Reference

Models catalog

Every public alias you can pass as the model field. Prices are quoted in USD per 1 million tokens, the same unit OpenAI, Anthropic and Google publish on their pricing pages. Relay billing meters at per-token resolution; amounts are shown in USD and your wallet is debited in USD-cents.

154 models live. You can also browse this list in the developer console.

Interchangeable model groups

Aliases in the same group are automatic substitutes when every route of the requested model is down (unless you send allow_substitution: false).

ds-v4-flash: deepseek-v4-flash ⇄ volc-deepseek-v4-flash

ds-v4-pro: deepseek-v4-pro ⇄ volc-deepseek-v4-pro

gpt5-flagship: gpt-5.4 ⇄ gpt-5.5

Routing & failover

You always pass the platform alias (e.g. gpt-5.2), never the upstream-specific id (e.g. openai/gpt-5.2). Behind the scenes:

1. Each alias maps to one or more upstream routes ordered by priority.
2. Each route consumes credentials from a per-provider pool. If a credential gets repeatedly rejected, it's cooled down for 60s and the next request picks a sibling.
3. A single retryable upstream error (5xx, 401/403 token issues, 429 rate limit) triggers the relay to retry the next candidate automatically — your client only sees the final result.
4. If every candidate is exhausted, you get an explicit 503 with a clear message instead of a stuck request.

See Common errors for what each status code means and how to react.

Automatic model routing (auto)

Send model: "auto" and the platform picks a concrete model for you, balancing cost and latency. Three intent variants steer the choice: auto:cheap (lowest price), auto:fast (lowest latency) and auto:quality (highest quality tier).

curl https://chinzy.com/v1/chat/completions \
  -H "Authorization: Bearer tsk_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto:cheap",
    "messages": [{"role": "user", "content": "Say hi in one sentence"}]
  }'

• Server switch required. Auto routing is a server-side feature flag (AUTO_ROUTING_ENABLED). When it is off, auto requests fail with 400 auto_routing_disabled — fall back to a concrete alias.
• Text chat only. Requests with images or tool definitions must name a concrete model; auto returns 400 for them.
• The billed model is always reported. Check the model field of the response, and the autobadge next to each call in the console usage page's recent-calls list.
• Candidate set = the Auto column above. A model marked ✓ eligible can be picked by the auto router (text + enabled + priced + at least one active route).

Cross-model failover & allow_substitution

When every route of the model you asked for is down, the platform automatically substitutes an equivalent model from the same interchangeable group (see the groups listed above). The response and your usage page always report the alias actually billed, with the original request preserved as the source annotation.

allow_substitution is a platform-reserved request field: it defaults to true, and only an explicit false opts out of substitution. The field is stripped before the request is forwarded, so it never leaks to the upstream provider. It can be sent at the top level of the request body on both the OpenAI and the Anthropic protocol.

Protocol matrix