We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
google/gemini-3.5-flash-liteThe fast Gemini for sorting, extracting and replying at volume
Gemini 3.5 Flash-Lite is Google's model for high-volume work, stable since July 2026. It sits between Gemini 3.1 Flash-Lite, which costs less, and Gemini 3.8 Flash, for harder tasks.
By default it answers without a thinking phase: 2 to 3 seconds in our tests. It reads text, images and PDFs in a one-million-token window, calls tools and returns JSON. A good fit for sorting customer messages, pulling the figures out of an invoice or translating in bulk.
On Tchavi you pay with mobile money, with no international card and no KYC, and one API key covers 80+ models. It is OpenAI-compatible: change the base URL, keep your SDK.
Measured in our tests, with no thinking phase by default
About a million input tokens in a single request
Invoices, screenshots and documents read directly
Function calling and structured output
Up to 65,536 tokens per answer
Read this PDF invoice and return the supplier, the total including tax and the due date as JSON.
Sort these 200 customer reviews by theme: delivery, price, quality or service.
Translate these product sheets into English, keeping the fabric names in French.
Both are built for volume. Gemini 3.1 Flash-Lite (model: "gemini-3.1-flash-lite") costs less; 3.5 Flash-Lite is the next generation. Try both on a sample of your requests before choosing.
Yes. Send images and PDFs in the message: it reads them alongside your text and answers in text.
Up to 1,048,576 input tokens, and up to 65,536 tokens per answer.
Not by default. In our tests it answered with no reasoning tokens at all, which keeps it fast and its cost per request predictable.
Point the base URL at Tchavi, use your Tchavi key and set model: "gemini-3.5-flash-lite" 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-3.5-flash-lite',
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-3.5-flash-lite`).
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.