[BOT ISSUE] Perplexity: add missing perplexity/nemotron-3-ultra-550b-a55b Agent API model

Open Beginner friendly
#1,100 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
85/100
Issue type
Feature
Clarity
Clearly specified
Activity status
Quiet
Tech stack
json
Domain
api

Research direction

Open model_list.json and compare nearby Perplexity Agent API entries, especially perplexity/sonar-pro-search, with the proposed specification. Add perplexity/nemotron-3-ultra-550b-a55b using the values in the issue, then verify the model ID and provider metadata appear correctly in the catalog.

Written by the indexing model from the issue text.

Description

autofix-blocked bot-issue

Summary

The model perplexity/nemotron-3-ultra-550b-a55b is listed on the Perplexity Agent API models page and pricing page, but is not present in the Braintrust proxy model catalog.

The underlying model nvidia/nemotron-3-ultra-550b-a55b already exists in the catalog (with together and openrouter providers), but the Perplexity-hosted variant is missing. This follows the same pattern as other Perplexity Agent API models like perplexity/sonar-pro-search.

Verification checklist

  • Cross-source: Model ID confirmed on Perplexity Agent API models page and pricing page (2 independent official sources)
  • Already-fixed check: Grepped model_list.json for perplexity/nemotron-3-ultra-550b-a55b — no match found; searched closed issues — no prior issue exists
  • ID format check: perplexity/nemotron-3-ultra-550b-a55b follows the established Perplexity Agent API naming convention (perplexity/ prefix, matches sibling models already in catalog)

Proposed catalog entry

{
  "perplexity/nemotron-3-ultra-550b-a55b": {
    "format": "openai",
    "flavor": "chat",
    "multimodal": false,
    "input_cost_per_mil_tokens": 0.25,
    "output_cost_per_mil_tokens": 2.5,
    "input_cache_read_cost_per_mil_tokens": 0.25,
    "max_input_tokens": 512300,
    "max_output_tokens": 32768,
    "available_providers": ["perplexity"]
  }
}

Note: max_input_tokens and max_output_tokens are derived from the base model nvidia/nemotron-3-ultra-550b-a55b already in the catalog, as Perplexity does not publish context window details for Agent API models.

Sources

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.