We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
openai/gpt-5-nanoThe GPT-5 tier for mechanical, high-volume pipeline steps
GPT-5 nano is the smallest model of the GPT-5 family, launched by OpenAI on 7 August 2025 alongside GPT-5 and GPT-5 mini. It keeps 400K of context and up to 128K of output, for text.
It is built for the mechanical steps of a pipeline: routing a message to the right queue, tagging at scale, pulling structured data out of text, first-pass filtering, driving a scripted assistant. Function calling, JSON output and streaming are available.
On Tchavi you pay with mobile money, no card and no KYC, and credits never expire. One API key for 80+ models: nano for the sorting, GPT-5 mini or GPT-5 for the judgement.
Whole batches of messages or texts to process in one call
Classification, routing and first-pass filtering
Reads images and documents alongside text
Function calling and structured JSON output
Room to return a full tagged batch
Show the answer as it is written
Here are 50 customer messages. For each one, return JSON with the destination queue (billing, technical, sales) and urgency (low, medium, high).
Extract the name, phone number and city of each person mentioned in this text. Return JSON and use null when the information is missing.
Nano for mechanical steps: routing, tagging, simple extraction, filtering. Mini as soon as the output needs better writing or real reasoning.
Nano is GPT-5 generation with 400K of context. GPT-4o mini stays an option if your pipeline already runs on it; test both on a sample.
GPT-5.4 nano is the next generation, also text only. Keep GPT-5 nano if your pipeline is already validated on it, try 5.4 for new flows.
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-nano". 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-nano',
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-nano`).
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.