gpt-6-lunaGPT-6 Luna is the efficiency tier of OpenAI's GPT-6 family — OpenAI's own description is its most efficient model for focused, high-volume tasks — released in September 2026 together with GPT-6 Sol. On APIMODELS it costs $0.09 per 1M input tokens and $0.45 per 1M output, 10% below OpenAI's $0.10 / $0.50 list, with cached input at $0.009. The specifications match Sol and Astra: a 1,050,000-token context window, 128,000 max output, text and image input, and a knowledge cutoff of 18 May 2026. reasoning_effort takes none / low / medium (default) / high / xhigh / max, and reasoning tokens are billed as output and count against max_tokens — set low or none for classification, extraction and other bulk work, which is where this tier earns its keep. Requests whose input exceeds 272K tokens bill input and cached input at 2× and output at 1.5×, the family's shared long-context tier. Call it through the OpenAI-compatible /v1/chat/completions or /v1/responses with one key; function calling works on both — we verified tool_calls coming back on /v1/chat/completions at the default reasoning_effort, so the reasoning_effort-none requirement in OpenAI's docs does not apply here. Failed requests are not charged.
View complete API reference with all parameters and examples.
Enable real-time streaming responses with Server-Sent Events.
{
"model": "gpt-6-luna",
"stream": true,
"messages": [...]
}Enable the model to use tools and call functions.
{
"model": "gpt-6-luna",
"tools": [{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "City name"}
},
"required": ["location"]
}
}
}],
"messages": [{"role": "user", "content": "What's the weather in Tokyo?"}]
}Get structured JSON responses from the model.
{
"model": "gpt-6-luna",
"response_format": {"type": "json_object"},
"messages": [{"role": "user", "content": "Extract info as JSON: John is 30 years old"}]
}| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model identifier (e.g., gpt-6-luna) |
| messages | array | Yes | Array of message objects with role and content |
| max_tokens | integer | No | Maximum tokens in the response |
| stream | boolean | No | Enable streaming responses (SSE) |
| temperature | number | No | Sampling temperature (0.0 - 2.0) |
| top_p | number | No | Nucleus sampling threshold (0.0 - 1.0) |
| tools | array | No | Function calling tools definition |
| response_format | object | No | Output format (e.g., json_object) |
View complete API reference with streaming, thinking, and more.
Billing: Cost = (input_tokens * input_price + output_tokens * output_price) / 1,000,000
$0.09 / $0.45 per 1M tokens against the $0.10 / $0.50 list; cached input $0.009
OpenAI: its most efficient model for focused, high-volume tasks — classification, extraction, routing
Same specs as Sol and Astra; text and image input; knowledge cutoff 18 May 2026
Reasoning tokens bill as output and count against max_tokens — use low or none for bulk work
GPT-6 Luna is a Large Language Model API provided by OpenAI. GPT-6 Luna is the efficiency tier of OpenAI's GPT-6 family — OpenAI's own description is its most efficient model for focused, high-volume tasks — released in September 2026 together with GPT-6 Sol. On APIMODELS it costs $0.09 per 1M input tokens and $0.45 per 1M output, 10% below OpenAI's $0.10 / $0.50 list, with cached input at $0.009. The specifications match Sol and Astra: a 1,050,000-token context window, 128,000 max output, text and image input, and a knowledge cutoff of 18 May 2026. reasoning_effort takes none / low / medium (default) / high / xhigh / max, and reasoning tokens are billed as output and count against max_tokens — set low or none for classification, extraction and other bulk work, which is where this tier earns its keep. Requests whose input exceeds 272K tokens bill input and cached input at 2× and output at 1.5×, the family's shared long-context tier. Call it through the OpenAI-compatible /v1/chat/completions or /v1/responses with one key; function calling works on both — we verified tool_calls coming back on /v1/chat/completions at the default reasoning_effort, so the reasoning_effort-none requirement in OpenAI's docs does not apply here. Failed requests are not charged. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: Input: $0.09, Output: $0.45 per 1M tokens.
Build intelligent conversational systems to automatically answer user queries and improve service efficiency.
Automatically write articles, emails, ad copy, and other text content to boost productivity.
Assist with code writing, debugging, and code review to accelerate software development.
Understand and analyze unstructured data, extract key insights, and generate summary reports.
GPT-6 Luna is available through APIMODELS at: Input: $0.09, Output: $0.45 per 1M tokens. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
APIMODELS offers the same GPT-6 Luna model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
$0.09 per 1M input tokens, $0.45 per 1M output and $0.009 for cached input — 90% of OpenAI's $0.10 / $0.50 / $0.01 list. When a single request's input exceeds 272K tokens, input and cached input bill at 2× and output at 1.5×, matching OpenAI's own long-context tier. Billing is per actual token, reasoning tokens count as output, and failed requests are free.
OpenAI describes Luna as its most efficient model for focused, high-volume tasks, with Sol as the workhorse tier. Here Luna is $0.09 / $0.45 and Sol is $1.00 / $5.00 — more than ten times apart. Use Luna for classification, extraction, routing, summarisation and log triage: high volume, low difficulty per item. Use Sol when you need stronger reasoning or long-horizon agents. The specs are identical: 1.05M context, 128K output, text and image input.
GPT-6 Luna defaults to reasoning_effort medium, and reasoning tokens count against max_tokens — in our test with max_tokens 300, all 300 tokens went to reasoning and no visible text came back. For bulk work set reasoning_effort to low or none, or leave max_tokens enough headroom for the reasoning.
POST https://api.apimodels.app/v1/chat/completions or /v1/responses with model gpt-6-luna and Authorization: Bearer your apimodels key; the OpenAI SDK only needs base_url changed. Streaming, function calling, JSON output and image input all work — we verified tool_calls coming back on /v1/chat/completions at the default reasoning_effort, so the reasoning_effort-none requirement in OpenAI's docs does not apply here.
On APIMODELS, GPT-6 Luna runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports 10% Below Official, High Volume, 1.05M Context, Reasoning Effort, and you can weigh it on price and capability against other Large Language Model models, then switch by changing a single model-name string — no new account or integration. Browse every Large Language Model option with live pricing at apimodels.app/models.
GPT-6 Luna supports: 10% Below Official, High Volume, 1.05M Context, Reasoning Effort. See the APIMODELS docs for full parameters and call examples.
Yes. APIMODELS exposes GPT-6 Luna through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.