Home/Models
Models/OpenAI

GPT-6 Luna

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.

openai/gpt-6-luna
Organization
OpenAI
Family
gpt-luna
Providers
36
Context
1,050,000
Output limit
128,000
Knowledge
2026-05-18
Release
2026-09-22
Updated
—
Weights
Closed
Input
text, image/jpeg, image/png, image/gif, image/webp, application/pdf
Output
text
Capabilities
—

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

47 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
302.AI
gpt-6-luna
1,050,000128,000— / ————
View
AIHubMix
gpt-6-luna
1,050,000128,000— / ————
View
AI/ML API
openai/gpt-6-luna
1,050,000128,000— / ————
View
Aixy
openai/gpt-6-luna
1,050,000128,000— / ————
View
Amazon Bedrock
openai.gpt-6-luna
1,050,000128,000— / ————
View
Amazon Bedrock
us.openai.gpt-6-luna
1,050,000128,000— / ————
View
Amazon Bedrock
global.openai.gpt-6-luna
1,050,000128,000— / ————
View
Azure
gpt-6-luna
1,050,000128,000— / ————
View
Boundless
gpt-6-luna
1,050,000128,000— / ————
View
Cloudflare AI Gateway
openai/gpt-6-luna
1,050,000128,000— / ————
View
CommandCode
gpt-6-luna
1,050,000128,000— / ————
View
Cortecs
gpt-6-luna
1,050,000128,000— / ————
View
CrossModel
openai/gpt-6-luna
1,050,000128,000— / ————
View
DevPass (LLM Gateway)
gpt-6-luna
1,050,000128,000— / ————
View
DigitalOcean
openai-gpt-6-luna
1,050,000128,000— / ————
View
Eden AI
openai/gpt-6-luna
1,050,000128,000— / ————
View
GitHub Copilot
gpt-6-luna
1,050,000128,000— / ————
View
GitLab Duo
duo-chat-gpt-6-luna
1,050,000128,000— / ————
View
Kilo Gateway
openai/gpt-6-luna
1,050,000128,000— / ————
View
LLM Gateway
openai/gpt-6-luna
1,050,000128,000— / ————
View
LLM Gateway
azure/gpt-6-luna
1,050,000128,000— / ————
View
LowRouter
auto/openai/gpt-6-luna
1,050,000128,000— / ————
View
Merge Gateway
openai/gpt-6-luna
1,050,000128,000— / ————
View
NanoGPT
openai/gpt-6-luna
1,050,000128,000— / ————
View
NEAR AI Cloud
openai/gpt-6-luna
1,050,000128,000— / ————
View
Neon
gpt-6-luna
1,050,000128,000— / ————
View
Ofox
openai/gpt-6-luna
1,050,000128,000— / ————
View
OpenAI
gpt-6-luna
1,050,000128,000— / ————
View
OpenCode
gpt-6-luna
1,050,000128,000— / ————
View
OpenCode Go
gpt-6-luna
1,050,000128,000— / ————
View
Amazon Bedrockvia OpenRouter
openai/gpt-6-luna
unknown		1,050,000128,000$0.11 / $0.55YesYesYes
View
Azurevia OpenRouter
openai/gpt-6-luna
unknown		1,050,000128,000$0.10 / $0.50YesYesYes
View
Azurevia OpenRouter
openai/gpt-6-luna
unknown		1,050,000128,000$0.11 / $0.55YesYesYes
View
Azurevia OpenRouter
openai/gpt-6-luna
unknown		1,050,000128,000$0.11 / $0.55YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-luna
unknown		1,050,000128,000$0.05 / $0.25YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-luna
unknown		1,050,000128,000$0.10 / $0.50YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-luna
unknown		1,050,000128,000$0.20 / $1.00YesYesYes
View
Perplexity Agent
openai/gpt-6-luna
1,050,000128,000— / ————
View
Prime Inference
openai/gpt-6-luna
1,050,000128,000— / ————
View
Requesty
gpt-6-luna@eu
1,050,000128,000— / ————
View
Requesty
gpt-6-luna
1,050,000128,000— / ————
View
SAP AI Core
gpt-6-luna
1,050,000128,000— / ————
View
Standard Compute
openai/gpt-6-luna
1,050,00050,000— / ————
View
Venice AI
openai-gpt-6-luna
1,050,000128,000— / ————
View
Vercel AI Gateway
openai/gpt-6-luna
1,050,000128,000— / ————
View
Vercel AI Gateway
openai/gpt-6-luna-fast
1,050,000128,000— / ————
View
Vivgrid
gpt-6-luna
1,050,000128,000— / ————
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.05Per 1M input tokens
Output from$0.25Per 1M output tokens
Available offers47Across 36 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 7 lowest-priced configurations
InputOutput
OpenAIopenai/flex
$0.05$0.25
Azureazure
$0.10$0.50
OpenAIopenai
$0.10$0.50
Amazon Bedrockamazon-bedrock/us-east-1
$0.11$0.55
Azureazure/us
$0.11$0.55
Azureazure/eu
$0.11$0.55
OpenAIopenai/fast
$0.20$1.00
openai/gpt-6-lunaObserved
Input
$0.10
Output
$0.50
Cache read
$0.01
Cache write
$0.125
Additional fees and pricing conditions
web search
$0.01 / search

overrides · USD per token for token prices; time windows use UTC.

[
  {
    "prompt": "0.0000002",
    "completion": "0.00000075",
    "input_cache_read": "0.00000002",
    "input_cache_write": "0.00000025",
    "min_prompt_tokens": 272000
  }
]
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Amazon Bedrockamazon-bedrock/us-east-1$0.11$0.55$0.011$0.1375
Azureazure$0.10$0.50$0.01$0.125
Azureazure/us$0.11$0.55$0.011$0.1375
Azureazure/eu$0.11$0.55$0.011$0.1375
OpenAIopenai/flex$0.05$0.25$0.005$0.0625
OpenAIopenai$0.10$0.50$0.01$0.125
OpenAIopenai/fast$0.20$1.00$0.02$0.25

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock/us-east-1
3,057–45,687.48 ms
Azureazure
2,939–57,875.56 ms
Azureazure/us
5,118–19,699.6 ms
Azureazure/eu
697.5–5,894.62 ms
OpenAIopenai/flex
4,319.5–68,872.43 ms
OpenAIopenai
2,541.5–35,104.63 ms
All latency percentiles 7 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/us-east-13,057 ms6,342 ms9,781 ms45,687.48 ms
Azureazure2,939 ms5,693 ms13,119.8 ms57,875.56 ms
Azureazure/us5,118 ms7,725 ms10,641.8 ms19,699.6 ms
Azureazure/eu697.5 ms931 ms1,374.8 ms5,894.62 ms
OpenAIopenai/flex4,319.5 ms8,984 ms17,675.6 ms68,872.43 ms
OpenAIopenai2,541.5 ms4,903.25 ms11,616.2 ms35,104.63 ms
OpenAIopenai/fast1,500 ms2,398 ms3,661.9 ms9,621.12 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock/us-east-1
34–69 t/s
Azureazure
80–222 t/s
Azureazure/us
56–199.95 t/s
Azureazure/eu
65–171 t/s
OpenAIopenai/flex
36–82.09 t/s
OpenAIopenai
76–155 t/s
All throughput percentiles 7 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/us-east-134 t/s44 t/s53 t/s69 t/s
Azureazure80 t/s120 t/s157 t/s222 t/s
Azureazure/us56 t/s91 t/s146 t/s199.95 t/s
Azureazure/eu65 t/s75 t/s108 t/s171 t/s
OpenAIopenai/flex36 t/s49 t/s62 t/s82.09 t/s
OpenAIopenai76 t/s99 t/s119 t/s155 t/s
OpenAIopenai/fast94 t/s132 t/s166 t/s234.75 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 7 endpoints
Endpoint5 minutes30 minutes24 hours
Amazon Bedrockamazon-bedrock/us-east-1
Azureazure
Azureazure/us
Azureazure/eu
OpenAIopenai/flex
OpenAIopenai
OpenAIopenai/fast

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations
openai/gpt-6-lunaObserved
Benchmark profileArtificial Analysis · shared source scale from 0 to 40
Intelligence38.1

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
tau bench verified airlineOpenAI: GPT-6 Luna
67.333%
gpqa diamondOpenAI: GPT-6 Luna
87.374%
EvaluationConfigurationSourceResultsDetails
tau bench verified airlineOpenAI: GPT-6 Lunaopenai/gpt-6-luna-20260922OpenRouter67.333%
Details
gpqa diamondOpenAI: GPT-6 Lunaopenai/gpt-6-luna-20260922OpenRouter87.374%
Details
Composite indicesGPT-6 Luna (Max)openai/gpt-6-luna-20260922Artificial AnalysisIntelligence 27.9 · Coding — · Agentic —
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Nov 5, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Nov 1, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Hermes Agentopenai/gpt-6-luna-2026092210–49 turns
$0.022574
Details
Codexopenai/gpt-6-luna-202609222–9 turns
$0.00489
Details
Kilo Codeopenai/gpt-6-luna-202609221 turn
$0.000165
Details
Hermes Agentopenai/gpt-6-luna-202609221 turn
$0.000827
Details
Hermes Agentopenai/gpt-6-luna-2026092250+ turns
$0.19985
Details
Claude Codeopenai/gpt-6-luna-2026092210–49 turns
$0.023619
Details
Claude Codeopenai/gpt-6-luna-202609222–9 turns
$0.004358
Details
Codexopenai/gpt-6-luna-202609221 turn
$0.001472
Details
Claude Codeopenai/gpt-6-luna-2026092250+ turns
$0.216731
Details
Codexopenai/gpt-6-luna-2026092250+ turns
$0.212752
Details
Codexopenai/gpt-6-luna-2026092210–49 turns
$0.025835
Details
Claude Codeopenai/gpt-6-luna-202609221 turn
$0.001896
Details
Kilo Codeopenai/gpt-6-luna-2026092210–49 turns
$0.034348
Details
Kilo Codeopenai/gpt-6-luna-2026092250+ turns
$0.262049
Details
Hermes Agentopenai/gpt-6-luna-202609222–9 turns
$0.003423
Details
Kilo Codeopenai/gpt-6-luna-202609222–9 turns
$0.008689
Details

Source: OpenRouter, as of Nov 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage43,678,383,142,844 reported tokens · 44 days with observations
Aug 7, 2026Nov 4, 2026
Daily observations · 44 days
Date (UTC)Reported tokensReported routes
Nov 4, 20261,136,980,562,5961
Nov 3, 20261,123,732,156,3001
Nov 2, 20261,122,007,411,4811
Nov 1, 2026802,869,553,1771
Oct 31, 2026810,419,813,2101
Oct 30, 20261,191,780,388,6361
Oct 29, 20262,758,971,784,1261
Oct 28, 20261,449,406,472,0941
Oct 27, 20261,083,066,115,6211
Oct 26, 20261,519,856,222,1291
Oct 25, 20261,458,177,596,3041
Oct 24, 20261,465,881,824,6141
Oct 23, 20261,625,523,749,1431
Oct 22, 2026986,155,259,8381
Oct 21, 2026937,191,027,8801
Oct 20, 20261,003,654,278,9091
Oct 19, 2026878,201,839,7051
Oct 18, 2026644,405,855,2831
Oct 17, 2026659,876,937,2631
Oct 16, 2026988,368,486,3361
Oct 15, 2026969,454,323,2361
Oct 14, 20261,066,569,516,8701
Oct 13, 20261,023,174,468,7531
Oct 12, 2026856,178,804,9341
Oct 11, 2026725,903,254,2661
Oct 10, 2026868,303,635,7621
Oct 9, 20261,257,848,001,5501
Oct 8, 20261,273,209,399,9921
Oct 7, 20261,094,658,009,5571
Oct 6, 20261,029,487,811,7521
Oct 5, 2026829,955,752,5071
Oct 4, 2026768,858,890,8611
Oct 3, 2026684,904,908,7551
Oct 2, 2026886,998,159,1021
Oct 1, 20261,161,202,170,9431
Sep 30, 20261,082,509,348,8561
Sep 29, 2026797,726,746,5701
Sep 28, 2026798,326,275,2451
Sep 27, 2026591,200,152,3191
Sep 26, 2026619,085,666,3311
Sep 25, 2026623,670,916,7791
Sep 24, 2026540,391,034,4291
Sep 23, 2026409,510,007,9561
Sep 22, 202672,728,550,8741

Source: OpenRouter (openrouter.ai/rankings), as of Nov 5, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
openai/gpt-6-lunaObserved
Context
1,050,000
Maximum output
128,000
Tokenizer
GPT
Input
file, image, text
Output
text
Moderation
Yes
Added to OpenRouter
2026-09-22
Base URLhttps://openrouter.ai/api/v1
Model IDopenai/gpt-6-luna
Version IDopenai/gpt-6-luna-20260922

Reasoning

Required
No
Enabled by default
Yes
Default effort
medium
Supported efforts
max, xhigh, high, medium, low, none

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • seed
  • structured_outputs
  • tool_choice
  • tools
  • verbosity

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does GPT-6 Luna cost?

Listed rates start at $0.05 per million input tokens and $0.25 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GPT-6 Luna?

There are 47 cataloged offers across 36 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,050,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 29360f15b22d
  • · efeb9b33f0b6