Transparent pricing with no hidden fees. Pay as you go.
gpt-6-lunagpt-6-lunagpt-6-lunagpt-6-luna| Model | Spec | PoYo price | Official price | You save |
|---|---|---|---|---|
| gpt-6-luna | Input | $0.080/1M tokens 16 credits /1M tokens | $0.100/1M tokens Official | 20% |
Output | $0.400/1M tokens 80 credits /1M tokens | $0.500/1M tokens Official | 20% | |
Cache Read | $0.008/1M tokens 1.6 credits /1M tokens | $0.010/1M tokens Official | 20% | |
Cache Write | $0.100/1M tokens 20 credits /1M tokens | $0.125/1M tokens Official | 20% |
* Actual fees are based on the final output.
Efficient reasoning for focused, high-volume tasks
GPT-6 Luna is OpenAI’s GPT-6 model for focused, high-volume workloads. Released on September 22, 2026, it accepts text and images and produces text. The specifications below describe the official model; PoYo provides the integration and prices shown on this page.
Efficient reasoning for focused, high-volume tasks
01
OpenAI documents a 1,050,000-token context window, up to 922,000 input tokens and 128,000 output tokens. Text and images are accepted as inputs; the output is text. These are official model limits, not a promise that every request can use all limits simultaneously.
02
The official settings are none, low, medium, high, xhigh and max; medium is the default. OpenAI directs tool use to Responses. Function calling through Chat Completions requires reasoning_effort=none.
PoYo has verified basic text requests through Chat Completions and Responses. Image input, streaming, reasoning settings, structured outputs and tool execution have not been validated in this integration; official support alone does not establish channel support.
03
For standard requests with up to 272K input tokens, OpenAI lists $0.10 input, $0.50 output, $0.01 cached input and $0.125 cache writes per million tokens. PoYo’s corresponding base rates are $0.08, $0.40, $0.008 and $0.10.
Evaluate Luna for routing support requests or applying a fixed set of document labels.
Try focused summaries or extraction from supplied text, and check results against your own examples.
Use constrained prompts for short drafts, rewrites and suggested replies.
Evaluate code explanations and small edits with your own tests before applying them.
| Specification | GPT-6 Luna |
|---|---|
| Release date | 2026-09-22 |
| Context window | 1,050,000 tokens |
| Maximum input | 922,000 tokens |
| Maximum output | 128,000 tokens |
| Knowledge cutoff | 2026-05-18 |
| Input / output | Text + images / text |
| Reasoning settings | none · low · medium · high · xhigh · max |
| Fine-tuning | Not supported by the official model |
Checked on September 23, 2026. Official model specifications; channel limits and feature availability may differ.
/v1/chat/completions + /v1/responses. Use model ID gpt-6-luna.Use gpt-6-luna in the existing Chat Completions or Responses integration.
Compare input, output and cache prices in the pricing table above.
Check the model specifications on this page and validate the features your application needs.
Try text prompts on this page and switch between Chat Completions and Responses before integrating.