# Gemini 4 Hydrogen Usage, Cost & Rank | OpenCode Data

> Gemini 4 Hydrogen costs $1.50 per 1M input tokens and $7.50 per 1M output tokens.

Google's Gemini 4 model for everyday coding and agentic workflows, with four thinking levels and a 1M-token context window

- Page: https://opencode.ai/data/google/gemini-4-hydrogen
- JSON: https://opencode.ai/data/google/gemini-4-hydrogen.json
- Model ID: google/gemini-4-hydrogen
- Lab: Google

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 1M |
| Max output | 66K |
| Knowledge cutoff | 2026-03 |
| Release date | 2026-11-12 |
| Input modalities | text, image, video, audio, pdf |
| Output modalities | text |
| Reasoning | Yes |
| Tool calling | Yes |
| Open weights | No |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $1.50 | $7.50 | $0.07 | - |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| SWE-sweep | 13.5 | % | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |
| Terminal-Bench | 57 | cheating-adjusted | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |
| Agents' Last Exam | 71.6 | score | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |
| AutomationBench-AA | 76.1 | % | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |
| Vending-Bench | 14549 | bank balance (USD) | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |
| OSWorld | 77.6 | offline subset | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |
| MKA | 53.4 | Climb WSR accuracy | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |
| Chartography | 66.6 | % | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |
| Terminal-Bench-Science | 51.4 | % | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |
| HLE-Diamond | 58.8 | % | https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/ |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.