Gemini 4 Hydrogen is Google's high-efficiency model in the Gemini 4 family, built for high-throughput agentic workflows and coding. It is a proprietary model available through Google's API and via OpenRouter. The price listed here is the OpenRouter listed price, checked Nov 18, 2026: $1.50 per million input tokens and $7.50 per million output tokens. No cached input rate is available from OpenRouter for this model.
Gemini 4 Hydrogen supports a 1,048,576-token context window and a maximum output of 943,718 tokens — one of the largest output limits among frontier models. It supports function calling and streaming. It does not support vision input according to the OpenRouter listing.
Within the Gemini 4 family, Hydrogen is positioned as the efficient workhorse variant. Gemini 4 Carbon ($2.00/$10.00) is the multimodal frontier variant with vision, audio, and video input support. Gemini 4 Argon is the reasoning-focused variant in the family.
Data source: OpenRouter listing, checked Nov 18, 2026. Data confidence: Partial — benchmark scores are not available for this model at this time. The OpenRouter listed price may differ from Google's direct API pricing; check ai.google.dev for the current official rate.
Gemini 4 Hydrogen is suited to high-throughput agentic workflows, coding tasks, and long-context applications where the 1M+ context window and large output limit are valuable. Its $1.50/$7.50 pricing makes it competitive with other efficient frontier models for cost-sensitive production deployments.
Input price vs 143 frontier models tracked. Avg: $5.58/1M.
| Model ID | gemini-4-hydrogen |
| Provider | |
| Model Family | Gemini 4 |
| Tier | Frontier |
| Context Window | 1,048,576 tokens (1.0M) |
| Max Output Tokens | 943,718 tokens |
| Input Price | $1.5 / 1M tokens |
| Output Price | $7.5 / 1M tokens |
| Cached Input Price | Not available |
| Throughput | — |
| Latency (P50) | — |
| Intelligence Score | — |
| LiveBench Score | — |
| Cost per Task (LiveBench) | — |
| Data Confidence | Partial |
| HLE Score | — |
| GPQA Diamond | — |
| SWE-bench Score | — |
| OSWorld Score | — |
| BrowseComp Score | — |
| Terminal-Bench Score | — |
| AutoBench Score | — |
| Parameters | — |
| Vision Support | No |
| Function Calling | Yes |
| Streaming | Yes |
| Reasoning Model | No |
| Open Weights | No |
| Data Source | Static (verified) |
| Last Updated | 2026-11-18 |
Self-hosting gemini-4-hydrogen? These GPUs are well-matched for this model's compute and memory requirements.