Where is the GPT-6 Luna documentation?

The GPT-6 Luna documentation on OpenRouter includes the GPT-6 Migration Guide cookbook, the Reranking in RAG: How to Fix Bad Retrieval with a Reranker blog post, the How to Benchmark LLMs blog post, the How to Stop an AI Agent Stuck in an Infinite Loop blog post, the MCP vs CLI vs Skills: What Each Costs in Context blog post, the LLM API Rate Limits: How to Fix OpenAI and Claude 429 Errors blog post, the How to Get Structured Output from Any LLM: JSON Schema, Tool Calls, or a Decision Model blog post, the How to Build a Voice AI Agent blog post, the Build an AI Code Reviewer with OpenRouter blog post, and the How to Extract Tables from a PDF with an LLM blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does GPT-6 Luna cost?

GPT-6 Luna costs $0.10/M input tokens and $0.50/M output tokens, with separate rates for Cache Read at $0.01/M tokens and Cache Write at $0.125/M tokens.

What is the context length of GPT-6 Luna?

GPT-6 Luna has a 1,050,000 token context window. It supports up to 128,000 completion tokens.

Does GPT-6 Luna support tool calling and structured outputs?

Yes. GPT-6 Luna accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Can I disable prompt caching for GPT-6 Luna?

Yes. OpenAI caches prompts of 1024 tokens or more automatically, and GPT-6 Luna bills a cache write on each cached prompt whether or not the cached prefix is read again. To turn caching off for a request, set prompt_cache_options.mode to "explicit" at the request root and do not mark any content block with prompt_cache_breakpoint. Explicit mode disables OpenAI-managed breakpoints, so a request with none of your own has no cacheable prefix and is billed at the plain input rate. See the prompt caching guide.

What inputs and outputs does GPT-6 Luna support?

GPT-6 Luna accepts files such as PDFs, images, and text as input and returns text.

Which providers serve GPT-6 Luna?

GPT-6 Luna is served by 3 providers on OpenRouter: OpenAI, Amazon Bedrock, and Azure. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was GPT-6 Luna released?

GPT-6 Luna was released on September 22, 2026.

OpenAI: GPT-6 Luna

openai/gpt-6-luna

Compare

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

Modalities

In / out price

$0.10 / $0.50per 1M

Context

1.1M

Released

Sep 22, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$0.10	$0.50	$0.01	1.19s	125 tok/s	100.00%
	$0.10	$0.50	$0.01	1.49s	69 tok/s	100.00%
	$0.10	$0.50	$0.01	3.03s	74 tok/s	100.00%
Not used in Standard routing:Why these endpoints are not used
Flex	$0.05	$0.25	$0.005	7.00s	25 tok/s	100.00%
	$0.11	$0.55	$0.011	3.55s	94 tok/s	99.82%
	$0.11	$0.55	$0.011	1.78s	48 tok/s	100.00%
	$0.11	$0.55	$0.011	1.10s	84 tok/s	100.00%
Fast	$0.20	$1.00	$0.02	0.89s	99 tok/s	100.00%

Input $0.10Output $0.50
125 tok/s100.00% uptime
Input $0.10Output $0.50
69 tok/s100.00% uptime
Input $0.10Output $0.50
74 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.05Output $0.25
Flex
25 tok/s100.00% uptime
Input $0.11Output $0.55
94 tok/s99.82% uptime
Input $0.11Output $0.55
48 tok/s100.00% uptime
Input $0.11Output $0.55
84 tok/s100.00% uptime
Input $0.20Output $1.00
Fast
99 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.04427/M tokens

Output

$0.4922/M tokens

GPT-6 Luna — Price history

Price history

No effective price data for this selection

		$0.0230	$0.501	89.3%	17.3%
		$0.0458	$0.500	69.4%	6.3%
		$0.0503	$0.501	66.5%	67.0%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.0249	$0.249	64.8%	3.8%
		$0.0346	$0.557	86.6%	2.7%
		$0.0530	$0.549	67.7%	0.1%
		$0.0615	$0.549	59.7%	1.3%
	Fast	$0.0691	$1.010	79.5%	1.5%

Effective in $0.0230Effective out $0.501
Token share
17.3%
Effective in $0.0458Effective out $0.500
Token share
6.3%
Effective in $0.0503Effective out $0.501
Token share
67.0%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.0249Effective out $0.249
FlexToken share
3.8%
Effective in $0.0346Effective out $0.557
Token share
2.7%
Effective in $0.0530Effective out $0.549
Token share
0.1%
Effective in $0.0615Effective out $0.549
Token share
1.3%
Effective in $0.0691Effective out $1.010
FastToken share
1.5%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

99.99%

Availability (3d)

99.90%

Availability over the last 3 days

Last 72 hours

Availability 99.90%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.90%

Without Routing

97.01%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for OpenAI: GPT-6 Luna (Artificial Analysis and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GPT-6 Luna (Xhigh) Intelligence Index	23.5
Artificial Analysis	GPT-6 Luna (Xhigh) HLE	34.3%
Artificial Analysis	GPT-6 Luna (Xhigh) AA-LCR	80.0%
Artificial Analysis	GPT-6 Luna (Xhigh) GDPval-AA	43.6%
Artificial Analysis	GPT-6 Luna (Xhigh) CritPt	17.4%
Artificial Analysis	GPT-6 Luna (Xhigh) SciCode	51.7%
Artificial Analysis	GPT-6 Luna (Xhigh) Terminal-Bench 4.0	8.1%
Artificial Analysis	GPT-6 Luna (Xhigh) AA-Omniscience Accuracy	38.6%
Artificial Analysis	GPT-6 Luna (Xhigh) AA-Omniscience Non-Hallucination Rate	16.0%
Artificial Analysis	GPT-6 Luna (Max) Intelligence Index	27.9
Artificial Analysis	GPT-6 Luna (Max) HLE	38.5%
Artificial Analysis	GPT-6 Luna (Max) AA-LCR	83.3%
Artificial Analysis	GPT-6 Luna (Max) GDPval-AA	47.2%
Artificial Analysis	GPT-6 Luna (Max) CritPt	19.4%
Artificial Analysis	GPT-6 Luna (Max) SciCode	54.6%
Artificial Analysis	GPT-6 Luna (Max) Terminal-Bench 4.0	12.6%
Artificial Analysis	GPT-6 Luna (Max) AA-Omniscience Accuracy	39.6%
Artificial Analysis	GPT-6 Luna (Max) AA-Omniscience Non-Hallucination Rate	20.7%
Artificial Analysis	GPT-6 Luna (High) Intelligence Index	21.4
Artificial Analysis	GPT-6 Luna (High) HLE	32.9%
Artificial Analysis	GPT-6 Luna (High) AA-LCR	79.3%
Artificial Analysis	GPT-6 Luna (High) GDPval-AA	42.6%
Artificial Analysis	GPT-6 Luna (High) CritPt	15.4%
Artificial Analysis	GPT-6 Luna (High) SciCode	50.3%
Artificial Analysis	GPT-6 Luna (High) Terminal-Bench 4.0	4.5%
Artificial Analysis	GPT-6 Luna (High) AA-Omniscience Accuracy	39.0%
Artificial Analysis	GPT-6 Luna (High) AA-Omniscience Non-Hallucination Rate	15.1%
Artificial Analysis	GPT-6 Luna (Low) Intelligence Index	9.7
Artificial Analysis	GPT-6 Luna (Low) HLE	20.3%
Artificial Analysis	GPT-6 Luna (Low) AA-LCR	74.0%
Artificial Analysis	GPT-6 Luna (Low) GDPval-AA	27.0%
Artificial Analysis	GPT-6 Luna (Low) CritPt	2.6%
Artificial Analysis	GPT-6 Luna (Low) SciCode	46.9%
Artificial Analysis	GPT-6 Luna (Low) Terminal-Bench 4.0	0.0%
Artificial Analysis	GPT-6 Luna (Low) AA-Omniscience Accuracy	36.1%
Artificial Analysis	GPT-6 Luna (Low) AA-Omniscience Non-Hallucination Rate	15.2%
Artificial Analysis	GPT-6 Luna (Medium) Intelligence Index	18.5
Artificial Analysis	GPT-6 Luna (Medium) HLE	28.3%
Artificial Analysis	GPT-6 Luna (Medium) AA-LCR	78.3%
Artificial Analysis	GPT-6 Luna (Medium) GDPval-AA	38.5%
Artificial Analysis	GPT-6 Luna (Medium) CritPt	10.6%
Artificial Analysis	GPT-6 Luna (Medium) SciCode	50.9%
Artificial Analysis	GPT-6 Luna (Medium) Terminal-Bench 4.0	2.5%
Artificial Analysis	GPT-6 Luna (Medium) AA-Omniscience Accuracy	38.7%
Artificial Analysis	GPT-6 Luna (Medium) AA-Omniscience Non-Hallucination Rate	14.7%
Artificial Analysis	GPT-6 Luna (Non-reasoning) Intelligence Index	9.4
Artificial Analysis	GPT-6 Luna (Non-reasoning) HLE	8.6%
Artificial Analysis	GPT-6 Luna (Non-reasoning) AA-LCR	39.7%
Artificial Analysis	GPT-6 Luna (Non-reasoning) GDPval-AA	27.6%
Artificial Analysis	GPT-6 Luna (Non-reasoning) CritPt	1.1%
Artificial Analysis	GPT-6 Luna (Non-reasoning) SciCode	43.1%
Artificial Analysis	GPT-6 Luna (Non-reasoning) Terminal-Bench 4.0	1.5%
Artificial Analysis	GPT-6 Luna (Non-reasoning) AA-Omniscience Accuracy	30.1%
Artificial Analysis	GPT-6 Luna (Non-reasoning) AA-Omniscience Non-Hallucination Rate	20.0%
Vals AI	GPT-6 Luna BioMysteryBench	61.5%
Vals AI	GPT-6 Luna ClaimBench	99.2%
Vals AI	GPT-6 Luna Code Migration v1.1	46.7%
Vals AI	GPT-6 Luna CyberBench v1.1	76.3%
Vals AI	GPT-6 Luna EMB v1.1	70.0%
Vals AI	GPT-6 Luna Finance Agent v2.1	56.8%
Vals AI	GPT-6 Luna Vals Finance Index	53.1%
Vals AI	GPT-6 Luna Financial Coaching Bench	65.2%
Vals AI	GPT-6 Luna HLAB-Vals-1.1	4.2%
Vals AI	GPT-6 Luna Immigration	62.5%
Vals AI	GPT-6 Luna IOI	55.6%
Vals AI	GPT-6 Luna Vals Legal Index	62.2%
Vals AI	GPT-6 Luna Legal Research Bench	30.3%
Vals AI	GPT-6 Luna MedCode	44.7%
Vals AI	GPT-6 Luna MedScribe	83.7%
Vals AI	GPT-6 Luna MysteryMechanism	19.4%
Vals AI	GPT-6 Luna ProgramBench	0.5%
Vals AI	GPT-6 Luna ProofBench v1.1	64.0%
Vals AI	GPT-6 Luna Public Benefits Bench v1.1	57.6%
Vals AI	GPT-6 Luna SAGE	83.4%
Vals AI	GPT-6 Luna Vals Science Index	28.4%
Vals AI	GPT-6 Luna SRE Bench	2.7%
Vals AI	GPT-6 Luna SWE-bench Multimodal	37.5%
Vals AI	GPT-6 Luna Tax Agent Bench	19.9%
Vals AI	GPT-6 Luna Terminal-Bench 4.0	13.6%
Vals AI	GPT-6 Luna Terminal-Bench-Science	4.3%
Vals AI	GPT-6 Luna Vals Index	52.3%
Vals AI	GPT-6 Luna Vibe Code Bench v1.1	81.6%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Codex

A coding agent that helps you build and ship with AI

3.58Ttokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

1.78Ttokens

There are many coding agents, but this one is yours.

586Btokens

Freebuff

Powerful coding models, funded by ads

537Btokens

websim agent

new

418Btokens

Rest of OpenRouter

874B

Top 5 Apps

211B

OpenAI: GPT Luna versions

Available through EU in-region routing

OpenAI: GPT-6 Luna is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe

Azure

Prices in Europe

Azure: $0.11/M tokens input, $0.55/M tokens output

Base URL

https://eu.openrouter.ai/api/v1

Plan

Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

More models from OpenAI

GPT Image 2.6 Sunburst

GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next at medium or high quality, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Flare instead when speed matters more than fine detail.

Image$8 / $30

GPT Image 2.6 Flare

GPT Image 2.6 Flare is OpenAI's image generation and editing model optimized for speed: fast iteration and interactive text-to-image and image-to-image workflows, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Sunburst instead when detail and edit-to-edit consistency matter more than latency.

Image$8 / $30

GPT-6.1 Terra Pro

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Terra instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Terra Pro (batch)

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.50 / $2.50

GPT-6.1 Terra

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

Text1.1M context$1 / $5

GPT-6.1 Terra (batch)

Text1.1M context$0.50 / $2.50

GPT-6 Luna Decisions

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content.

Decisions$0.10 / $0

GPT-6.1 Sol Pro

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6.1 Sol Pro (batch)

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Sol

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

Text1.1M context$2 / $10

GPT-6.1 Sol (batch)

Text1.1M context$1 / $5

GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Luna instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.10 / $0.50

GPT-6 Luna Pro (batch)

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.05 / $0.25

GPT-6 Luna (batch)

Text1.1M context$0.05 / $0.25

GPT-6 Sol Pro

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6 Sol Pro (batch)

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6 Sol

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

Text1.1M context$2 / $10

GPT-6 Sol (batch)

Text1.1M context$1 / $5

GPT Astra Latest

This model always redirects to the latest model in the GPT Astra family.

Text1.1M context

GPT Sol Latest

This model always redirects to the latest model in the GPT Sol family.

Text1.1M context

OpenAI: GPT-6 Luna

Providers