gemini-4-hydrogenCompare gemini-4-hydrogen API pricing, supported endpoints, capabilities and access options on Modelsell.
Compare prices and service performance for this model across suppliers.
| Supplier | Discount | Input/M | Output/M | Cache Read/M | ||||
|---|---|---|---|---|---|---|---|---|
Google AI Studio 谷歌官方接口 | -50% | $0.75 | $3.75 | $0.0375 | ||||
Google Vertex 谷歌官方接口 | -30% | $1.05 | $5.25 | $0.0525 |
Scroll horizontally to compare all prices and performance metrics.
SentencePiece (Gemini)Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·Gemini 4 Hydrogen
This model is not included in the current benchmark snapshot.
Missing models or measurements are not zero scores.
Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.
资料核实日期:2026-11-13。模型 ID:gemini-4-hydrogen,发布于 2026-11-12。
Gemini 4 Hydrogen 是 Google 面向日常编程、智能体与企业工作流的多模态推理模型,侧重速度和效率。支持文本、图片、音频、视频及文档输入,输出文本;知识截止日期为 2026 年 3 月,参数量未公开。
输入与输出共用 1,048,576 token 预算,输出包含思考、函数调用和最终回答。流式与非流式单段输出均最多 65,536 token;官方通过 GenerateContent(v1beta1)或 Interactions API 的续写机制,可将总输出扩展至 1,048,576 token 减去输入用量。元数据中的最大输出记录官方续写总上限;本站普通单次请求与渠道支持范围需另行验证。
模型支持函数调用、结构化输出、代码执行、搜索、URL 上下文、计算机操作和视频理解。官方还支持 PDF、Word、PowerPoint、Excel 与 OpenDocument 文件。相关工具及文件格式能否经由本站调用,取决于具体渠道和接口适配。
思考等级为 LOW、MEDIUM、HIGH(默认)和 XHIGH;thinking_budget 与 MINIMAL 会报 400。自定义 temperature、top_p、top_k 被忽略。支持至少 4,096 token 前缀的隐式缓存,默认开启持久缓存,不支持显式 cached_content。
该模型属于短期 GA 版本,官方承诺至少提前 45 天通知退役;当前没有公布退役日期。
单位为美元 / 百万 token。以下标准价格覆盖文本、图片、视频和音频输入,输出价格包含思考 token;官方未为 Hydrogen 列出长上下文分档加价。
| 模式与区域 | 输入 | 输出 | 缓存读取 |
|---|---|---|---|
| Standard / Global(本站基础价) | 1.50 | 7.50 | 0.075 |
| Standard / Non-global | 1.65 | 8.25 | 0.0825 |
| Priority / Global | 2.70 | 13.50 | 0.135 |
| Priority / Non-global | 2.97 | 14.85 | 0.1485 |
| Batch / Global | 0.75 | 3.75 | 0.0375 |
| Batch / Non-global | 0.825 | 4.125 | 0.04125 |
官方公布 Standard / Global 缓存写入价为 $1.875,2027-01-12 起生效;当前不将该未来价格加入本站计费配置。Priority、Batch 和非 Global 价格仅作参考,本站基础配置采用 Standard / Global,实际费用叠加所选分组倍率。
搜索等工具可能另行收费。官方自 2026-11-13 起,对输出超过 32K token 的长生成,即使最后因客户端或服务端超时失败,仍可能收取可取回的 token 用量费用;这是 Google 的上游计费规则。
绑定支持该模型的渠道后,可以使用本站 Gemini 原生接口。以下示例依据官方参数和本站鉴权方式编写,尚未完成该模型的真实调用验证。
POST /v1beta/models/gemini-4-hydrogen:generateContent
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
{
"contents": [
{
"role": "user",
"parts": [{ "text": "分析这段程序的边界条件,并给出可验证的改进建议。" }]
}
],
"generationConfig": {
"maxOutputTokens": 8192,
"thinkingConfig": { "thinkingLevel": "MEDIUM" }
}
}
也可在支持的渠道通过 POST /v1/chat/completions 指定 model: "gemini-4-hydrogen"。不要发送 thinking_budget、MINIMAL 或显式缓存引用;多轮工具调用应保留完整的思考签名与历史内容。Interactions API、长输出自动续写和官方内置工具均须另外确认本站适配与渠道支持。
/v1beta/models/gemini-4-hydrogen:generateContent| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Replace <YOUR_API_KEY> with the API key from your token settings.
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| Google AI Studio | Unlimited | Unlimited | Unlimited |
| Google Vertex | Unlimited | Unlimited | Unlimited |
No restriction
Compare gemini-4-hydrogen API pricing, supported endpoints, capabilities and access options on Modelsell.
Create an API key with access to gemini-4-hydrogen, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
The model catalog lists a context window of 1048576 tokens. Check the selected endpoint for request limits.
The model catalog lists a maximum output of 1048576 tokens. Your request settings may set a lower limit.
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.
