We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
openai/gpt-6-astraOpenAI's most capable GPT, for the hardest work
GPT-6 Astra is the top of the GPT-6 family, released by OpenAI on 3 September 2026. OpenAI presents it as its most capable model for the most demanding work.
It targets tasks that run from an initial request to a finished result: hard reasoning, system-scale coding, computer use, research, document writing. 1.05M tokens of context, up to 128K of output, image input, reasoning effort from low to max.
On Tchavi you pay with mobile money, no card and no KYC. One API key opens 100+ models: compare Astra with Sol on your real prompts without opening a second account.
OpenAI's most capable model, according to OpenAI
A whole codebase or case file in one call, up to 128K of output
Set reasoning per request: low, medium, high, xhigh or max
Multi-step analysis, system-scale code review, research synthesis
Reads charts, screenshots and diagrams alongside your text
Strict JSON output — but not function tools on this path
Audit this codebase for security issues. Verify each finding against the real execution path, drop anything you cannot prove is reachable, and propose a minimal fix for each remaining flaw.
Plan a zero-downtime migration from a single Postgres instance to read replicas: steps, validation criteria and a rollback path for each one.
Sol is the default for coding and agents. Take Astra, which OpenAI calls its most capable model, for problems where a lower tier has already failed.
Astra belongs to the GPT-6 generation, newer than GPT-5.5. GPT-5.5 stays useful if your prompts are already validated on it; test Astra on your hardest cases.
1.05M tokens of context and up to 128K of output. It accepts images and documents as input and returns text.
Per OpenAI: low, medium (default), high, xhigh and max. The none level is not available on Astra.
No: the model rejects them, so Tchavi strips them from the request. Steer it with your instructions and the reasoning effort.
Swap the base URL for Tchavi's, use your Tchavi API key and set model: "gpt-6-astra".
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-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-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.
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`).
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.