Perplexity models
Perplexity has 7 models in the directory. The newest is Embed v1 0.6b, released Feb 26, 2026.
The cheapest to run is Sonar at $1 per million input tokens.
Sonar Pro Search has the longest context window, 200K tokens.
- Models
- 7
- Newest
- Feb 26, 2026
- From
- $1/M input
- Longest context
- 200K
All Perplexity models
Filter in the directoryEmbed v1 0.6b
Embeddings32K contextTurns text into vectors for search and retrieval.
by perplexityFeb 26, 2026
Embed v1 4b
Embeddings32K contextTurns text into vectors for search and retrieval.
by perplexityFeb 26, 2026
- 200K context
Reads text and images. Structured output, reasoning.
by perplexityOct 30, 2025$3/M input tokens$15/M output tokens
- 128K context
Reads text. Reasoning. Served by 6 providers.
by perplexityJan 27, 2025$2/M input tokens$8/M output tokens6 providers
- 128K context
Reads text. Tool calling, structured output. Served by 11 providers.
by perplexityJan 1, 2024$1/M input tokens$1/M output tokens11 providers
- 200K context
Reads text and images. Structured output. Served by 8 providers.
by perplexityJan 1, 2024$3/M input tokens$15/M output tokens8 providers
- 128K context
Reads text and images. Structured output, reasoning. Served by 6 providers.
by perplexityJan 1, 2024$2/M input tokens$8/M output tokens6 providers
Prices and context from models.dev (MIT licensed), refreshed Oct 15, 2026.
Not sure which Perplexity model fits?
I benchmark the candidates on your own tasks and ship on the one that wins on cost and accuracy.
Book Meeting