[BOT ISSUE] Add perplexity/sonar to model catalog (Perplexity Agent API)

Open Beginner friendly
#1,114 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
1/5
Estimated time
Under an hour
Newbie friendliness
76/100
Issue type
Feature
Clarity
Clearly specified
Activity status
Quiet
Tech stack
json
Domain
backend-api-design

Research direction

Open model_list.json near the existing perplexity/sonar-pro-search entry at line 13343 and compare it with other Agent API model entries. Add the perplexity/sonar catalog metadata with the documented provider, token pricing, chat flavor, and openai format, then verify the model ID appears in the catalog without adding undocumented token limits.

Written by the indexing model from the issue text.

Description

autofix-blocked model-catalog

Summary

Perplexity's own perplexity/sonar model is listed on the Agent API with token-based pricing but is missing from the model catalog. This is Perplexity's first-party model exposed through the Agent API (distinct from the Sonar API sonar model which has per-request pricing).

Source verification

Field Value Source
Model ID perplexity/sonar Perplexity Pricing
Input cost $0.25 / 1M tokens Perplexity Pricing
Output cost $2.50 / 1M tokens Perplexity Pricing
Cached input cost $0.0625 / 1M tokens Perplexity Pricing

Cross-source verification

  • Confirmed on Perplexity pricing page as an Agent API model with full pricing
  • Confirmed on Perplexity guides/pricing page with matching pricing
  • Not present in model_list.json (grep confirmed zero matches for "perplexity/sonar" — only perplexity/sonar-pro-search exists)
  • No existing open GitHub issue covers this model ID

Notes

  • perplexity/sonar is the Agent API variant with standard token-based pricing ($0.25/$2.50/$0.0625 per 1M tokens). This is distinct from the Sonar API model sonar which charges $1/$1 per 1M tokens plus $5–$12 per 1K requests
  • The existing perplexity/sonar-pro-search entry (line 13343) has available_providers: ["openrouter"] and uses a different pricing structure ($3/$15) — it is a separate model accessed via OpenRouter, not the same as this Agent API model
  • max_input_tokens and max_output_tokens are not included because Perplexity does not publish context window details for this Agent API model — these should only be added when officially documented
  • Follows the perplexity/ prefix convention used by other Agent API models (perplexity/nemotron-3-ultra-550b-a55b, perplexity/kimi-k3, etc.)
Dominant language
TypeScript
Stars
410
Forks
65
Avg merge
18h 29m
Merged PRs (30d)
51

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from braintrustdata/braintrust-proxy

All issues in braintrustdata/braintrust-proxy

Similar issues

More TypeScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.