AIpedia#198 GPT-6 Astra
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 | $0.5 / 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 | $0.5 / 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 | $1 / 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 | $1 / 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 | $1 / 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 | $2 / 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 | $2 / 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%. Fast is unavailable with EU data residency.Source · 19.09.2026 |
| OpenAI · API | $4 / 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%. Fast is unavailable with EU data residency.Source · 19.09.2026 |
| OpenAI · API | $6.25 / 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 | $6.25 / 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 | $12.5 / 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 | $12.5 / 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 | $12.5 / 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 | $25 / 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 | $25 / 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%. Fast is unavailable with EU data residency.Source · 19.09.2026 |
| OpenAI · API | $50 / 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%. Fast is unavailable with EU data residency.Source · 19.09.2026 |
| OpenAI · API | $5 / 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 | $5 / 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 | $10 / 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 | $10 / 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 | $10 / 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 | $20 / 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 | $20 / 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%. Fast is unavailable with EU data residency.Source · 19.09.2026 |
| OpenAI · API | $40 / 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%. Fast is unavailable with EU data residency.Source · 19.09.2026 |
| OpenAI · API | $25 / 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 | $25 / 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 | $37.5 / 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 | $37.5 / 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 | $50 / 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 | $75 / 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 | $100 / 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%. Fast is unavailable with EU data residency.Source · 19.09.2026 |
| OpenAI · API | $150 / 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%. Fast is unavailable with EU data residency.Source · 19.09.2026 |
Evaluator & score
Composite index · published model-group index · 20.09.2026 · Higher is better
Snapshot: 2026-09-20 · 90% CI [163, 171.88]
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 · 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-6-astra_max; mode: max; source id: TAGZYToqgQmFZr7uYL4rSF; 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: 30.08.2026
Independent run · max · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
EBR-bench; Epoch AI own run; best score across scorers
Epoch AI own run; EBR-bench; version: gpt-6-astra_max; mode: max; source id: GhVYxWxttDxZ7akiJQPYsE; file: ebr_bench.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
FrontierMath Open Problems (Erdős); Epoch AI own run; best score across scorers
Epoch AI own run; FrontierMath Open Problems (Erdős); version: gpt-6-astra_max; mode: max; source id: bloom68-ultima-e1dhs43ykrmakree; file: frontiermath_erdos.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: 28.08.2026
Independent run · high · 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-6-astra_high; mode: high; source id: f46NQY9jSxyKqo9qzrmk6F; 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: 30.08.2026
Independent run · low · 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-6-astra_low; mode: low; source id: kRPSnHnDdheajNdqmKsMjs; 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: 30.08.2026
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-6-astra_max; mode: max; source id: f7BCT27LzcAtaLDP2tcrWF; 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: 30.08.2026
Independent run · medium · 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-6-astra_medium; mode: medium; source id: 5sNRWemuVwb4adBaSwrLFf; 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: 30.08.2026
Independent run · none · 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-6-astra_none; mode: none; source id: 4BCZTu7HQKmhdwRR2W4bzT; 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: 30.08.2026
Independent run · xhigh · 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-6-astra_xhigh; mode: xhigh; source id: AfKJ2DGMhkjZmeFZxGoY3w; 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: 30.08.2026
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-6-astra_max; mode: max; source id: csK2fe5T8p2R7WgoJUu6bZ; 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: 30.08.2026
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; source version: gpt-6-astra_max; file: gpqa_diamond.csv; row: 3h8STJpG2VzY9LiBUzwotv.
Measurement date: 30.08.2026
Independent run · high · 20.09.2026 · Higher is better
Snapshot: 2026-09-20
Conditions
MirrorCode; Epoch AI own run; best score across scorers
Epoch AI own run; MirrorCode; version: gpt-6-astra_high; mode: high; source id: mirrorcode-ml-2l-gpt-6-astra; file: mirrorcode.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
Mock AIME 2024/2025; Epoch AI own run; best score across scorers
Epoch AI own run; source version: gpt-6-astra_max; file: otis_mock_aime_2024_2025.csv; row: L7kW8yxFKCjVXhxNnt3VTq.
Measurement date: 30.08.2026
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-6-astra_max; mode: max; source id: FA7pM9hKdkgTXmGHptcno7; 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-6-astra_max; mode: max; source id: PppwnX7EjXx2SeTcFN8Ujn; 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: 30.08.2026