NewGPT-6.2 Astra, GPT Image 2.6, Kling V4 and Kimi K3.1 Pro are now available.

Tchavi
ModelsStudioPricingDocsBlog
Tchavi
  • Why Tchavi
  • Models
  • Pricing

Tchavi is an OpenAI-compatible AI API: 100+ models, from text to video, topped up with mobile money in FCFA or your local currency, no bank card needed.

  • support@tchavi.com
  • Support

Popular models

  • GPT-6 Sol API
  • Claude Sonnet 5.5 API
  • Claude Opus 5.5 API
  • Gemini 4 Argon API
  • DeepSeek V4.1 Flash API
  • Nano Banana 2.1 (images)
  • GPT Image 2 (images)
  • Wan 3.0 (video)
  • All 100+ models

Developers

  • Quickstart
  • API Reference
  • Claude Code
  • Cursor
  • SDKs

Resources

  • Documentation
  • Blog
  • Image models
  • Video models
  • Music models
  • Audio models
  • Mobile money payments
  • Pay for AI APIs with M-Pesa
  • Claude Code with mobile money

Legal

  • Privacy
  • Terms of Service

APIs by creator

  • OpenAI API
  • Gemini API
  • Claude API
  • Qwen API
  • DeepSeek API
  • Seedance API
  • MiniMax API
  • Mistral API

Mobile money payments · Available in 12 countries: Benin, Cameroon, Congo, Côte d'Ivoire, DR Congo, Gabon, Kenya, Rwanda, Senegal, Sierra Leone, Uganda, and Zambia. Operators: Moov Money, MTN MoMo, Airtel Money, Orange Money, M-Pesa, Free Money, and Zamtel Kwacha.

© 2026 Tchavi. All rights reserved.

We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.

Back to models

GPT-6.2 Astra

openai/gpt-6.2-astra

GPT-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.

Modalities
Input / Output
17.56 / 87.798cr / 1K
Context window
1.1M
Max output
128K
Capabilities
  • JSON mode
  • Vision
  • PDF
  • Streaming
  • Prompt caching· read 0.878 cr / 1K

Last updated Nov 19, 2026

What this model does well

  • 🎯

    Agentic work, per OpenAI

    OpenAI reports a new record on Agents' Last Exam and on Terminal-Bench-Science, 9 points above GPT-6 Astra

  • 📊

    Professional documents

    Trained for slides, spreadsheets and documents that follow professional conventions

  • 💻

    Cleaner code and interfaces

    Better code and better interfaces, including 3D, according to OpenAI

  • 📚

    1.05M context, 128K output

    A whole repository or a year of reports in, a full migration diff or report out, with images and documents accepted

Example prompts

  • 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.

Good to know

  • Function tools are not accepted on /v1/chat/completions, which is the path Tchavi uses. OpenAI returns `Function tools with reasoning_effort are not supported for gpt-6.2-astra`, and this model also rejects the `reasoning_effort: 'none'` workaround, so there is no way to use function tools on it here. Use GPT-5.4 or another tool-capable model for tool loops.
  • Prompts over 272K input tokens are billed by OpenAI at 2x input and 1.5x output for the whole request, and Tchavi applies its own long rate to match. Keep very long prompts for the cases that need them.
  • OpenAI says this model reaches the Critical threshold for cyber capability and ships with reinforced guardrails that, in OpenAI's own words, also limit some legitimate vulnerability research and security testing workflows. If you are buying it for security work, expect refusals and test before you spend.
  • It emits reasoning tokens, which are billed as output, so a short answer can cost more than its visible length suggests. Check the usage field on your first calls.
We never save what you send to a model or what it returns. We log only your settings (like size or voice) and how much was used, for billing. Files you attach in the playground are deleted after 24 hours.

Technical specifications

Provider
openai
API identifier
gpt-6.2-astra
Category
Chat & Text
Context window
1,050,000 tokens
Max output
128,000 tokens
Rate limit
500 RPM
Billing unit
token
Streaming
Yes

Ideal for

  • Hard coding tasks across a whole repository
  • Slides, spreadsheets and reports for clients
  • Long agentic analysis where quality matters most
  • Structured extraction from large document sets

Ready to try it?

Test this model in the playground, no setup needed.

Frequently asked questions

Can I pay with mobile money, without a bank card?

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.

Is the API compatible with OpenAI's?

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.

API

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);

API parameters

Every parameter this model accepts on the API. Check the SDK for full typings.

modelRequired
string

ID of the chat model (e.g. `gpt-6.2-astra`).

messagesRequired
Array<{ role, content }>

Conversation 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`).

temperature
number
Default: 1

Sampling temperature between 0 and 2. Higher values = more random.

max_tokens
integer

Maximum number of tokens to generate in the response.

max_completion_tokens
integer

OpenAI alias for `max_tokens`. Either field works; if both are sent, `max_completion_tokens` wins.

stream
boolean
Default: false

If true, partial message deltas are streamed as Server-Sent Events.

response_format
{ type: "json_object" | "text" }

Constrain 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_effort
"low" | "medium" | "high"

Reasoning depth on OpenAI o-series / GPT-5 reasoning models. Values `"low"`, `"medium"`, `"high"`. Silently ignored by non-reasoning OpenAI models.

Pricing

per 1,000 tokens
17.56 credits
Input 17.56 · Output 87.798 cr/1K

How billing works

  • Billed per token used, down to a thousandth of a credit.
  • A typical message (500 in, 150 out) costs about —, or 21.95 credits.
  • Prompt cache reads: — per 1K tokens (0.878 credits).

Long-prompt pricing

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 lengthInput / 1KOutput / 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.

Real-world scenarios
Per day
Per week
Per month

Estimated over 30 days, for a typical message: ~500 input + ~150 output tokens, billed to the thousandth of a credit.

A 10 000 F CFA top-up gives you about ~1 366 questions. Pay with Orange Money, MTN MoMo or M-Pesa, no Visa card needed.

Ready to use GPT-6.2 Astra?

Create your accountAPI Documentation

Bonus credits on your first top-up · No card to sign up