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 light…
openai/gpt-6-luna-20260922
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.
Specifications & capabilities
- Input
- file, image, text
- Output
- text
- Context window · tokens
- 1050000
- Published model ID
- gpt-6-luna
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
1–20 / 139
0.01
- source id
- lmarena
- leaderboard name
- LMArena Agent Tool Hallucination Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 10
- sample size
- 77405
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT-6 Luna (Medium)
- confidence lower
- 0.009155283989100134
- confidence upper
- 0.01065747494577564
Original result ↗0.01
- source id
- lmarena
- leaderboard name
- LMArena Agent Tool Hallucination Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 11
- sample size
- 40869
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT-6 Luna (Low)
- confidence lower
- 0.009155283988411027
- confidence upper
- 0.010657474945086294
Original result ↗1,211.014
- source id
- lmarena
- leaderboard name
- LMArena Search Style Control Overall
- dimension
- search
- metric
- Arena rating
- rank
- 12
- sample size
- 46776
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-6 Luna (Max)
- confidence lower
- 1203.8894347988116
- confidence upper
- 1218.1390006315773
Original result ↗88.159%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · OpenAI
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 13
- sample size
- 594
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 3
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- OpenAI
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-02T23:20:31.396Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 594
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8815936666666665
- accuracy_std_dev
- 0.00975199857579064
- cost_per_task_usd
- 0.002981575757575758
- output_tokens_per_task
- 5804.632996632997
- latency_seconds_per_task
- 52.993442760942756
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 26
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-6-luna-20260922
- source model id
- openai/gpt-6-luna-20260922
Original result ↗0.095
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Reliability Overall
- dimension
- general
- metric
- Arena score
- rank
- 14
- sample size
- 47705
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT-6 Luna (Max)
- confidence lower
- 0.09200047755198543
- confidence upper
- 0.09753676089797386
Original result ↗0.01
- source id
- lmarena
- leaderboard name
- LMArena Agent Tool Hallucination Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 16
- sample size
- 217070
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT-6 Luna (Max)
- confidence lower
- 0.009135384614307913
- confidence upper
- 0.010638071086762561
Original result ↗68%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · OpenAI
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 17
- sample size
- 150
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 3
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- OpenAI
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-02T23:08:44.329Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 150
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.68
- accuracy_std_dev
- 0.03810292105162893
- cost_per_task_usd
- 0.00883898
- output_tokens_per_task
- 8841.28
- latency_seconds_per_task
- 114.39612
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 27
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-6-luna-20260922
- source model id
- openai/gpt-6-luna-20260922
Original result ↗87.818%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Amazon Bedrock
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 18
- sample size
- 1583
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 8
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Amazon Bedrock
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-03T03:00:05.640Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1583
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8781846784586228
- accuracy_std_dev
- 0.00428175396303899
- cost_per_task_usd
- 0.00286223562855338
- output_tokens_per_task
- 5494.553379658875
- latency_seconds_per_task
- 91.55878395451674
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 32
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-6-luna-20260922
- source model id
- openai/gpt-6-luna-20260922
Original result ↗0.052
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Recovery Steps Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 19
- sample size
- 305361
- evaluated at
- 2026-10-08T00:00:00.000Z
- source model id
- GPT 6 Luna (Max)
- confidence lower
- 0.044084920435632204
- confidence upper
- 0.0600554760412246
Original result ↗0.069
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Reliability Overall
- dimension
- general
- metric
- Arena score
- rank
- 20
- sample size
- 16879
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT-6 Luna (Medium)
- confidence lower
- 0.06454756524180312
- confidence upper
- 0.0725027120899333
Original result ↗0.035
- source id
- lmarena
- leaderboard name
- LMArena Agent Steerability Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 20
- sample size
- 141119
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT-6 Luna (Max)
- confidence lower
- 0.029612685370268038
- confidence upper
- 0.041340585933141855
Original result ↗87.71%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Azure
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 21
- sample size
- 1188
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 6
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Azure
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-01T08:25:15.234Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1188
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8771043333333335
- accuracy_std_dev
- 0.007896528133018712
- cost_per_task_usd
- 0.003143374579124579
- output_tokens_per_task
- 5733.669191919192
- latency_seconds_per_task
- 35.45033585858586
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 43
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-6-luna-20260922
- source model id
- openai/gpt-6-luna-20260922
Original result ↗68.417%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Amazon Bedrock
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 24
- sample size
- 400
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 8
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- Amazon Bedrock
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-03T03:04:12.747Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 400
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.6841667499999999
- accuracy_std_dev
- 0.019982613972838976
- cost_per_task_usd
- 0.00873134
- output_tokens_per_task
- 8518.3375
- latency_seconds_per_task
- 302.344745
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 31
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-6-luna-20260922
- source model id
- openai/gpt-6-luna-20260922
Original result ↗1,185.559
- source id
- lmarena
- leaderboard name
- LMArena Search Factuality Overall
- dimension
- search
- metric
- Arena rating
- rank
- 25
- sample size
- 46776
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-6 Luna (Max)
- confidence lower
- 1180.490042872291
- confidence upper
- 1190.62729106611
Original result ↗1,565.906
- source id
- lmarena
- leaderboard name
- LMArena Webdev Image To Webdev
- dimension
- coding
- metric
- Arena rating
- rank
- 26
- sample size
- 7382
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- GPT-6 Luna (Max)
- confidence lower
- 1557.7217364747867
- confidence upper
- 1574.0898433427951
Original result ↗0.016
- source id
- lmarena
- leaderboard name
- LMArena Agent Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 26
- sample size
- 231000
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT-6 Luna (Max)
- confidence lower
- 0.011044273315355896
- confidence upper
- 0.020232590421098012
Original result ↗1,510.724
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Software And It Services
- dimension
- factuality
- metric
- Arena rating
- rank
- 27
- sample size
- 37844
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-6 Luna (Max)
- confidence lower
- 1506.0361912396347
- confidence upper
- 1515.4112630681725
Original result ↗1,497.872
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Hard Prompts
- dimension
- factuality
- metric
- Arena rating
- rank
- 28
- sample size
- 66562
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-6 Luna (Max)
- confidence lower
- 1494.0115537018141
- confidence upper
- 1501.7328138139037
Original result ↗-0.001
- source id
- lmarena
- leaderboard name
- LMArena Agent Steerability Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 28
- sample size
- 57064
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- GPT-6 Luna (Medium)
- confidence lower
- -0.00745773814293594
- confidence upper
- 0.0053465739335747465
Original result ↗68.111%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Azure
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 29
- sample size
- 300
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 6
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- Azure
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-01T08:05:22.516Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 300
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.6811111666666666
- accuracy_std_dev
- 0.008088865998326882
- cost_per_task_usd
- 0.00903582
- output_tokens_per_task
- 8459.866666666667
- latency_seconds_per_task
- 105.46992666666667
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 40
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-6-luna-20260922
- source model id
- openai/gpt-6-luna-20260922
Original result ↗Published prices
101–120 / 127
$0.55
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272001
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$0.28
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- max_exclusive
- 272001
- min_inclusive
- 0
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$0.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272001
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.10
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- max_exclusive
- 272001
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.05
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- flex
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- priority
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.40
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272001
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- max_exclusive
- 272001
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.22
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- eu
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272001
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.11
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- eu
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- max_exclusive
- 272001
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.22
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272001
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.11
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- max_exclusive
- 272001
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.44
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272001
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.22
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- max_exclusive
- 272001
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.75
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272001
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.50
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- max_exclusive
- 272001
- min_inclusive
- 0
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.25
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- flex
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- priority
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.50
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272001
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- max_exclusive
- 272001
- min_inclusive
- 0
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–5 / 5
- source model id
- gpt-6-luna
- hosting
- gateway
- context length
- 1050000
- max output tokens
- 128000
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- GPT-6 Luna
- hosting
- copilot-subscription
- license
- CC-BY-4.0
- attribution
- GitHub and github/docs contributors
- plans
- max
- true
- pro
- true
- business
- true
- pro_plus
- true
- enterprise
- true
- clients
- vs
- true
- cli
- true
- xcode
- true
- dotcom
- true
- vscode
- true
- eclipse
- true
- jetbrains
- true
- auto selection
- app
- true
- cli
- true
- chat
- true
- cloud_agent
- true
- access scope
- Published plan/client flags; account settings, organization policy and additional access conditions apply
- availability
- supported
- release status
- GA
- billing scope
- Copilot subscription usage; not an unconditional inference API rate
- billing rates
- tier
- Default
- unit
- tokens_per_million
- input
- 0.1
- output
- 0.5
- currency
- USD
- original
- tier
- Default
- input
- $0.10
- model
- GPT-6 Luna
- output
- $0.50
- category
- Lightweight
- provider
- openai
- threshold
- ≤ 272K
- cache_write
- $0.125
- cached_input
- $0.01
- release_status
- GA
- threshold
- ≤ 272K
- cache_write
- 0.125
- cached_input
- 0.01
- footnote_restrictions
- false
- requires_subscription
- true
- tier
- Long context
- unit
- tokens_per_million
- input
- 0.2
- output
- 0.75
- currency
- USD
- original
- tier
- Long context
- input
- $0.20
- model
- GPT-6 Luna
- output
- $0.75
- category
- Lightweight
- provider
- openai
- threshold
- > 272K
- cache_write
- $0.25
- cached_input
- $0.02
- release_status
- GA
- threshold
- > 272K
- cache_write
- 0.25
- cached_input
- 0.02
- footnote_restrictions
- false
- requires_subscription
- true
- comparison
- name
- GPT-6 Luna
- excels_at
- Quick, cost-efficient responses for smaller, faster tasks
- task_area
- Fast help with simple or repetitive tasks
- further_reading
- [GPT-6 Luna model card](https://deploymentsafety.openai.com/gpt-6-astra/gpt-6-astra.pdf)
- source model id
- openai.gpt-6-luna
- hosting
- bedrock-managed
- source model id
- openai/gpt-6-luna
- hosting
- third-party
- context length
- 1050000
- max output tokens
- 128000
- source model id
- openai/gpt-6-luna
- hosting
- vercel-gateway
- context length
- 1050000
- max output tokens
- 128000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/gpt-6-luna-20260922
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- OpenAI
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 35 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–12 / 12
- field
- context_length
- value
- 1050000
- normalized value
- 1050000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- context_length
- value
- 1050000
- normalized value
- 1050000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1050000
- normalized value
- 1050000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1050000
- normalized value
- 1050000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1050000
- normalized value
- 1050000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- May 18, 2026
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2026-05-18
- normalized value
- 2026-05-18
- precision
- day
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
Explore more models