Agents

Codex SetupClaude Code SetupOne-Click Setup

API Reference

API overview
ResponsesChat CompletionsAnthropic MessagesGemini API
Error codes

Billing

Model pricingTroubleshooting calls
API families and API entries

Anthropic Messages

The Anthropic Messages API entry, authentication headers, and usage settlement boundaries.

Anthropic uses x-api-key

Claude Code and Anthropic-compatible tools should use the Messages entry and put the DINGJIAI user API Key in x-api-key. Sending only Bearer authentication will not pass Anthropic authentication.

Paths

PurposeMethod and path
Model requestPOST /v1/messages
Compatible pathPOST /anthropic/v1/messages
Model listGET /anthropic/v1/models or GET /anthropic/v1/models/

Request example

POST /v1/messages
curl https://dingjiai.com/v1/messages \
  -H "x-api-key: YOUR_USER_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "A_MODEL_NAME_COPIED_FROM_THE_ANTHROPIC_MODEL_LIST",
    "max_tokens": 256,
    "messages": [
      { "role": "user", "content": "Introduce yourself in one sentence" }
    ]
  }'

Streaming request

stream=true
curl -N https://dingjiai.com/v1/messages \
  -H "x-api-key: YOUR_USER_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "A_MODEL_NAME_COPIED_FROM_THE_ANTHROPIC_MODEL_LIST",
    "max_tokens": 256,
    "stream": true,
    "messages": [
      { "role": "user", "content": "Explain the integration in three points" }
    ]
  }'

Headers and version

Prop

Type

Usage and billing

Settlement reads usage.input_tokens, usage.output_tokens, and the optional usage.cache_creation_input_tokens and usage.cache_read_input_tokens fields.

Trusted usage takes priority. When usage is missing or invalid, generated visible text, thinking, and tool_use.input may be used for estimation. For a valid non-stream success JSON object billed by tokens, missing or invalid usage incurs at least one output token even when no extractable output is available (including {}). Stream estimation requires extractable model output. A disconnect, cancellation, or delivery failure is not necessarily free; settlement does not require the client to have successfully received a chunk. For the complete estimation conditions, partial-usage rules, and failed-request settlement rules, see Usage and billing.

Anthropic requests are not automatically converted to OpenAI

Anthropic Messages selects the model products and upstream candidates exposed for the Anthropic entry. A model with the same name in the OpenAI Chat list does not automatically mean that it is available for Anthropic Messages; it must also be published for the Anthropic Messages entry.

Last updated on

Chat CompletionsGemini API

On this page

PathsRequest exampleStreaming requestHeaders and versionUsage and billing