pplx-embed-v2-late-9b
pplx-embed-v2-late-9bPerplexityOpen weightsNon-reasoningReleased Oct 7, 2026
Overall score
—
Not enough evidence to rank yet
Context window
4K
4,096 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet
Benchmark results (2)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
No benchmark results with redistributable sources yet.
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price | — | — | — |
MIT-licensed weights are available for self-hosting. Zero token rates represent self-hosted use; hardware, storage, and serving costs still apply. The official model card publishes no hosted API token tariff for this checkpoint. Output is a set of token embeddings, not generated text.
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.