Roboflow
OpenAI

OpenAI: GPT-5.6 Luna

GPT-5.6 Luna Overview

GPT-5.6 Luna is the fastest and most cost-efficient model in OpenAI's GPT-5.6 family, which also includes Sol (the flagship tier) and Terra (the balanced mid-tier). Introduced under a new naming convention where the generation number (5.6) and a durable capability tier name (Luna, Terra, Sol) together define each model, Luna occupies the lightweight end of the family and is designed for high-volume, latency-sensitive workloads such as summarization, drafting, autocomplete, classification, and routine automation. The GPT-5.6 family as a whole advances capabilities in software engineering, computer use, professional knowledge work, scientific research, and cybersecurity, with all three tiers rated at the "High" capability level under OpenAI's Preparedness Framework for both cybersecurity and biological/chemical risk domains.

GPT-5.6 Luna supports multimodal input and function calling, and shares the family's 1.5 million token context window. On Terminal-Bench 2.1, Luna scores 82.5%, and on the Artificial Analysis Coding Agent Index it outperforms comparable models at roughly one-quarter the estimated cost of higher-tier alternatives. Luna is priced at $1 per million input tokens and $6 per million output tokens, with cached input reads at $0.10 per million tokens under the GPT-5.6 prompt caching scheme, which introduces explicit cache breakpoints and a 30-minute minimum cache life. The model was previewed on June 26, 2026 to a limited group of trusted partners via the OpenAI API and Codex, with general availability rolling out on July 9, 2026 across ChatGPT, Codex, and the API.

GPT-5.6 Luna Interactive Demo

GPT-5.6 Luna Details & Performance

Details

Resources

Tutorial

Vision Tasks

CaptioningChart Question AnsweringClassificationDocument Question AnsweringImage TaggingMulti-Label ClassificationOCRObject DetectionVision LanguageVisual Question Answering

Features

Foundation VisionLLMs with Vision CapabilitiesMultimodal Vision

Usage

Past 30 Days

Performance

Avg. Latency

Arena Rankings

GPT-5.6 Luna Vision Evals

Vision Evals is Roboflow's ground-truth benchmark: every model runs the same real-world samples across six vision tasks, and answers are scored against ground truth.

Evals updated August 20, 2026Pricing updated August 23, 2026

Overall score#14 of 31
71.5%
Avg cost / sample#5 of 31
$0.0010
Avg speed / sample#11 of 31
6.55s
Avg tokens / sample
2.1K

Strengths and weaknesses

GPT-5.6 Luna averages 71.5% across the six Vision Evals tasks, ranking #14 of 31 models overall.

Its weakest relative showing is Data Extraction, ranking #25 of 31 at 81.4%.

At $0.0010 per sample it is the 5th cheapest of the 31 benchmarked models, and its average inference time of 6.5s per sample makes it the 11th fastest.

Performance profile

Field medianGPT-5.6 Luna

Field medians: Object Detection 54.5%, Counting 63.5%, Identification 84.4%, OCR 89.3%, Data Extraction 86.6%, Reasoning 57.6%.

Results by task

TaskScoreField (0 to 100)RankCost / sampleSpeed
Object Detection
59.9%
#9 of 31$0.001510.29s
Counting
66.2%
#13 of 31$0.00074.18s
Identification
78.1%
#22 of 31$0.00043.43s
OCR
88.4%
#21 of 31$0.00125.06s
Data Extraction
81.4%
#25 of 31$0.00042.94s
Reasoning (low)
55.0%
#18 of 31$0.00064.85s
Reasoning (high)
60.9%
#23 of 31$0.00158.49s
  • Thinking longer helps: 6 points higher on reasoning at high effort for 2.4x the cost and 1.7x the latency.

Price vs. performance

Score vs. cost

Overall benchmark score against estimated cost per sample. Upper-left is the sweet spot: high quality at low cost.

31 models on the current benchmark · scores and efficiency pooled across all six tasks at low effort · GPT-5.6 Luna highlighted

GPT-5.6 Luna scores from a single evaluation run · Methodology

View all Vision Evals →

GPT-5.6 Luna Pricing

GPT-5.6 Luna costs $0.200 per 1M input tokens and $1.20 per 1M output tokens.

Input$0.200 / 1M tokens
Output$1.20 / 1M tokens
Cached input$0.020 / 1M tokens

Pricing updated Aug 23, 2026

Alternatives to GPT-5.6 Luna

Other models worth comparing for similar use cases.

Google
Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite is a natively multimodal reasoning model developed by Google DeepMind, released on July 21, 2026 as part of the Gemini 3.5 model family. It is the fastest model in the 3.5 series, designed for both low-latency tasks and high-throughput production workloads such as agentic search, document processing, receipt translation, and large-scale data extraction. The model accepts text, images, audio, and video as inputs, with a context window of up to 1 million tokens, and produces text output. It supports configurable thinking levels, allowing developers to tune the balance between response quality, cost, and latency depending on workload requirements.On agentic and coding benchmarks, Gemini 3.5 Flash-Lite significantly outperforms its predecessor, Gemini 3.1 Flash-Lite, including on Terminal-Bench 2.1 (54% vs. 31%), GDM-MRCR v2 long-context (72.2% vs. 60.1%), and real-world task execution as measured by GDPval-AA v2 (1140 vs. 642). It also surpasses Gemini 3 Flash on SWE-Bench Pro (54.2% vs. 49.6%) and OSWorld-Verified (74.0% vs. 65.1%). According to the Artificial Analysis Index, the model generates output at approximately 350 tokens per second. It is built on the Gemini 3.5 Flash foundation and is evaluated across reasoning, coding, multimodal understanding, multilingual performance, and long-context tasks. The model is developed under Google's Frontier Safety Framework.
Google
Gemini 3.1 Flash-Lite
Gemini 3.1 Flash-Lite is a natively multimodal reasoning model from Google DeepMind in the Gemini 3 series, based on the Gemini 3 Pro architecture. It processes text, image, video, audio, and PDF inputs within a 1 million token context window and produces text output up to 64K tokens. The model targets high-volume, latency-sensitive workloads and supports visual question answering, image and document data extraction, content moderation, classification, translation, automated speech recognition, and agentic data pipelines. It exposes configurable thinking levels of minimal, low, medium, and high, which set the depth of internal reasoning applied per request and let developers balance response quality against cost and latency.On benchmarks reported at launch, Gemini 3.1 Flash-Lite scores 86.9% on GPQA Diamond and 76.8% on the MMMU Pro multimodal benchmark, and reaches an Elo score of 1432 on the Arena.ai leaderboard. According to Artificial Analysis benchmarks, it produces a 2.5 times faster time to first answer token and a 45% increase in output speed relative to Gemini 2.5 Flash. It also shows improved instruction following, higher audio input quality for automated speech recognition tasks, and support for structured JSON output used in data extraction pipelines.
Anthropic
Claude Haiku 4.5
Claude Haiku 4.5 is Anthropic’s lightweight model in the Claude 4.5 series, released in October 2025 under a proprietary license. Designed for speed and cost efficiency, it delivers near-frontier performance while maintaining Anthropic’s AI Safety Level 2 standard. Haiku 4.5 supports both text and multimodal (text and image) inputs, integrates tool use and extended reasoning, and features a 200,000 token context window, making it adept at handling long or complex workflows. Though the parameter count remains undisclosed, it achieves about 73.3% on SWE-bench Verified, reflecting strong coding and reasoning ability. Haiku 4.5 is ideal for developers and researchers seeking rapid, cost-effective model calls for analysis, coding, or multimodal understanding.
Qwen
Qwen3.5 9b
Qwen3.5-9B is a 9-billion-parameter multimodal foundation model developed by Alibaba Cloud's Qwen team, released on March 2, 2026 as part of the Qwen3.5 model family. Designed for efficient multimodal reasoning and long-context language tasks, it notably outperforms the older Qwen3-30B, a model more than three times its size, on key benchmarks including GPQA Diamond, IFEval, and LongBench.The model supports vision-language inputs through an early-fusion multimodal architecture built on a dense hybrid foundation of Gated Delta Networks and Gated Attention. It can also operate in a text-only mode by skipping the vision encoder during inference. It provides a 262,144-token context window (extensible to ~1M tokens via YaRN) and is released under the Apache License 2.0. Within the current AI landscape, Qwen3.5-9B offers a strong balance of capability and efficiency, making it well-suited for multimodal assistants, document analysis, long-context reasoning, and developer-deployed agentic systems.
Qwen
Qwen3 VL 8B Instruct
Qwen3 VL 8B Instruct is an open-weight multimodal vision-language model developed by Qwen / Alibaba Cloud as part of the Qwen3-VL series, designed for instruction-following tasks that combine text with visual inputs such as images and video. Released around October 2025 under the Apache-2.0 license, it targets developers who need capable multimodal reasoning without the scale or cost of very large models.The model contains roughly 8.8 billion dense parameters and supports text, image, and video understanding with strong spatial perception, visual reasoning, and emerging visual agent abilities such as GUI interaction. A standout feature is its native ~256K token context window, extendable to around 1M tokens, enabling long-document reading and extended video comprehension. In today’s landscape, it balances openness, long-context capacity, and solid multimodal performance against heavier proprietary models. Typical applications include multimodal assistants, document and video analysis, visual question answering, and research or product prototyping where transparency and deployability matter.

Other OpenAI GPT Nano models

Other versions in the same family as GPT-5.6 Luna.

OpenAIGPT-5.4 NanoOpenAIGPT-5 Nano

Deploy GPT-5.6 Luna with an API

GPT-5.6 Luna runs as a hosted REST endpoint through Roboflow Workflows. Pick a task, then hand the prompt to your coding agent or copy the code. Deploying the workflow into a free Roboflow workspace replaces the your-workspace and YOUR_API_KEY placeholders with your own.

Connect your agent to Roboflow (once)

Add the Roboflow MCP server

claude mcp add --transport http roboflow https://mcp.roboflow.com/mcp

Run /mcp and authorize Roboflow in your browser when the OAuth flow opens.

Start a new Claude Code session so the MCP loads, then paste the prompt below (it works the same in any agent).

Deploy this workflow to your Roboflow workspace to use it.

Integrate the Roboflow "GPT-5.6 Luna" workflow into my app.

- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/gpt-5-6-luna-classification
- Auth: send my Roboflow API key as `api_key` in the request body, read from the ROBOFLOW_API_KEY env var (never hardcode).
- Body: { "api_key": ..., "inputs": { `image`: { type: "url" | "base64", value }, `classes`: string array } }.
- Billing: this workflow needs no provider API key — inference runs on my Roboflow credits. A BYO provider key can be added to the model step in the Roboflow workflow editor later.

With the Roboflow MCP connected, call `workflows_get` on "gpt-5-6-luna-classification" to read the exact input schema (the source of truth), then `workflows_run` on a sample image to confirm the output shape before writing code (the MCP is authenticated, so this needs no key). Without the MCP, use the contract above.

Before running the app, set up these keys so it does not error at runtime:
- `ROBOFLOW_API_KEY` (sent as `api_key`) from https://app.roboflow.com/settings/api
Create a .gitignore'd .env with these variables, using placeholder values for any I haven't given you. Then pause and tell me directly, in your reply: the full path to the .env file, exactly which keys I need to paste in, and the link to get each one. Wait for me to confirm I've added them before you run anything. Do not run the app until I confirm.

Then add the integration to my codebase: match my project's language, framework, and conventions; read every key from environment variables (never hardcode); add basic error handling; and include a small runnable example. If you can't tell what language my project uses, ask me.
Installpip install inference-sdk

Deploy this workflow to your Roboflow workspace to use it.

# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
# 1. Import the library
from inference_sdk import InferenceHTTPClient

# 2. Connect to your workflow
client = InferenceHTTPClient(
  api_url="https://serverless.roboflow.com",
  api_key="YOUR_API_KEY"
)

# 3. Run your workflow on an image
result = client.run_workflow(
  workspace_name="your-workspace",
  workflow_id="gpt-5-6-luna-classification",
  images={
    "image": "YOUR_IMAGE.jpg"  # Path to your image file
  },
  parameters={
    "classes": ["class1", "class2", "class3"]
  },
  use_cache=True  # cache workflow definition for 15 minutes
)

# 4. Get your results
print(result)

Deploy this workflow to your Roboflow workspace to use it.

// Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/gpt-5-6-luna-classification', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    api_key: 'YOUR_API_KEY',
    inputs: {
      "image": {"type": "url", "value": "IMAGE_URL"},
      "classes": ["class1", "class2", "class3"]
    }
  })
});

const result = await response.json();
console.log(result);

Deploy this workflow to your Roboflow workspace to use it.

# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/gpt-5-6-luna-classification' \
--header 'Content-Type: application/json' \
--data '{
  "api_key": "YOUR_API_KEY",
  "inputs": {
    "image": {"type": "url", "value": "IMAGE_URL"},
    "classes": ["class1", "class2", "class3"]
  }
}'

GPT-5.6 Luna License

Proprietary

GPT-5.6 Luna is proprietary: the weights are not distributed, and the GPT-5.6 Luna license is the vendor's commercial terms of service that you accept when you call the API.

Commercial use
Permitted under the vendor terms, typically metered per token or per request, with the vendor usage policy applying to your inputs and outputs.
Modification
Not available. GPT-5.6 Luna weights are closed, so you can configure prompts and use vendor-hosted fine-tuning where it is offered, but you cannot modify the model itself.
Redistribution
Not permitted. You cannot self-host or resell the model; you build on the hosted API instead.

Vendor terms govern data retention, whether your inputs can be trained on, rate limits, and regional availability, and they can change with notice. Review them if you handle regulated or customer data.

Do I need a commercial license for GPT-5.6 Luna?

Proprietary terms are set by the vendor rather than negotiated per project, and no open-source obligation attaches to your code. If you would rather deploy a model whose commercial license is included in your plan — on Roboflow Managed Cloud or a Self-Hosted Inference Server — Roboflow's licensing page lists the supported alternatives to GPT-5.6 Luna.

Do not hesitate to reach out with questions for your commercial project — our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.

Talk to sales

This model is proprietary. The author retains all rights, and use of the model is governed by their specific terms of service or license agreement.

Commercial use depends on the terms set by the model author. Most proprietary commercial models require a paid subscription, API key, or per-call billing. Check the provider’s pricing and terms-of-service for details.

License information is provided as a guide and is not legal advice.

Frequently Asked Questions About GPT-5.6 Luna Vision

Yes. GPT-5.6 Luna accepts image input and handles OCR, data extraction, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is Object Detection at 59.9% (#9 of 31). You can test it on your own image in the demo above.

Yes. its transcriptions match the ground truth 88.4% on average (#21 of 31) on Vision Evals OCR. Pulling specific fields out of documents (data extraction) scores 81.4%.

It's serviceable. On Vision Evals, GPT-5.6 Luna scores 59.9% mAP@50 on object detection (#9 of 31) and 66.2% exact-match accuracy on object counting.

On our benchmark's task mix, GPT-5.6 Luna averages $0.0010 per sample at $0.20 per 1M input and $1.20 per 1M output tokens (#5 of 31 on cost), with an average speed of 6.5s per sample across the benchmark. Actual cost depends on your images and prompts.

On the overall Vision Evals ranking, GPT-5.6 Luna sits #14 of 31 at 71.5%, just behind GPT-5.6 Terra (72.4%) and just ahead of Muse Glimmer 30B (70.8%). See the full side-by-side: GPT-5.6 Luna vs GPT-5.6 Terra.