兔子API 兔子API
中

provider

01.AI Yi

Direct answerDirect Yi access should use the current 01.AI console API key, base URL, and model ID. This gateway uses its own Bearer token and /v1/chat/completions; the credentials are not interchangeable.

Updated · Reviewed

What can currently be verified

The 01.AI domain still exposes Yi platform and API-reference entry points, but the dynamic documentation timed out during this review and official-domain search returned no stable current API detail. This page therefore adds no model, base URL, context, or price and does not infer “latest” capabilities from old releases or third-party benchmarks.

Direct access versus this gateway

Direct access should use the API key, current base URL, and exact model ID issued by the live 01.AI console. This gateway uses its own base URL, Bearer token, and the adapted /v1/chat/completions route listed here; credentials are not interchangeable. An OpenAI SDK integration must test streaming, errors, and parameter support rather than changing only the address.

Model and protocol ownership

Yi belongs to 01.AI, but current availability and support for vision, tools, JSON, or a particular context must come from the live model page and console. A gateway name may also be a channel mapping rather than an official display name. Without official evidence, this page does not describe Yi as an asynchronous media service or claim task IDs or temporary media URLs.

Errors, data, and cost safety

For 401, first separate provider keys from gateway tokens. A missing model requires checking the official console and gateway model list independently. Before production, verify limits, price, retention, region, content policy, and migration notices, and set timeouts, concurrency, budgets, and bounded retries.

Content and rights review

Generated text still needs factual, safety, and copyright review and is not a source or license warranty. Send only task-required data, never secrets or restricted material, and retain model ID, request time, and human acceptance evidence.

Reviewed provider catalog

Latest models by capability

These are provider-catalog models, not a promise of availability on this site. Confirm callable IDs, endpoints, and pricing in the model marketplace.

Text, reasoning, and code

Check live availability in the model marketplace

Use cases

  • General text generation
  • Chinese and multilingual tasks
  • Open platform API

API protocols

  • /v1/chat/completions

FAQ

Which credentials are used for direct Yi access versus this gateway?

Direct access uses the API key, official base URL, and model ID currently issued by the 01.AI console. This gateway's /v1/chat/completions uses its own base URL and Bearer token. A Yi key cannot authenticate the gateway, and a gateway token cannot authenticate 01.AI.

Which Yi models are currently available, and what should model contain?

This review could not reliably read the live model table from public official pages, so do not reuse IDs from historical blogs. Sign in to the live console, copy the exact API ID, and verify enablement for the account, region, and protocol.

Can the Yi brand alone prove support for vision, tools, or JSON?

No. Vision, tools, structured output, context, and streaming fields require explicit support in the current model or API reference. Through this gateway, also verify that the channel passes the fields through.

Can a third-party tutorial replace official documentation when the official page is unavailable?

It should not be the production authority. Third-party tutorials may aid troubleshooting but cannot establish current service status, price, limits, data terms, or lifecycle. Wait for verifiable official material or confirm through the console and official support.

  • OpenAI-compatible API guideThis site's OpenAI-compatible routes use a Bearer token; Responses, Chat Completions, and media endpoints have distinct objects and streaming semantics and must match the target model.
  • Choosing and calling coding modelsSelect coding models by patch correctness, test pass rate, tool success, latency, and cost on real repositories, not marketplace copy or a single benchmark.
  • AI API quickstart: from API key to first requestAn AI API call needs a matching base URL, API key, model ID, and endpoint; start with minimal curl, then add error handling, cost controls, and key security.
  • Common AI API error codes and troubleshootingHandle AI API failures by parsing the HTTP status, provider code, error type, message, retry hints, and request ID together. Fix request, authentication, billing, and hard-quota causes first; retry only transient throttling, network failures, and selected 5xx errors with strict bounds.

Official sources

  1. 零一万物开放平台文档 Official
  2. 零一万物 API Reference Official