We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
openai/gpt-6-lunaGPT-6 efficiency for focused, high-volume tasks
GPT-6 Luna is the most efficient tier of the GPT-6 family, released by OpenAI on 22 September 2026 alongside Sol. OpenAI aims it at focused, high-volume work.
Classify tickets, tag reviews, pull fields out of a contract, triage emails: Luna keeps adjustable reasoning effort (none to max), image and document input, tools and JSON, with up to 128K of output.
On Tchavi you pay with mobile money, no card and no KYC, and credits never expire. One account and one API key for 100+ models: give Luna the bulk of the flow, step up to Sol only when needed.
Described by OpenAI as its most efficient model for focused, high-volume work
From none to max: none to triage, more to reason
Reads screenshots, scans and attached files alongside text
Function calling and structured JSON output
Room for long summaries or whole batches
Show the answer as it is written
Here are 200 product reviews. Tag each with a sentiment (positive, neutral, negative) and the feature it talks about most. Answer in JSON, one object per review.
Extract every date, amount and counterparty from this contract, with the source sentence. Return JSON and flag any ambiguous value instead of guessing.
For each of these emails, decide: human reply needed or automatic acknowledgement? Give a one-sentence reason.
Luna for focused, high-volume tasks: classify, tag, extract, triage. Sol as soon as the job needs multi-step reasoning, code or complex documents.
Luna belongs to the GPT-6 generation, with adjustable reasoning effort and image and document input. GPT-4o mini stays an option if your text pipeline already runs on it.
Yes: images and documents in, text out, up to 128K tokens of output. Well suited to triaging scans or screenshots in batches.
Yes: OpenAI offers the none effort on Luna, plus low, medium (default), high, xhigh and max. Set it per task difficulty.
No: the model rejects them, so Tchavi strips them from the request. Pin the format with your instructions and JSON mode.
Swap the base URL for Tchavi's, use your Tchavi API key and set model: "gpt-6-luna".
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-luna',
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-luna`).
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).
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.