DeepSeek V4.1 Flash Uncensored · Try it →
Catalog
OpenAIPartner-hosted · no ZDR

GPT-5.6 Luna

GPT-5.6 Luna is the low-priced Luna tier of OpenAI's GPT-5.6 generation, which preceded GPT-6; its weights are closed. Through our API it reads images as well as text, reasons before answering, calls tools and returns structured output, with a context of about a million tokens. It is served by a third-party inference provider through our partner, not on Heabsy hardware: the same key and the same invoice, but no zero data retention, and the request may be processed outside the EEA.

model id: gpt-5.6-luna

from openai import OpenAI client = OpenAI(    api_key="hb-...",    base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create(    model="gpt-5.6-luna",    messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)

Use it in Claude Code · OpenCode · Cline · Kilo Code · SillyTavern · n8n

Models we run ourselves, behind the same key

GPT-5.6 Luna on this page is partner-hosted: no zero data retention, and the provider handles the request under its own policy. The same API key also reaches models we serve on our own GPUs without storing prompts or completions — Qwen3.8 27B for coding and agents, which also runs Claude Code through our Anthropic-compatible endpoint, and MiMo V2.6 Flash with a million-token context.

This page · partner-hosted
GPT-5.6 Luna
$0.24 / $1.44
input / output per 1M tokens
Heabsy · EEA
Qwen3.8 27B
$1.05 / $3.15
input / output per 1M tokens

Our flagship for coding, agents and documents; every speed figure on this site was measured on it.

Heabsy · EEA
MiMo V2.6 Flash
$0.50 / $1.50
input / output per 1M tokens

Xiaomi's agent model with a million-token context, image input, reasoning and tool calling.

Context
1M tokens
Serving
Partner provider · no ZDR
Tool calling
Reasoning
Structured output
Vision
Input
$0.24/ 1M
Cached input
$0.024/ 1M
Output
$1.44/ 1M

Price list, updated 30 October 2026. No minimum spend, no subscription.

Claude and GPT through Heabsy: what changes

The weights of these models are closed, so nobody but the developer and the providers it works with can run them — including us. We pass your request to a partner provider and bill it on our invoice, with the same key you use for every other model in the catalogue.

What you do not get here is what our own models offer: there is no zero data retention, the provider handles the request under its own policy, and processing is not guaranteed to stay in the EEA. For personal or regulated data, use a model on Heabsy hardware.

Technical details

Context window
1M tokens
Max output
128,000 tokens
Throughput limit
—
Tokenizer
Other
Streaming
yes
Open weights
—
Supported parameters
max_tokens
1 … 128000
Partner-hosted: same key and invoice, no ZDR

This model is served by a third-party inference provider through our partner, not on Heabsy hardware. You keep one key and one invoice from an EU company, but there is no zero data retention: the provider handles the request under its own policy, and processing may take place outside the EEA. For personal or regulated data, use a model on Heabsy hardware.

Questions about this model

›Where is GPT-5.6 Luna computed?

At a third-party inference provider that serves this model through our partner, outside our own infrastructure. Where exactly the request is computed is not fixed and may be outside the EEA. The contract and the invoice stay with our EU company.

›Does GPT-5.6 Luna store prompts and completions?

There is no zero-data-retention guarantee for this model: the request goes to a third-party provider, which handles it under its own policy and may keep logs. For personal or regulated data, use a model on Heabsy hardware.

›How large is the GPT-5.6 Luna context window?

1M tokens, with up to 128,000 tokens of output.

›What does GPT-5.6 Luna cost?

$0.24 per million input tokens and $1.44 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.

›Is there a throughput limit on GPT-5.6 Luna?

The catalog does not report a throughput limit for this model.

Compare with similar models

ModelDeveloperParametersContextLicenceInput / 1M
GPT-5.6 LunaOpenAI—1M—$0.24
GPT-6 LunaOpenAI—1M—$0.12
gpt-oss-120bOpenAI117B / 5.1B125KApache-2.0$0.70
GPT-5.6 SolOpenAI—1M—$2.40

36 more models behind the same key and the same invoice.

Browse the catalog