gpt-5-6-lunaGPT-5.6 Luna is optimized for cost-sensitive, high-volume workloads — the nano tier of the GPT-5.6 family. It delivers high reasoning at fast speed, text + image input and text output, a 1,050,000-token context window, 128,000 max output tokens, reasoning-token support, and a Feb 16 2026 knowledge cutoff. Live on API Models over both /v1/chat/completions and /v1/responses: $0.221 input / $1.324 output per 1M tokens (cached input $0.022) — 20% of GPT-5.6 Sol, and about 78% below OpenAI's own $1 / $6 list. Call it as gpt-5.6-luna-max; the gpt-5.6-luna alias routes here. One API key for every model, pay-as-you-go, only successful requests billed.
The nano tier — built for high-volume, low-cost workloads
Reasoning-token support tuned for throughput
Text + image input, text output; 1.05M context, 128K max output
OpenAI-compatible /v1/chat/completions and /v1/responses; $0.221 / $1.324 per 1M
View complete API reference with all parameters and examples.
Enable real-time streaming responses with Server-Sent Events.
{
"model": "gpt-5-6-luna",
"stream": true,
"messages": [...]
}Enable the model to use tools and call functions.
{
"model": "gpt-5-6-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-5-6-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-5-6-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
GPT-5.6 Luna is a Large Language Model API provided by OpenAI. GPT-5.6 Luna is optimized for cost-sensitive, high-volume workloads — the nano tier of the GPT-5.6 family. It delivers high reasoning at fast speed, text + image input and text output, a 1,050,000-token context window, 128,000 max output tokens, reasoning-token support, and a Feb 16 2026 knowledge cutoff. Live on API Models over both /v1/chat/completions and /v1/responses: $0.221 input / $1.324 output per 1M tokens (cached input $0.022) — 20% of GPT-5.6 Sol, and about 78% below OpenAI's own $1 / $6 list. Call it as gpt-5.6-luna-max; the gpt-5.6-luna alias routes here. One API key for every model, pay-as-you-go, only successful requests billed. Through API Models platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: Input: $0.221, Output: $1.324 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-5.6 Luna is available through API Models at: Input: $0.221, Output: $1.324 per 1M tokens. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at API Models, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
API Models offers the same GPT-5.6 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.
GPT-5.6 Luna is the nano tier of the GPT-5.6 family for cost-sensitive, high-volume workloads — high reasoning at fast speed, text + image input, a 1,050,000-token context, 128,000 max output, reasoning-token support, Feb 2026 cutoff. On apimodels.app it is $0.221 per 1M input and $1.324 per 1M output (cached input $0.022) — 20% of GPT-5.6 Sol, roughly a fifth of OpenAI's own $1 / $6 list, and the cheapest model in the GPT-5.6 family.
Point base_url at https://apimodels.app/api/v1 and set model to gpt-5.6-luna-max. Both OpenAI-compatible endpoints work — /v1/chat/completions and /v1/responses — and function calling (tools) is supported. Note that upstream currently serves only the max reasoning depth, so the name gpt-5.6-luna is aliased to gpt-5.6-luna-max at the same price. One API key for every model, pay-as-you-go, failed requests are never billed.
Requests whose input exceeds 272,000 tokens are billed end-to-end at $0.442 input / $1.986 output (2× input, 1.5× output), matching the upstream long-context rate step. Reasoning tokens count as output tokens.
Luna is itself the cheapest tier of the GPT-5.6 family: $0.221 per 1M input and $1.324 per 1M output on apimodels.app — a fifth of Sol and roughly a fifth of OpenAI's own $1/$6 list, with cached input at just $0.022. For bulk classification, extraction, rewriting and support workloads it is the best value; step up to gpt-5.6-terra or gpt-5.6-sol when you need stronger reasoning. Migrating from OpenAI direct or another gateway takes no code changes: point base_url at https://apimodels.app/api/v1 and set model to gpt-5.6-luna-max. The API is OpenAI-compatible and failed requests are never billed.
Most important: upstream currently serves only the max reasoning depth, so use the model id gpt-5.6-luna-max (gpt-5.6-luna is aliased to it at the same price). Beyond that, upstream injects a ~1,450-token system preamble into every request, so input_tokens never drops below that floor; `parallel_tool_calls: false` is ignored and the model may return several tool_calls at once; and input above 272,000 tokens rebills the whole request at a higher rate. Function calling (tools), streaming and /v1/responses are all verified working.
On API Models, GPT-5.6 Luna runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Cost-Efficient、High-Volume、Fast、1.05M Context, 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-5.6 Luna supports: Cost-Efficient、High-Volume、Fast、1.05M Context. See the API Models docs for full parameters and call examples.
Yes. API Models exposes GPT-5.6 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.