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
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
Summary
The model
perplexity/nemotron-3-ultra-550b-a55bis 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-a55balready exists in the catalog (withtogetherandopenrouterproviders), but the Perplexity-hosted variant is missing. This follows the same pattern as other Perplexity Agent API models likeperplexity/sonar-pro-search.Verification checklist
model_list.jsonforperplexity/nemotron-3-ultra-550b-a55b— no match found; searched closed issues — no prior issue existsperplexity/nemotron-3-ultra-550b-a55bfollows 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_tokensandmax_output_tokensare derived from the base modelnvidia/nemotron-3-ultra-550b-a55balready in the catalog, as Perplexity does not publish context window details for Agent API models.Sources