AIpedia#165 GPT-5.6 Luna
Released: · SourceText; Coding; Reasoning
- Use cases
- Coding, Reasoning, Text
- Accepts
- No verified data
- Produces
- No verified data
Access
Price USD
| Provider | Price USD | Conditions |
|---|---|---|
| OpenAI · API | $0.01 / 1M cache-read tokens | Batch · short context · Batch; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.01 / 1M cache-read tokens | Flex · short context · Flex; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.02 / 1M cache-read tokens | Standard · short context · Standard; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.02 / 1M cache-read tokens | Batch · long context · Batch; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.02 / 1M cache-read tokens | Flex · long context · Flex; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.04 / 1M cache-read tokens | Standard · long context · Standard; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.04 / 1M cache-read tokens | Fast · short context · Fast; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.08 / 1M cache-read tokens | Fast · long context · Fast; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.125 / 1M cache-write tokens | Batch · short context · Batch; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.125 / 1M cache-write tokens | Flex · short context · Flex; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.25 / 1M cache-write tokens | Standard · short context · Standard; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.25 / 1M cache-write tokens | Batch · long context · Batch; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.25 / 1M cache-write tokens | Flex · long context · Flex; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.5 / 1M cache-write tokens | Standard · long context · Standard; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.5 / 1M cache-write tokens | Fast · short context · Fast; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $1 / 1M cache-write tokens | Fast · long context · Fast; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.1 / 1M input tokens | Batch · short context · Batch; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.1 / 1M input tokens | Flex · short context · Flex; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.2 / 1M input tokens | Standard · short context · Standard; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.2 / 1M input tokens | Batch · long context · Batch; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.2 / 1M input tokens | Flex · long context · Flex; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.4 / 1M input tokens | Standard · long context · Standard; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.4 / 1M input tokens | Fast · short context · Fast; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.8 / 1M input tokens | Fast · long context · Fast; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.6 / 1M output tokens | Batch · short context · Batch; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.6 / 1M output tokens | Flex · short context · Flex; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.9 / 1M output tokens | Batch · long context · Batch; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $0.9 / 1M output tokens | Flex · long context · Flex; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $1.2 / 1M output tokens | Standard · short context · Standard; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $1.8 / 1M output tokens | Standard · long context · Standard; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $2.4 / 1M output tokens | Fast · short context · Fast; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
| OpenAI · API | $3.6 / 1M output tokens | Fast · long context · Fast; The short/long threshold has not been verified. Cache writes have a separate rate. Additional tools are billed separately. Eligible regional processing endpoints: +10%.Source · 19.09.2026 |
Evaluator & score
Composite index · published model-group index · 20.09.2026 · Higher is better
Snapshot: 2026-09-20 · 90% CI [154.06, 158.86]
Official Epoch AI index; combines own, third-party and developer-reported results. It is not a safety audit or a media-generation score.
Conditions
Epoch Capabilities Index; official model-group estimates
Official ECI model scores, Epoch AI, CC BY 4.0. Composite of own, third-party and developer-reported results. 90% bootstrap interval. Not a per-effort score; export date is the model release date, not measurement date. Methodology: https://epoch.ai/eci#documentation
Independent run · low · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Chess Puzzles; Epoch AI own run; best score across scorers
Epoch AI own run; Chess Puzzles; version: gpt-5.6-luna_low; mode: low; source id: UhmACN5spAPyAtWWBf4MAP; file: chess_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 07.08.2026
Independent run · max · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Chess Puzzles; Epoch AI own run; best score across scorers
Epoch AI own run; Chess Puzzles; version: gpt-5.6-luna_max; mode: max; source id: BJiQ8aRjMyCGPTBGYfBhyj; file: chess_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 09.07.2026
Independent run · none · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Chess Puzzles; Epoch AI own run; best score across scorers
Epoch AI own run; Chess Puzzles; version: gpt-5.6-luna_none; mode: none; source id: d9jMGFp8BwebW7sufdxbnC; file: chess_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 07.08.2026
Independent run · max · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
FrontierMath-Tier-4-v2-Private; Epoch AI own run; best score across scorers
Epoch AI own run; FrontierMath-Tier-4-v2-Private; version: gpt-5.6-luna_max; mode: max; source id: NLiiJJSyA9wmg2FHENFpAq; file: frontiermath_tier_4_v2.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 09.07.2026
Independent run · low · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
FrontierMath-Tiers-1-3-v2-Private; Epoch AI own run; best score across scorers
Epoch AI own run; FrontierMath-Tiers-1-3-v2-Private; version: gpt-5.6-luna_low; mode: low; source id: ZryXhNUpPedPvGhbqdNBEw; file: frontiermath_tiers_1_3_v2.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 29.08.2026
Independent run · max · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
FrontierMath-Tiers-1-3-v2-Private; Epoch AI own run; best score across scorers
Epoch AI own run; FrontierMath-Tiers-1-3-v2-Private; version: gpt-5.6-luna_max; mode: max; source id: YLAk5J3Wd8EruVXee8bAQb; file: frontiermath_tiers_1_3_v2.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 09.07.2026
Independent run · none · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
FrontierMath-Tiers-1-3-v2-Private; Epoch AI own run; best score across scorers
Epoch AI own run; FrontierMath-Tiers-1-3-v2-Private; version: gpt-5.6-luna_none; mode: none; source id: YwHKNFQjbat97wVLqachmi; file: frontiermath_tiers_1_3_v2.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 29.08.2026
Independent run · low · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
GPQA Diamond; Epoch AI own run; best score across scorers
Epoch AI own run; GPQA diamond; version: gpt-5.6-luna_low; mode: low; source id: nW39ZzuDQ3xTAGVoEfFG95; file: gpqa_diamond.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 07.08.2026
Independent run · max · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
GPQA Diamond; Epoch AI own run; best score across scorers
Epoch AI own run; GPQA diamond; version: gpt-5.6-luna_max; mode: max; source id: LWkDtkmd3TNmLzMhfZD5HW; file: gpqa_diamond.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 09.07.2026
Independent run · none · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
GPQA Diamond; Epoch AI own run; best score across scorers
Epoch AI own run; GPQA diamond; version: gpt-5.6-luna_none; mode: none; source id: bDKKx7zTdW5WwMCfwqsLi4; file: gpqa_diamond.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 07.08.2026
Independent run · low · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Mock AIME 2024/2025; Epoch AI own run; best score across scorers
Epoch AI own run; OTIS Mock AIME 2024-2025; version: gpt-5.6-luna_low; mode: low; source id: ZgU8BagFmaj7BE94y3JDZA; file: otis_mock_aime_2024_2025.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 07.08.2026
Independent run · max · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Mock AIME 2024/2025; Epoch AI own run; best score across scorers
Epoch AI own run; OTIS Mock AIME 2024-2025; version: gpt-5.6-luna_max; mode: max; source id: AhtQ5ggs4pTfLDqHFjueGy; file: otis_mock_aime_2024_2025.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 09.07.2026
Independent run · none · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Mock AIME 2024/2025; Epoch AI own run; best score across scorers
Epoch AI own run; OTIS Mock AIME 2024-2025; version: gpt-5.6-luna_none; mode: none; source id: QYZ6wRuT7WMkaYPKc9dRPy; file: otis_mock_aime_2024_2025.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 07.08.2026
Independent run · low · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Mystery Game Puzzles; Epoch AI own run; best score across scorers
Epoch AI own run; Mystery Game Puzzles; version: gpt-5.6-luna_low; mode: low; source id: iTY94tKhVEcZsUZivMwLJa; file: mystery_game_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 27.08.2026
Independent run · max · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Mystery Game Puzzles; Epoch AI own run; best score across scorers
Epoch AI own run; Mystery Game Puzzles; version: gpt-5.6-luna_max; mode: max; source id: Epg7eNLwwGPXtX3sSAwPf8; file: mystery_game_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 28.07.2026
Independent run · medium · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Mystery Game Puzzles; Epoch AI own run; best score across scorers
Epoch AI own run; Mystery Game Puzzles; version: gpt-5.6-luna_medium; mode: medium; source id: BvShPsULJMkwxxf8vBSNfu; file: mystery_game_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 27.08.2026
Independent run · none · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
Mystery Game Puzzles; Epoch AI own run; best score across scorers
Epoch AI own run; Mystery Game Puzzles; version: gpt-5.6-luna_none; mode: none; source id: PBrQpAgRCXeUSNveEn4aDE; file: mystery_game_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 30.08.2026
Independent run · max · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
SimpleQA Verified; Epoch AI own run; best score across scorers
Epoch AI own run; SimpleQA Verified; version: gpt-5.6-luna_max; mode: max; source id: CeDghdBk8CqtiFSbUzxNH5; file: simpleqa_verified.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.
Measurement date: 10.08.2026