OpenRouter 模型 ↗ · 2026-09-23
openai/gpt-6-luna
Model release OpenRouter 模型 Source language: Chinese
OpenRouter 于 2026-09-23 收录该模型(收录时间不等于模型正式发布日期);上下文:1,050,000 tokens;输入价:$0.1000/百万 tokens;输出价:$0.5000/百万 tokens;定位(来源描述):GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.
Full text
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
Compare
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$0.0101.12s131 tok/s
100.00%
$0.10$0.50$0.0102.17s65 tok/s
100.00%
$0.10$0.50$0.0103.70s88 tok/s
100.00%
Not used in Standard routing:Why these endpoints are not used
Flex
$0.05$0.25$0.0056.81s36 tok/s
100.00%
$0.11$0.55$0.0113.32s83 tok/s
100.00%
$0.11$0.55$0.0111.98s79 tok/s
100.00%
$0.11$0.55$0.0110.84s87 tok/s
100.00%
Fast
$0.20$1.00$0.0200.82s134 tok/s
100.00%
ProviderInput / Output /M
Input $0.10 / Output $0.50
131 tok/s100.00% uptime
Input $0.10 / Output $0.50
65 tok/s100.00% uptime
Input $0.10 / Output $0.50
88 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.05 / Output $0.25
Flex
36 tok/s100.00% uptime
Input $0.11 / Output $0.55
83 tok/s100.00% uptime
Input $0.11 / Output $0.55
79 tok/s100.00% uptime
Input $0.11 / Output $0.55
87 tok/s100.00% uptime
Input $0.20 / Output $1.00
Fast
134 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
$0.04479/M tokens
Output
$0.4651/M tokens
GPT-6 Luna — Price history
Price history
No effective price data for this selection
$0.0290$0.50886.9%27.0%
$0.0503$0.50166.3%53.5%
$0.0724$0.50150.0%3.8%
Not used in Standard routing:Why these endpoints are not used
$0.0394$0.54777.8%1.0%
Flex
$0.0429$0.25033.3%9.8%
$0.0477$0.55472.5%1.7%
Fast
$0.0598$1.00282.5%1.7%
$0.0635$0.56374.4%1.5%
ProviderInput / Output /M
Token share
Effective in $0.0290 / Effective out $0.508
Token share
27.0%
Effective in $0.0503 / Effective out $0.501
Token share
53.5%
Effective in $0.0724 / Effective out $0.501
Token share
3.8%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.0394 / Effective out $0.547
Token share
1.0%
Effective in $0.0429 / Effective out $0.250
FlexToken share
9.8%
Effective in $0.0477 / Effective out $0.554
Token share
1.7%
Effective in $0.0598 / Effective out $1.002
FastToken share
1.7%
Effective in $0.0635 / Effective out $0.563
Token share
1.5%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Throughput
134tok/s
P50, best across providers
Latency
0.82s
P50, best provider
Reasoning effortLatency / throughput
AutoExacto benchmarks
GPQA DiamondTAU-BenchAmazon Bedrock87.5%70.0%Amazon Bedrock87.8%68.7%
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)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.91%
Availability over the last 3 days
Last 72 hours
Availability 99.91%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
99.92%
Without Routing
99.13%
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)
SourceBenchmarkScore
Artificial AnalysisGPT-6 Luna (High) Intelligence Index21.4
Artificial AnalysisGPT-6 Luna (High) HLE32.9%
Artificial AnalysisGPT-6 Luna (High) AA-LCR79.3%
Artificial AnalysisGPT-6 Luna (High) GDPval-AA42.5%
Artificial AnalysisGPT-6 Luna (High) CritPt15.4%
Artificial AnalysisGPT-6 Luna (High) SciCode50.3%
Artificial AnalysisGPT-6 Luna (High) Terminal-Bench 4.04.5%
Artificial AnalysisGPT-6 Luna (High) AA-Omniscience Accuracy39.0%
Artificial AnalysisGPT-6 Luna (High) AA-Omniscience Non-Hallucination Rate15.1%
Artificial AnalysisGPT-6 Luna (Non-reasoning) Intelligence Index9.4
Artificial AnalysisGPT-6 Luna (Non-reasoning) HLE8.6%
Artificial AnalysisGPT-6 Luna (Non-reasoning) AA-LCR39.7%
Artificial AnalysisGPT-6 Luna (Non-reasoning) GDPval-AA27.6%
Artificial AnalysisGPT-6 Luna (Non-reasoning) CritPt1.1%
Artificial AnalysisGPT-6 Luna (Non-reasoning) SciCode43.1%
Artificial AnalysisGPT-6 Luna (Non-reasoning) Terminal-Bench 4.01.5%
Artificial AnalysisGPT-6 Luna (Non-reasoning) AA-Omniscience Accuracy30.1%
Artificial AnalysisGPT-6 Luna (Non-reasoning) AA-Omniscience Non-Hallucination Rate20.0%
Artificial AnalysisGPT-6 Luna (Low) Intelligence Index9.7
Artificial AnalysisGPT-6 Luna (Low) HLE20.3%
Artificial AnalysisGPT-6 Luna (Low) AA-LCR74.0%
Artificial AnalysisGPT-6 Luna (Low) GDPval-AA27.0%
Artificial AnalysisGPT-6 Luna (Low) CritPt2.6%
Artificial AnalysisGPT-6 Luna (Low) SciCode46.9%
Artificial AnalysisGPT-6 Luna (Low) Terminal-Bench 4.00.0%
Artificial AnalysisGPT-6 Luna (Low) AA-Omniscience Accuracy36.1%
Artificial AnalysisGPT-6 Luna (Low) AA-Omniscience Non-Hallucination Rate15.2%
Artificial AnalysisGPT-6 Luna (Medium) Intelligence Index18.5
Artificial AnalysisGPT-6 Luna (Medium) HLE28.3%
Artificial AnalysisGPT-6 Luna (Medium) AA-LCR78.3%
Artificial AnalysisGPT-6 Luna (Medium) GDPval-AA38.5%
Artificial AnalysisGPT-6 Luna (Medium) CritPt10.6%
Artificial AnalysisGPT-6 Luna (Medium) SciCode50.9%
Artificial AnalysisGPT-6 Luna (Medium) Terminal-Bench 4.02.5%
Artificial AnalysisGPT-6 Luna (Medium) AA-Omniscience Accuracy38.7%
Artificial AnalysisGPT-6 Luna (Medium) AA-Omniscience Non-Hallucination Rate14.7%
Artificial AnalysisGPT-6 Luna (Max) Intelligence Index27.9
Artificial AnalysisGPT-6 Luna (Max) HLE38.5%
Artificial AnalysisGPT-6 Luna (Max) AA-LCR83.3%
Artificial AnalysisGPT-6 Luna (Max) GDPval-AA47.2%
Artificial AnalysisGPT-6 Luna (Max) CritPt19.4%
Artificial AnalysisGPT-6 Luna (Max) SciCode54.6%
Artificial AnalysisGPT-6 Luna (Max) Terminal-Bench 4.012.6%
Artificial AnalysisGPT-6 Luna (Max) AA-Omniscience Accuracy39.6%
Artificial AnalysisGPT-6 Luna (Max) AA-Omniscience Non-Hallucination Rate20.7%
Artificial AnalysisGPT-6 Luna (Xhigh) Intelligence Index23.5
Artificial AnalysisGPT-6 Luna (Xhigh) HLE34.3%
Artificial AnalysisGPT-6 Luna (Xhigh) AA-LCR80.0%
Artificial AnalysisGPT-6 Luna (Xhigh) GDPval-AA43.7%
Artificial AnalysisGPT-6 Luna (Xhigh) CritPt17.4%
Artificial AnalysisGPT-6 Luna (Xhigh) SciCode51.7%
Artificial AnalysisGPT-6 Luna (Xhigh) Terminal-Bench 4.08.1%
Artificial AnalysisGPT-6 Luna (Xhigh) AA-Omniscience Accuracy38.6%
Artificial AnalysisGPT-6 Luna (Xhigh) AA-Omniscience Non-Hallucination Rate16.0%
Vals AIGPT-6 Luna BioMysteryBench61.5%
Vals AIGPT-6 Luna ClaimBench99.2%
Vals AIGPT-6 Luna Code Migration v1.146.7%
Vals AIGPT-6 Luna CyberBench v1.176.3%
Vals AIGPT-6 Luna EMB v1.170.0%
Vals AIGPT-6 Luna Finance Agent v2.156.8%
Vals AIGPT-6 Luna Vals Finance Index53.1%
Vals AIGPT-6 Luna Financial Coaching Bench65.2%
Vals AIGPT-6 Luna HLAB-Vals-1.14.2%
Vals AIGPT-6 Luna Immigration62.5%
Vals AIGPT-6 Luna IOI55.6%
Vals AIGPT-6 Luna Vals Legal Index62.2%
Vals AIGPT-6 Luna Legal Research Bench30.3%
Vals AIGPT-6 Luna MedCode44.7%
Vals AIGPT-6 Luna MedScribe83.7%
Vals AIGPT-6 Luna MysteryMechanism19.4%
Vals AIGPT-6 Luna ProgramBench0.5%
Vals AIGPT-6 Luna ProofBench v1.164.0%
Vals AIGPT-6 Luna Public Benefits Bench v1.157.6%
Vals AIGPT-6 Luna SAGE83.4%
Vals AIGPT-6 Luna Vals Science Index28.4%
Vals AIGPT-6 Luna SRE Bench2.7%
Vals AIGPT-6 Luna SWE-bench Multimodal37.5%
Vals AIGPT-6 Luna Tax Agent Bench19.9%
Vals AIGPT-6 Luna Terminal-Bench 4.013.6%
Vals AIGPT-6 Luna Terminal-Bench-Science4.3%
Vals AIGPT-6 Luna Vals Index52.3%
Vals AIGPT-6 Luna Vibe Code Bench v1.181.6%
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.
1.
Codex
A coding agent that helps you build and ship with AI
3.61Ttokens
2.
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.
1.72Ttokens
3.
pi
There are many coding agents, but this one is yours.
529Btokens
4.
websim
new
415Btokens
5.
Freebuff
Powerful coding models, funded by ads
370Btokens
Rest of OpenRouter
72.8B
Top 5 Apps
11.8B
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
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 EuropeAzurePrices in Europe
Azure: $0.11/M tokens input, $0.55/M tokens output
Base URLhttps://eu.openrouter.ai/api/v1PlanRequires 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
Documentation
Guides, cookbooks, blog posts, and tools for building with OpenAI: GPT-6 Luna on OpenRouter.
GPT-6 Migration GuideCookbook
Reranking in RAG: How to Fix Bad Retrieval with a RerankerBlog post
How to Benchmark LLMsBlog post
How to Stop an AI Agent Stuck in an Infinite LoopBlog post
MCP vs CLI vs Skills: What Each Costs in ContextBlog post
LLM API Rate Limits: How to Fix OpenAI and Claude 429 ErrorsBlog post
How to Get Structured Output from Any LLM: JSON Schema, Tool Calls, or a Decision ModelBlog post
How to Build a Voice AI AgentBlog post
Build an AI Code Reviewer with OpenRouterBlog post
How to Extract Tables from a PDF with an LLMBlog post
Frequently asked questions
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.
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.
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.
GPT-6 Luna has a 1,050,000 token context window. It supports up to 128,000 completion tokens.
Yes. GPT-6 Luna accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
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.
GPT-6 Luna accepts files such as PDFs, images, and text as input and returns text.
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.
GPT-6 Luna was released on September 22, 2026.