POST https://api.prysm1.com/v1/route · Requires authentication
Preview a routing decision without generating a completion. Returns the model PRYSM would
select for a prompt plus an estimated cost — perfect for testing
BRAIN.md rules and showing users a price before they spend.
Authorization Your secret key as a bearer token: Bearer prysm_sk_...
Body The prompt to classify and route.
Force a routing mode: quality, balanced, or agility. Omit to let PRYSM choose.
An inline BRAIN.md config to apply when routing. Response The routing decision. quality, balanced, or agility.
The chosen model’s catalog ID.
Human-readable model name.
Why this model was chosen.
budget, mid, premium, or frontier.
Intent signals detected in the prompt.
Input price, USD per MTok.
Output price, USD per MTok.
Input price, USD per MTok.
Output price, USD per MTok.
Estimated cost for ~1K tokens, USD.
Maximum context length in tokens.
Typical latency in milliseconds.
What this model is good at.
from prysm import Prysm client = Prysm() print (client.route( "write a python function to sort a list" ))
{ "routing" : { "mode" : "balanced" , "model" : "deepseek-v3.2" , "display" : "DeepSeek V3.2" , "provider" : "deepseek" , "why" : "Code: 95% cheaper than GPT-5.2" , "tier" : "budget" , "signals" : { "code" : true }, "in_cost" : 0.28 , "out_cost" : 0.42 }, "estimated_cost" : { "input_per_mtok" : 0.28 , "output_per_mtok" : 0.42 , "est_1k_tokens" : 0.0007 }, "model_info" : { "context_window" : 128000 , "expected_latency_ms" : 220 , "strengths" : [ "general" , "code" , "multilingual" , "value" ] } }
