GPT-6 Luna

Tool callingStructured outputReasoningImage inputFile input

Launch post Website Docs

OpenAI's most efficient model for focused, high-volume tasks

Context: 1.1M
Released: 3w ago
Input / 1M tokens: $0.10
Output / 1M tokens: $0.50
Cached input / 1M tokens: $0.01
Cache write / 1M tokens: $0.13

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

Evaluation	Reported score and source
ARC-AGI-2	31.4% Third-party evaluator · gpt-6-luna_high Reasoning effort: high External evaluation via Epoch AI Original-source terms apply
ARC-AGI-2	4.6% Third-party evaluator · gpt-6-luna_low Reasoning effort: low External evaluation via Epoch AI Original-source terms apply
ARC-AGI-2	59.3% Third-party evaluator · gpt-6-luna_max Reasoning effort: max External evaluation via Epoch AI Original-source terms apply
ARC-AGI-2	18.1% Third-party evaluator · gpt-6-luna_medium Reasoning effort: medium External evaluation via Epoch AI Original-source terms apply
ARC-AGI-2	0.0% Third-party evaluator · gpt-6-luna_none Reasoning effort: none External evaluation via Epoch AI Original-source terms apply
ARC-AGI-2	41.9% Third-party evaluator · gpt-6-luna_xhigh Reasoning effort: xhigh External evaluation via Epoch AI Original-source terms apply
FrontierMath-Tier-4-v2-Private	56.1% Epoch AI · gpt-6-luna_max Reasoning effort: max Epoch AI evaluation
FrontierMath-Tiers-1-3-v2-Private	78.9% Epoch AI · gpt-6-luna_max Reasoning effort: max Epoch AI evaluation
GPQA diamond	90.5% Epoch AI · gpt-6-luna_max Reasoning effort: max Epoch AI evaluation
OTIS Mock AIME 2024-2025	98.9% Epoch AI · gpt-6-luna_max Reasoning effort: max Epoch AI evaluation
SimpleQA Verified	41.4% Epoch AI · gpt-6-luna_max Reasoning effort: max Epoch AI evaluation

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer: OpenAI
Model family: GPT
Type: Language model
Predecessor: —
Successor: —
Released: September 22, 2026
Model ID: openai/gpt-6-luna
Openness: Closed
License: —
Input modalities: file, image, text
Output modalities: text
Modality: text+image+file->text
Tokenizer: GPT
Max output tokens: 128K
Knowledge cutoff: 2026-05-18
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: openai/gpt-6-luna
Source family: gpt-luna
Last updated: 2026-09-22
Knowledge cutoff: 2026-05-18
Model context: 1.1M
Maximum input: 922K
Model output limit: 128K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature control: No

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
DeepSWE	66.6 · score	max effort · 1.1 · 2026-09-22	Source

Complete source record (JSON)

{
  "id": "openai/gpt-6-luna",
  "name": "GPT-6 Luna",
  "description": "OpenAI's most efficient model for focused, high-volume tasks",
  "family": "gpt-luna",
  "last_updated": "2026-09-22",
  "knowledge": "2026-05-18",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": false,
  "modalities": {
    "input": [
      "text",
      "image",
      "pdf"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 1050000,
    "input": 922000,
    "output": 128000
  },
  "benchmarks": [
    {
      "name": "DeepSWE",
      "score": 66.6,
      "source": "https://openai.com/index/introducing-gpt-6-sol-and-luna/",
      "metric": "score",
      "variant": "max effort",
      "version": "1.1",
      "date": "2026-09-22"
    }
  ],
  "release_date": "2026-09-22",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
OpenAI	openai/flex	1.1M	$0.05	$0.25	$0.005	$0.06	92.36%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
OpenAI	openai/flexBatch pricing	1.1M	$0.05	$0.25	$0.005	$0.06	92.36%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Azure	azure	1.1M	$0.10	$0.50	$0.01	$0.13	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Azure	azureBatch pricing	1.1M	$0.10	$0.50	$0.01	$0.13	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
OpenAI	openai	1.1M	$0.10	$0.50	$0.01	$0.13	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
OpenAI	openaiBatch pricing	1.1M	$0.10	$0.50	$0.01	$0.13	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Amazon Bedrock	amazon-bedrock/us-east-1	1.1M	$0.11	$0.55	$0.01	$0.14	99.89%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Amazon Bedrock	amazon-bedrock/us-east-1Batch pricing	1.1M	$0.11	$0.55	$0.01	$0.14	99.89%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Azure	azure/us	1.1M	$0.11	$0.55	$0.01	$0.14	99.56%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Azure	azure/eu	1.1M	$0.11	$0.55	$0.01	$0.14	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Azure	azure/usBatch pricing	1.1M	$0.11	$0.55	$0.01	$0.14	99.56%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Azure	azure/euBatch pricing	1.1M	$0.11	$0.55	$0.01	$0.14	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
OpenAI	openai/fast	1.1M	$0.20	$1.00	$0.02	$0.25	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
OpenAI	openai/fastBatch pricing	1.1M	$0.20	$1.00	$0.02	$0.25	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Text provenance

EU · product-scoped

OpenAI textGrain watermarking

In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.

Official explanation