We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
openai/gpt-6.2-solGPT-6.2 Sol, OpenAI's everyday model, at GPT-6.1 Sol's rates
GPT-6.2 Sol keeps GPT-6.1 Sol's per-token rates exactly, 4.4 credits per 1K input, and OpenAI calls it its default for everyday work. OpenAI reports a gain of 5.3 points over GPT-6.1 Sol on GDPval v2 and results within 0.5 point of Astra on FrontierCode 2.0 for about a fifth of the cost. A typical message (500 tokens in, 150 out) costs 5.5 credits, about 1.8 F CFA.
Last updated Nov 19, 2026
Per-token rates identical to GPT-6.1 Sol, with a reported 5.3 point gain on GDPval v2
Within 0.5 point of GPT-6.2 Astra on FrontierCode 2.0 for about a fifth of the cost
OpenAI says it gets better results on demanding tasks with fewer output tokens
A whole repository or forty invoices in one call, with images and documents accepted
Review this pull request for race conditions around our credit deduction and propose a patch with the tests that prove it.
Read these 60 mobile money statements and return one JSON row per month, flagging every transaction without a matching invoice.
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-sol',
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-sol`).
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.