Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
X-Clear-* headers that tell you how your request was routed.
model); they don’t expose internal routing details like channel
identifiers or upstream backend URLs.
| Header | Present when | Example | Meaning |
|---|---|---|---|
X-Clear-Fallback-Level | extra_body.models caused a fallback | 1 | Zero-indexed position in your fallback chain that served the response. 0 means the primary model succeeded and fallback did not trigger. |
X-Clear-Fallback-Model | Fallback triggered (level > 0) | google/gemini-2.5-pro | The model that actually served the response after the primary failed. |
X-Clear-Router | You called clearmaas/{name} | auto | The name of the router you invoked. |
X-Clear-Resolved-Model | You called clearmaas/{name} | openai/gpt-4o-mini | The concrete model the router resolved to at request time. |
Retry-After | Response is 429 Too Many Requests | 5 | How many seconds to wait before retrying. |
response = client.chat.completions.with_raw_response.create(
model="clearmaas/auto",
messages=[...],
)
print(response.headers.get("X-Clear-Resolved-Model"))
const { data, response } = await openai.chat.completions
.with_raw_response
.create({ model: "clearmaas/auto", messages: [...] });
console.log(response.headers.get("x-clearmaas-resolved-model"));
curl -v https://api.clearmaas.com/v1/chat/completions \
-H "Authorization: Bearer sk-..." \
-H "Content-Type: application/json" \
-d '{"model":"clearmaas/auto","messages":[...]}'
# -v dumps response headers to stderr; look for X-Clear-* lines
provider or routed_to header or response field