POST
https://api.prysm1.com/v1/chat/completions · Requires authenticationmodel: "auto" and PRYSM
routes the request to the best-value model, returning a standard
completion plus a prysm block.
Authorization
string
required
Your secret key as a bearer token:
Bearer prysm_sk_...Body
object[]
required
The conversation so far. Each message has a
role (system, user, or assistant)
and content (string).string
default:"auto"
"auto" to let PRYSM choose, or any catalog model ID to pin the request to
a specific model. Unknown IDs fall back to a safe budget default.integer
default:"1000"
Maximum number of tokens to generate in the completion.
number
default:"0.7"
Sampling temperature between 0 and 2. Lower is more deterministic.
boolean
default:"false"
Reserved for streaming responses.
string
Force a routing mode:
quality, balanced, or agility. Omit to let PRYSM choose.
PRYSM-specific.object
An inline BRAIN.md config (normalized object) to apply to this
request — rules,
max_cost, blocked, fallback, and more. PRYSM-specific.Response
Returns an OpenAI-compatible chat completion object with an addedprysm block.
string
Unique completion ID, prefixed
prysm-.string
Always
chat.completion.integer
Unix timestamp (seconds) when the completion was created.
string
The catalog ID of the model that actually ran.
object[]
The generated choices.
object
Token accounting:
prompt_tokens, completion_tokens, total_tokens.object
The PRYSM extension block — routing decision, cost, latency, and proof.