GPT-5.6 Luna

Official

openai/gpt-5.6-luna

The efficient GPT-5.6 model for high-volume assistants, extraction, routing, and coding tasks. It keeps the 1.05M-token context window, vision, tools, configurable reasoning, persisted reasoning, and explicit prompt caching at the lowest price in the family.

1050K contextVisionReasoningTool callingCodingPrompt cachePaid cache writes

Pricing

Source: openai_x0.10 · Verified 2026-08-02

InputOfficial $0.2 / M tokens

$0.02/ M tokensSave 90%

OutputOfficial $1.2 / M tokens

$0.12/ M tokensSave 90%

Fast $0.04 / $0.24 /M

Cache read $0.002/M · Cache write $0.025/M

Tier	Input	Cache read	Cache write	Output
Standard ≤272K	$0.02~~$0.2~~ −90%	$0.002~~$0.02~~ −90%	$0.025~~$0.25~~ −90%	$0.12~~$1.2~~ −90%
Standard >272K	$0.04~~$0.4~~ −90%	$0.004~~$0.04~~ −90%	$0.05~~$0.5~~ −90%	$0.18~~$1.8~~ −90%
Priority ≤272K	$0.04~~$0.4~~ −90%	$0.004~~$0.04~~ −90%	$0.05~~$0.5~~ −90%	$0.24~~$2.4~~ −90%

Estimate cost

Input tokensOutput tokens

Estimated cost$0.00032

Protocols

OpenAI Chat CompletionsStatus: Available: Streaminghttps://api.routemux.com/v1
OpenAI ResponsesStatus: Available: Streaminghttps://api.routemux.com/v1
Anthropic MessagesStatus: Available: Streaminghttps://api.routemux.com/anthropic
Google Vertex AIStatus: Not supported—
OpenAI ImagesStatus: Not supported—
OpenAI SoraStatus: Not supported—

Call IDs

Use either ID to call this model via the API.

RouteMux nameopenai/gpt-5.6-luna

Try it

Replace the ROUTEMUX_KEY placeholder with your API key. Create one →

from openai import OpenAI

client = OpenAI(
    base_url="https://api.routemux.com/v1",
    api_key="<ROUTEMUX_KEY>",
)

completion = client.chat.completions.create(
    model="openai/gpt-5.6-luna",
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)

base_url: https://api.routemux.com/v1

Other variants in this family

GPT-5.6 Sol

OpenAI's flagship GPT-5.6 for the hardest reasoning, coding, and agentic work.

$0.5/M↓ · $3/M↑

GPT-5.6 Terra

Balanced GPT-5.6 quality and cost for production workloads.

$0.2/M↓ · $1.2/M↑

GPT-5.4 mini

OpenAI GPT-5.4 mini — fast, cheapest GPT-5 text route.

$0.075/M↓ · $0.45/M↑

GPT-5.4

OpenAI GPT-5.4 — strong general model, 1M context, lower cost than 5.5.

$0.25/M↓ · $1.5/M↑

GPT-5.5

OpenAI GPT-5.5 — flagship, 1M context, top reasoning & agentic coding.

$0.5/M↓ · $3/M↑

Frequently asked questions

›What is GPT-5.6 Luna?

The most efficient GPT-5.6 for high-volume and latency-sensitive work.

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

GPT-5.6 Luna supports a context window of up to 1.1M tokens, with up to 128K output tokens per request.

›How much does the GPT-5.6 Luna API cost?

Through RouteMux, GPT-5.6 Luna costs $0.02 for input and $0.12 for output (USD per 1M tokens), below the official list price.

›How do I call GPT-5.6 Luna via API?

GPT-5.6 Luna is OpenAI-compatible: point your base URL at RouteMux and set the model field to openai/gpt-5.6-luna — no code changes needed.

›Which input and output modalities does GPT-5.6 Luna support?

GPT-5.6 Luna accepts text, image as input and produces text as output.

›When was GPT-5.6 Luna released?

GPT-5.6 Luna was released on July 9, 2026.