Google · Preview
Gemini 4 Carbon
Launched 2026-10-28
Prices updated . Benchmarks updated .
Google's preview model. It is not on a public API yet, so there is no token price here.
You send / 1M
TBA
tokens in
It replies / 1M
TBA
tokens out
Context
TBA
tokens it can read at once
Typical request
TBA
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| CritPtHigh effort | 36.0% | Independent | 2026-10-28 | CritPt, republished by Epoch AI |
| Arena Elo (text)High effort | 1,540 | Independent | 2026-10-28 | LMArena |
| Arena Elo (webdev)High effort | 1,768 | Independent | 2026-10-28 | LMArena |
What it can do
- Reads: text
- Writes: text
- Weights: Closed
- Reasoning: n/a
- Tool calling: n/a
Our coverage
Compare with
Appears in
Estimate your monthly cost with Gemini 4 Carbon
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.