We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
google/gemini-4-hydrogenGoogle's everyday and speed tier, with reasoning you pay for but never see
Gemini 4 Hydrogen is Google's everyday and speed tier, released on 12 November 2026. Google describes it as cutting-edge intelligence for everyday coding and agentic workflows. It takes text, images, audio, video and PDFs, returns text, and reads up to 1,048,576 tokens of context with up to 65,536 tokens of output.
Last updated Nov 19, 2026
It always reasons before it answers, and that cannot be switched off. The reasoning is billed as output tokens and you do not see it. In our own test, a short Python tracing question came back right in 12.2 seconds after 1,818 billed output tokens, of which 1,786 were reasoning: 98.2% of the billed output was invisible, for a visible answer of 30 characters. A price per million output tokens therefore tells you little about a request's cost. Try it on your own prompts first.
On Tchavi you pay with mobile money, no bank card and no KYC. One account and one API key open 100+ models, and your credits never expire.
Google's speed-oriented model: 12.2 s on our code-tracing test
A codebase or a stack of long documents in a single call
Mixed input in one request, text out
Function calling and structured output for your agents
Gemini 4 Hydrogen always reasons before it answers, and that reasoning is billed as output tokens even though it is not shown. In our test, 1,786 of 1,818 billed output tokens (98.2%) were reasoning, for an answer of 30 characters.
No. It is always on for this model. If you want plain short replies, pick a lighter model from the catalogue.
The default reasoning effort is not the same on every route, so how much the model thinks, and therefore what you are billed, can vary between requests.
Up to 1,048,576 tokens in and 65,536 out. Reasoning counts in what you are billed, so set max_tokens with that in mind.
Swap the base URL for Tchavi's, use your Tchavi key and set model: "gemini-4-hydrogen" on /v1/chat/completions.
Yes. Top up your Tchavi account with Orange Money, MTN MoMo, M-Pesa or another mobile money operator. No bank card is needed. Credits land as soon as the payment is confirmed and are deducted as you use them.
Yes. Keep your current OpenAI SDK, just change the base URL to Tchavi's (shown in the API tab) and use your Tchavi key. The rest of your code stays the same.
import Tchavi from '@tchavi/sdk';
const client = new Tchavi({ apiKey: 'API_KEY' });
const response = await client.chat.completions.create({
model: 'gemini-4-hydrogen',
messages: [
{
"role": "user",
"content": "Hello!"
}
],
});
console.log(response.choices[0].message.content);
console.log('Credits used:', response.tchavi.credits_used);Every parameter this model accepts on the API. Check the SDK for full typings.
modelRequiredID of the chat model (e.g. `gemini-4-hydrogen`).
messagesRequiredConversation messages. Each item has a `role` (system/user/assistant) and a `content` that's either a plain string or an array of content blocks (`text`, `image_url`, `document_url`).
temperature1Sampling temperature between 0 and 2. Higher values = more random.
max_tokensMaximum number of tokens to generate in the response.
max_completion_tokensOpenAI alias for `max_tokens`. Either field works; if both are sent, `max_completion_tokens` wins.
streamfalseIf true, partial message deltas are streamed as Server-Sent Events.
toolsFunction-calling toolbox. Pass an array of `{ type: "function", function: { name, description, parameters } }`. Returned tool calls land in `choices[].message.tool_calls`. Only models with `supportsTools: true` accept this.
tool_choiceHow the model picks among tools: `"auto"` (default), `"none"` to force a plain text reply, or `{ type: "function", function: { name } }` to force a specific tool. Only with `supportsTools: true`.
response_formatConstrain the output. Pass `{ type: "json_object" }` to force valid JSON (the model still needs a JSON instruction in your prompt). Only models with `supportsJsonMode: true` honour this.
Estimated over 30 days, for a typical message: ~500 input + ~150 output tokens, billed to the thousandth of a credit.