[BOT ISSUE] Perplexity: add missing embedding model `pplx-embed-context-v1-4b`

[github-actions]

Summary

The Perplexity embedding model pplx-embed-context-v1-4b is missing from packages/proxy/schema/model_list.json. This is a follow-up to #645 which covers the other three Perplexity embedding models.

Missing Model ID

Model ID	Dimensions	Context	Input $/M tokens	Type
pplx-embed-context-v1-4b	2560	32K	$0.05	Contextualized embedding

Details

pplx-embed-context-v1-4b is the largest Perplexity contextualized embedding model. Contextualized embeddings generate document-aware representations by incorporating surrounding context, improving RAG pipeline quality.

Suggested entry

"pplx-embed-context-v1-4b": {
  "format": "openai",
  "flavor": "embedding",
  "input_cost_per_mil_tokens": 0.05,
  "displayName": "Perplexity Embed Context v1 (4B)",
  "max_input_tokens": 32000,
  "available_providers": ["perplexity"]
}

Verification checklist

• Cross-source: Model ID confirmed on Perplexity pricing page and Embeddings quickstart
• Recent commits: Not covered by any recent commit to model_list.json
• ID format: Uses Perplexity's official model ID format
• Existing issues: Not covered by [BOT ISSUE] Perplexity: add missing embedding models pplx-embed-v1-0.6b, pplx-embed-v1-4b, pplx-embed-context-v1-0.6b #645 (which covers the other 3 embedding models)

Verification notes

Field	Source	Notes
Model ID	Pricing page + Embeddings quickstart	Listed on both pages
Dimensions (2560)	Embeddings quickstart	Documented specification
Context (32K)	Embeddings quickstart	All embedding models: 32K context
Pricing ($0.05/M)	Pricing page + Embeddings quickstart	Consistent across both sources
format: "openai"	Catalog convention	Perplexity uses OpenAI-compatible API
flavor: "embedding"	API endpoint	Uses /embeddings endpoint

Local files inspected

• packages/proxy/schema/model_list.json — grep for pplx-embed-context-v1-4b returns no matches

Source URLs

• https://docs.perplexity.ai/guides/pricing
• https://docs.perplexity.ai/docs/embeddings/quickstart

{
  "kind": "missing_model",
  "provider": "perplexity",
  "models": ["pplx-embed-context-v1-4b"],
  "status": "active",
  "model_specs": {
    "pplx-embed-context-v1-4b": {
      "format": "openai",
      "flavor": "embedding",
      "input_cost_per_mil_tokens": 0.05,
      "displayName": "Perplexity Embed Context v1 (4B)",
      "max_input_tokens": 32000,
      "available_providers": ["perplexity"]
    }
  },
  "source_urls": [
    "https://docs.perplexity.ai/guides/pricing",
    "https://docs.perplexity.ai/docs/embeddings/quickstart"
  ]
}

[github-actions]

Prepared catalog updates for pplx-embed-context-v1-4b. Added models: pplx-embed-context-v1-4b.

Verification sources: https://docs.perplexity.ai/guides/pricing, https://docs.perplexity.ai/docs/embeddings/quickstart
Verified metadata applied:

• pplx-embed-context-v1-4b: format=openai, flavor=embedding, displayName=Perplexity Embed Context v1 (4B), max_input_tokens=32000, max_output_tokens=n/a, pricing(input/output per 1M)=0.05/?, providers=perplexity

Opened #656 to apply the catalog update.