We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
openai/gpt-5-miniMost of GPT-5, built for everyday text work
GPT-5 mini is the compact version of GPT-5, launched by OpenAI on 7 August 2025 alongside GPT-5 and GPT-5 nano. It keeps 400K of context and up to 128K of output, for text.
It suits repetitive work that runs all day: assistants, support-thread summaries, copy rewriting and translation, field extraction from plain text, drafts before a human edit. Function calling, JSON output and streaming come with it.
On Tchavi you pay with mobile money, no card and no KYC, and credits never expire. One API key covers 80+ models: when a text needs more depth, switch to GPT-5 by changing one string.
Long threads, reports or conversation histories in one call
Room for long texts or whole batches
Reads images and documents alongside text
Function calling and structured JSON output
Show the answer as it is written
Write three versions of a WhatsApp message promoting my sandwich restaurant: one warm, one short and direct, one with a daily special. Under 40 words each.
Translate to French in a warm, professional tone: "Welcome to our shop, pickup available in store from tomorrow". Give two variants.
Mini for text at volume: assistants, summaries, rewriting, extraction. GPT-5 for the deepest reasoning.
Nano for the mechanical steps of a pipeline: routing, tagging, filtering. Mini when the text needs better writing or reasoning while staying on a compact model.
GPT-5.4 mini is the next generation. Keep GPT-5 mini if your text prompts are already validated on it.
400K tokens of context, up to 128K of output. It reads images and PDFs as well as text.
Swap the base URL for Tchavi's, use your Tchavi API key and set model: "gpt-5-mini". 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: 'gpt-5-mini',
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. `gpt-5-mini`).
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.
reasoning_effortReasoning depth on OpenAI o-series / GPT-5 reasoning models. Values `"low"`, `"medium"`, `"high"`. Silently ignored by non-reasoning OpenAI models.
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`).
parallel_tool_callstrueWhether the model may call multiple tools in parallel within one turn. Set `false` to force serial tool calls. Only with `supportsTools: true` (OpenAI).
Estimated over 30 days, for a typical message: ~500 input + ~150 output tokens, billed to the thousandth of a credit.