Gemini 4 Neon launches at $3/$15 on the Gemini API paid tier
Google's new middle Gemini 4 model sits between Hydrogen and Carbon, with no free tier.
Google released Gemini 4 Neon on November 18, 2026, as gemini-4-neon on the paid tier of the Gemini API. Google places it between Gemini 4 Hydrogen and Gemini 4 Carbon for complex coding, knowledge work and science tasks. It lists at $3.00 input and $15.00 output per million tokens.
What changed
- New stable model ID
gemini-4-neon, generally available throughgenerateContentand the Interactions API. It is also in Google AI Studio for Google AI Pro and Ultra plans. - Paid tier only. Google's pricing page says Neon is not available on the free tier, and thinking tokens bill as output.
- One 1,048,576-token window shared by input, thinking and output. Max output is 65,536 tokens per request, or up to 1,048,576 with long decode.
- Inputs: text, image, video, audio and PDF. Output: text. Thinking levels
low,medium,high(default) andxhigh. - Context caching is implicit only. Batch, Flex and Priority inference are supported. Google's deprecations page lists no shutdown date.
Google list prices
Paid tier, per million tokens, from the Gemini API pricing page on November 18, 2026.
| Tier | Input | Cached input | Output |
|---|---|---|---|
| Standard | $3.00 | $0.15 | $15.00 |
| Batch | $1.50 | $0.075 | $7.50 |
| Flex | $1.50 | $0.075 | $7.50 |
| Priority | $5.40 | $0.27 | $27.00 |
The Gemini 4 family on the same page, Standard paid tier:
| Model | Input | Output |
|---|---|---|
gemini-4-hydrogen | $1.50 | $7.50 |
gemini-4-neon | $3.00 | $15.00 |
gemini-4-carbon | $2.00 to Nov 30, then $4.00 | $10.00 to Nov 30, then $20.00 |
gemini-4-argon | $2.00 to Nov 30, then $4.00 | $10.00 to Nov 30, then $20.00 |
What to do
From another Gemini 4 model, Google says no request schema changes are needed:
- Change the model ID to
gemini-4-neon. - Neon defaults to
highthinking and supportsxhigh, like Hydrogen. Carbon and Argon default tomediumand cap athigh, so setthinking_levelif you want the old behavior. - Use a paid-tier project.
From Gemini 3.8 Flash or earlier, also remove temperature, top_p and top_k, stop sending the minimal thinking level (Neon rejects it), drop explicit cached_content calls, and raise low max_output_tokens caps to 65,536.
- "model": "gemini-4-carbon"
+ "model": "gemini-4-neon"Gemini 4 Neon is not in the RouterPlus catalog as of November 18, 2026. See Google models on RouterPlus.
