Perplexity Agent API adds Gemini 4 Hydrogen and unlists three older Gemini Flash models (November 2026)
google/gemini-4-hydrogen is on the Agent API at $1.50 in and $7.50 out per 1M tokens. Gemini 3.6, 3.7 and 3.8 Flash left the model docs.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
- Perplexity API keyPERPLEXITY_API_KEYGet key
Open the API Keys page in the Perplexity API console and generate a key. Add credits in Billing first.
What changed
Perplexity's changelog (November 2026) says the Agent API now supports google/gemini-4-hydrogen.
Price per 1M tokens:
- input: $1.50
- cached input: $0.075
- output: $7.50, and reasoning tokens are billed at the output rate
The same entry says google/gemini-3.6-flash, google/gemini-3.7-flash and google/gemini-3.8-flash are no longer listed in the Agent API model docs, pricing calculator or examples. The models page now lists three Google models: google/gemini-4-argon, google/gemini-4-carbon and google/gemini-4-hydrogen.
What to do
- To try it, set
modeltogoogle/gemini-4-hydrogenin your Agent API request. The Perplexity SDK reads the key fromPERPLEXITY_API_KEY. - It is the lowest priced Google model on the models page. Argon and Carbon are $2.00 input, $0.10 cached input and $10.00 output, and that is introductory pricing through November 30, 2026.
- If your code sends one of the three older Gemini Flash IDs, test a listed model now and plan the move.
Not confirmed
- The changelog does not say whether requests to the three older Gemini Flash IDs still work, and it gives no shutdown date.
- The entry has no day, only "November 2026".
- The models page does not state a context window for the Google models. It links to Google's model docs.
