We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
openai/gpt-6.2-astraGPT-6.2 Astra, OpenAI's new record-setter, 20% under GPT-6 Astra
GPT-6.2 Astra is OpenAI's top GPT-6.2 model. OpenAI reports a new record on Agents' Last Exam, 5.2 points above GPT-6 Astra at under a third of the cost, and a lead on GDPval v2 with 22% fewer output tokens. A typical message (500 tokens in, 150 out) costs 21.95 credits, about 7.3 F CFA. Same 1.05M context and 128K output.
Last updated Nov 19, 2026
OpenAI reports a new record on Agents' Last Exam and on Terminal-Bench-Science, 9 points above GPT-6 Astra
Trained for slides, spreadsheets and documents that follow professional conventions
Better code and better interfaces, including 3D, according to OpenAI
A whole repository or a year of reports in, a full migration diff or report out, with images and documents accepted
Here is our monorepo's payment module and its 300 failing tests. Find the root cause, fix it, and explain why the other 299 failures follow from it.
Turn these three quarterly exports into a board deck: ten slides, one chart per slide, and a spreadsheet with the formulas visible.
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-6.2-astra',
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-6.2-astra`).
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.
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.
This model costs more upstream once a prompt passes a threshold, and we pass that through rather than cap the window or raise the price for everyone. The rate above is the first band.
| Prompt length | Input / 1K | Output / 1K |
|---|---|---|
| Under 272K tokens | ||
| 272K tokens and above |
The threshold counts every input token on the request, cached ones included: a 95K cache hit plus 10K of new prompt is a 105K prompt. Output is priced by the prompt’s length, so a long prompt with a short answer still pays the higher output rate.
Estimated over 30 days, for a typical message: ~500 input + ~150 output tokens, billed to the thousandth of a credit.