We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
google/gemini-4-argonGoogle's Gemini 4 flagship, thinking before it answers
Gemini 4 Argon is the flagship of Google's Gemini 4 family. It reasons before it answers, which suits problems where a quick reply is not enough. On Tchavi it takes a 1M-token window and writes up to 65K tokens in one reply.
It reads text, images and PDFs in a single request, calls functions and returns structured JSON, with both json_object and json_schema. Think of it for research synthesis, reviewing long technical documents, analysing charts and scans, or agents that must plan their steps.
On Tchavi you pay with mobile money, no international bank card and no KYC, and one API key opens 80+ other models. OpenAI-compatible: swap the base URL, keep your SDK. Your credits never expire.
Works the problem through first, for harder questions
Text, images and PDF documents in a single request
About a million tokens in a single request
Function calling, json_object and json_schema
Enough for a full report in one reply
Read this 80-page contract and list every clause that conflicts with the payment schedule, quoting the passages and explaining each conflict.
Plan a multi-step agent that reconciles mobile-money transactions with invoices: the tools it needs, the order of calls and what it does when amounts do not match.
Claude Sonnet 5.5 (model: "claude-sonnet-5-5") and Gemini 4 Argon both read images and documents and call tools. Argon opens a 1M-token window and thinks before every answer, so expect a few seconds of wait. Test both on your own task.
Because it reasons first. We measured 3 to 18 seconds per answer. For instant chat or autocompletion, a Flash model such as Gemini 3.1 Flash Lite (model: "gemini-3.1-flash-lite") fits better.
frequency_penalty, presence_penalty, n greater than 1, seed, reasoning_effort set to "minimal" or "xhigh", and verbosity. The API returns an error for each; it never ignores them silently.
Yes: images and PDF documents in, text out. JSON mode accepts json_object and json_schema.
Swap the base URL for Tchavi's, use your Tchavi key and set model: "gemini-4-argon" on /v1/chat/completions. The rest of your code stays the same.
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-argon',
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-argon`).
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.
top_p1Nucleus sampling: only tokens in the top `top_p` probability mass are considered.
seedInteger seed for deterministic output. The same seed + identical request yields the same completion when supported by the provider. OpenAI honours it; Anthropic ignores.
n1Number of completions to generate in one call. Defaults to 1; each extra completion is billed.
stream_optionsStreaming options, e.g. `{ "include_usage": true }` to receive a final SSE chunk with usage counts. Effective only when `stream: true`.
stopUp to 4 sequences where the API will stop generating further tokens.
frequency_penalty0Between -2.0 and 2.0. Positive values penalize tokens that have appeared frequently.
presence_penalty0Between -2.0 and 2.0. Positive values encourage the model to talk about new topics.
userEnd-user identifier passed to the upstream provider for abuse / moderation tracking. Should be stable per end-user.
logit_biasPer-token logit bias `{ "<tokenId>": <-100..100>, ... }`. OpenAI-specific; Anthropic ignores silently.
messages[].content[].image_urlAttach an image on a user message. Pass a content block `{ "type": "image_url", "image_url": { "url": ... } }`. PNG / JPEG / WebP, up to 4 per request. Only models with `supportsImageInput: true` accept this block (e.g. `gpt-4o`, `claude-opus-4-7`).
messages[].content[].document_urlAttach a PDF on a user message. Pass a content block `{ "type": "document_url", "document_url": { "url": ... } }`. Up to 5 PDFs per request. Only models with `supportsDocuments: true` accept this block (e.g. `claude-sonnet-4-6`, `gpt-4.1`).
Estimated over 30 days, for a typical message: ~500 input + ~150 output tokens, billed to the thousandth of a credit.