POST https://api.prysm1.com/v1/chat/completions · Requires authentication
The main endpoint. Send OpenAI-shaped messages with model: "auto" and PRYSM
routes the request to the best-value model, returning a standard
completion plus a prysm
Authorization Your secret key as a bearer token: Bearer prysm_sk_...
Body The conversation so far. Each message has a role (system, user, or assistant)
and content (string).
"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.Maximum number of tokens to generate in the completion.
Sampling temperature between 0 and 2. Lower is more deterministic.
Reserved for streaming responses.
Force a routing mode: quality, balanced, or agility. Omit to let PRYSM choose.
PRYSM-specific.
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 added prysm block.
Unique completion ID, prefixed prysm-.
Unix timestamp (seconds) when the completion was created.
The catalog ID of the model that actually ran.
The generated choices. The assistant message: { "role": "assistant", "content": "..." }.
Why generation stopped, e.g. stop.
Token accounting: prompt_tokens, completion_tokens, total_tokens.
The PRYSM extension block — routing decision, cost, latency, and proof. quality, balanced, agility, or direct.
Human-readable model name.
Upstream provider that served the call.
Why this model was chosen.
budget, mid, premium, or frontier.
Intent signals detected in the prompt.
Cost of input tokens, USD.
Cost of output tokens, USD.
End-to-end latency in milliseconds.
The PrysmProof receipt: request_id, timestamp,
proof_hash, model, provider, mode, reason, verifiable. true if the intended model was unavailable and a fallback served the call.
Intended model, if a fallback occurred.
Model that actually served the call, if a fallback occurred.
from prysm import Prysm client = Prysm() resp = client.chat.completions.create( model = "auto" , messages = [{ "role" : "user" , "content" : "Write a Python quicksort" }], ) print (resp.choices[ 0 ].message.content)
{ "id" : "prysm-a1b2c3d4" , "object" : "chat.completion" , "created" : 1748888641 , "model" : "deepseek-v3.2" , "choices" : [ { "index" : 0 , "message" : { "role" : "assistant" , "content" : "def quicksort(a): ..." }, "finish_reason" : "stop" } ], "usage" : { "prompt_tokens" : 18 , "completion_tokens" : 240 , "total_tokens" : 258 }, "prysm" : { "routing" : { "mode" : "balanced" , "model_display" : "DeepSeek V3.2" , "provider" : "deepseek" , "reason" : "Code: 95% cheaper than GPT-5.2" , "tier" : "budget" , "signals_detected" : { "code" : true } }, "cost" : { "input_usd" : 0.00000504 , "output_usd" : 0.0001008 , "total_usd" : 0.00010584 }, "latency_ms" : 740 , "proof" : { "request_id" : "b1e7c0d2-3f4a-5b6c-7d8e-9f0a1b2c3d4e" , "timestamp" : "2026-06-02T18:24:01.123456+00:00" , "proof_hash" : "sha256:a1b2c3d4e5f6a7b8" , "model" : "DeepSeek V3.2" , "provider" : "deepseek" , "mode" : "balanced" , "reason" : "Code: 95% cheaper than GPT-5.2" , "verifiable" : true }, "fallback" : false , "fallback_from" : null , "fallback_to" : null } }
