OpenAI: GPT-5.6 Luna
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providi…
openai/gpt-5.6-luna-20260709
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.
Specifications & capabilities
- Input
- file, image, text
- Output
- text
- Context window · tokens
- 1050000
- Knowledge cutoff
- 2026-02-16
- Published model ID
- gpt-5.6-luna
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
1–20 / 113
72.667%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · OpenAI
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- 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
- 2026-10-02T23:07:05.152Z
- 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
- 0.7266666666666667
- accuracy_std_dev
- 0.014401440259764123
- cost_per_task_usd
- 0.013071513333333333
- output_tokens_per_task
- 4935.306666666666
- latency_seconds_per_task
- 97.59757333333333
- 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-5.6-luna-20260709
- source model id
- openai/gpt-5.6-luna-20260709
Original result ↗86.756%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · OpenAI
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 15
- 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
- 2026-10-02T23:19:10.742Z
- 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
- 0.8675643333333334
- accuracy_std_dev
- 0.0028614651647170092
- cost_per_task_usd
- 0.009448984848484849
- output_tokens_per_task
- 7744.79797979798
- latency_seconds_per_task
- 79.37702525252526
- 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-5.6-luna-20260709
- source model id
- openai/gpt-5.6-luna-20260709
Original result ↗87.879%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Amazon Bedrock
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 17
- 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
- Amazon Bedrock
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-30T00:00:06.145Z
- 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
- 0.8787880000000001
- accuracy_std_dev
- 0.007273551310513108
- cost_per_task_usd
- 0.009556249158249158
- output_tokens_per_task
- 7331.292929292929
- latency_seconds_per_task
- 52.070994949494946
- 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-5.6-luna-20260709
- source model id
- openai/gpt-5.6-luna-20260709
Original result ↗88.561%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Azure
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 20
- sample size
- 1186
- 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
- 2026-10-01T19:12:42.994Z
- 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
- 1186
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8856098161888702
- accuracy_std_dev
- 0.01054693657998484
- cost_per_task_usd
- 0.010296545531197302
- output_tokens_per_task
- 7923.973018549747
- latency_seconds_per_task
- 75.11894940978078
- 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-5.6-luna-20260709
- source model id
- openai/gpt-5.6-luna-20260709
Original result ↗70.556%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Azure
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 21
- 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
- 2026-10-01T19:05:16.550Z
- 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
- 0.7055558333333333
- accuracy_std_dev
- 0.032754340019894884
- cost_per_task_usd
- 0.012937629999999999
- output_tokens_per_task
- 4842.643333333333
- latency_seconds_per_task
- 95.53639333333332
- 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-5.6-luna-20260709
- source model id
- openai/gpt-5.6-luna-20260709
Original result ↗1,460.236
- source id
- lmarena
- leaderboard name
- LMArena Document Style Control Overall
- dimension
- productivity
- metric
- Arena rating
- rank
- 25
- sample size
- 8832
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1453.0368574571485
- confidence upper
- 1467.436107935731
Original result ↗68.222%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Amazon Bedrock
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 25
- 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
- Amazon Bedrock
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-30T00:15:40.872Z
- 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
- 0.6822223333333333
- accuracy_std_dev
- 0.021998563367234276
- cost_per_task_usd
- 0.014046139999999999
- output_tokens_per_task
- 5022.28
- latency_seconds_per_task
- 71.68916
- 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-5.6-luna-20260709
- source model id
- openai/gpt-5.6-luna-20260709
Original result ↗1,495.013
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality French
- dimension
- factuality
- metric
- Arena rating
- rank
- 26
- sample size
- 1097
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1478.5115292725527
- confidence upper
- 1511.514152719562
Original result ↗1,453.799
- source id
- lmarena
- leaderboard name
- LMArena Document Overall
- dimension
- productivity
- metric
- Arena rating
- rank
- 26
- sample size
- 8832
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1446.7771028174877
- confidence upper
- 1460.82181035018
Original result ↗1,461.153
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Spanish
- dimension
- factuality
- metric
- Arena rating
- rank
- 30
- sample size
- 999
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1444.0434255101009
- confidence upper
- 1478.2627826837809
Original result ↗0.005
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Recovery Steps Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 33
- sample size
- 108092
- evaluated at
- 2026-10-08T00:00:00.000Z
- source model id
- GPT 5.6 Luna (xHigh)
- confidence lower
- -0.005483332601142353
- confidence upper
- 0.015773038012478577
Original result ↗1,504.752
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Expert
- dimension
- factuality
- metric
- Arena rating
- rank
- 34
- sample size
- 3951
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1496.115032909837
- confidence upper
- 1513.388170441268
Original result ↗1,478.234
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control German
- dimension
- style
- metric
- Arena rating
- rank
- 34
- sample size
- 720
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1455.387332792542
- confidence upper
- 1501.0804188700718
Original result ↗1,485.657
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Legal And Government
- dimension
- factuality
- metric
- Arena rating
- rank
- 36
- sample size
- 2963
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1475.2464889478947
- confidence upper
- 1496.0665999731773
Original result ↗1,256.605
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Creative Writing Vision
- dimension
- multimodal
- metric
- Arena rating
- rank
- 39
- sample size
- 987
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1236.654399645836
- confidence upper
- 1276.5560730332897
Original result ↗87.626%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · auto-routing
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 39
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- auto-routing
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-01T19:14:22.294Z
- 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
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8762625
- accuracy_std_dev
- 0.005892500000000023
- cost_per_task_usd
- 0.009382047979797978
- output_tokens_per_task
- 7689.015151515152
- latency_seconds_per_task
- 83.11884595959596
- 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
- 132
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-5.6-luna-20260709
- source model id
- openai/gpt-5.6-luna-20260709
Original result ↗1,469.64
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Mathematical
- dimension
- factuality
- metric
- Arena rating
- rank
- 40
- sample size
- 1891
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1457.653957790863
- confidence upper
- 1481.6262612623009
Original result ↗1,469
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Math
- dimension
- factuality
- metric
- Arena rating
- rank
- 40
- sample size
- 1634
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1455.2518412022403
- confidence upper
- 1482.7473667906781
Original result ↗1,467.843
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Business And Management And Financial Operations
- dimension
- factuality
- metric
- Arena rating
- rank
- 41
- sample size
- 7119
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1461.2212361221523
- confidence upper
- 1474.464038939836
Original result ↗1,476.769
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Math
- dimension
- style
- metric
- Arena rating
- rank
- 43
- sample size
- 1903
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.6 Luna (xHigh)
- confidence lower
- 1463.0221077015221
- confidence upper
- 1490.516675553571
Original result ↗Published prices
101–120 / 121
$0.80
- 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
- 272000
- 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
- max_exclusive
- 272000
- 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
- eu
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272000
- 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
- max_exclusive
- 272000
- 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
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272000
- 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
- max_exclusive
- 272000
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.88
- 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
- 272000
- 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
- max_exclusive
- 272000
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.80
- 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
- 272000
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.20
- 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
- 272000
- min_inclusive
- 0
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.60
- 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
$2.40
- 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
$3.60
- 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
- 272000
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$2.40
- 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
- 272000
- min_inclusive
- 0
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.98
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_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
- 272000
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.32
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_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
- 272000
- min_inclusive
- 0
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.98
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_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
- 272000
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.32
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_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
- 272000
- min_inclusive
- 0
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$3.96
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_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
- 272000
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$2.64
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_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
- 272000
- min_inclusive
- 0
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–5 / 5
- source model id
- gpt-5.6-luna
- hosting
- gateway
- context length
- 1050000
- max output tokens
- 128000
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- GPT-5.6 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
- false
- dotcom
- true
- vscode
- true
- eclipse
- false
- jetbrains
- false
- 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
- 0.2
- output
- 1.2
- currency
- USD
- original
- tier
- Default
- input
- $0.20
- model
- GPT-5.6 Luna
- output
- $1.20
- category
- Lightweight
- provider
- openai
- threshold
- ≤ 200K
- cache_write
- $0.25
- cached_input
- $0.02
- release_status
- GA
- threshold
- ≤ 200K
- cache_write
- 0.25
- cached_input
- 0.02
- footnote_restrictions
- false
- requires_subscription
- true
- tier
- Long context
- unit
- tokens_per_million
- input
- 0.4
- output
- 1.8
- currency
- USD
- original
- tier
- Long context
- input
- $0.40
- model
- GPT-5.6 Luna
- output
- $1.80
- category
- Lightweight
- provider
- openai
- threshold
- > 200K
- cache_write
- $0.50
- cached_input
- $0.04
- release_status
- GA
- threshold
- > 200K
- cache_write
- 0.5
- cached_input
- 0.04
- footnote_restrictions
- false
- requires_subscription
- true
- comparison
- name
- GPT-5.6 Luna
- excels_at
- Quick, cost-efficient responses for smaller, faster coding tasks
- task_area
- Fast help with simple or repetitive tasks
- further_reading
- [GPT-5.6 model card](https://deploymentsafety.openai.com/gpt-5-6/gpt-5-6.pdf)
- source model id
- openai.gpt-5.6-luna
- hosting
- bedrock-managed
- source model id
- openai/gpt-5.6-luna
- hosting
- third-party
- context length
- 1050000
- max output tokens
- 128000
- source model id
- openai/gpt-5.6-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-5.6-luna-20260709
- 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
1–11 / 11
- 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
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2026-02-16
- normalized value
- 2026-02-16
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2026-02-16
- normalized value
- 2026-02-16
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2026-02-16
- normalized value
- 2026-02-16
- 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
- vercelAIGatewayCatalog
- confidence
- 1
Explore more models