Perplexity's Agent API adds GPT-6.1 Sol

By Steven Van · 2026-09-01

Perplexity's Agent API adds openai/gpt-6.1-sol at $2 per million input tokens up to 272k, with flex and priority service tiers.

The Agent API now supports openai/gpt-6.1-sol, according to Perplexity's Agent API models reference. The model is available to Perplexity API users by setting it as the model in a request.

The reference lists the following rates for it, per million tokens:

Input: $2.00 up to 272k tokens, $4.00 above that.
Output: $10.00 up to 272k tokens, $15.00 above that.
Cache read: 95% off the input price.
Service tiers: flex and priority. Flex is billed at 0.5× the listed token prices and priority at 2×.

Perplexity says charges are based on actual token consumption, and every API response includes exact token counts.

Perplexity

AI-powered answer engine — ask anything and get cited, real-time answers from across the web.

Sources