GPT-6 Astra
Closed weights. No supported local deployment or GPU requirement is published.
GeekRadar / The comparison desk
COMPARE.
AI modelsGPT-6 Astra
AI model Released
- API mode
- Chat*
- Context window
- 1,050,000 tokens
- Maximum output
- 128,000 tokens
- Open weights
- No
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
Benchmark results
- Reported score · version unreported · intelligence61*Platform unreported Compare results
Recorded results
Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Arena text preference / chinesehuman preference · 2026-10-28 · rating
GPT-6 Astra
1,491.70 rating
Confidence interval: 1,474.50 – 1,508.90
1185 votes
- Category
- chinese
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
GPT-6 Astra
1,487.99 rating
Confidence interval: 1,477.40 – 1,498.59
3393 votes
- Category
- coding
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
GPT-6 Astra
1,420.18 rating
Confidence interval: 1,408.91 – 1,431.45
3323 votes
- Category
- creative_writing
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,447.12 rating
Confidence interval: 1,438.86 – 1,455.39
6008 votes
- Category
- english
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
GPT-6 Astra
1,436.65 rating
Confidence interval: 1,428.96 – 1,444.35
11081 votes
- Category
- exclude_ties
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
GPT-6 Astra
1,493.25 rating
Confidence interval: 1,477.65 – 1,508.85
1451 votes
- Category
- expert
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,435.17 rating
Confidence interval: 1,406.92 – 1,463.41
473 votes
- Category
- french
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,459.35 rating
Confidence interval: 1,421.28 – 1,497.43
237 votes
- Category
- german
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
GPT-6 Astra
1,462.09 rating
Confidence interval: 1,455.04 – 1,469.14
9105 votes
- Category
- hard_prompts
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,464.53 rating
Confidence interval: 1,454.18 – 1,474.87
3634 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
GPT-6 Astra
1,437.61 rating
Confidence interval: 1,425.60 – 1,449.62
2613 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
GPT-6 Astra
1,426.97 rating
Confidence interval: 1,416.54 – 1,437.40
3837 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
GPT-6 Astra
1,455.34 rating
Confidence interval: 1,438.28 – 1,472.40
1263 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
GPT-6 Astra
1,449.61 rating
Confidence interval: 1,437.40 – 1,461.82
2543 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,486.66 rating
Confidence interval: 1,466.58 – 1,506.74
875 votes
- Category
- industry_mathematical
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
GPT-6 Astra
1,419.09 rating
Confidence interval: 1,400.49 – 1,437.70
1067 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
GPT-6 Astra
1,474.61 rating
Confidence interval: 1,466.00 – 1,483.23
5349 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
GPT-6 Astra
1,438.67 rating
Confidence interval: 1,428.76 – 1,448.59
4214 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
GPT-6 Astra
1,454.06 rating
Confidence interval: 1,444.98 – 1,463.15
4755 votes
- Category
- instruction_following
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
GPT-6 Astra
1,406.74 rating
Confidence interval: 1,370.41 – 1,443.06
296 votes
- Category
- japanese
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,429.64 rating
Confidence interval: 1,392.05 – 1,467.23
256 votes
- Category
- korean
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,460.94 rating
Confidence interval: 1,452.59 – 1,469.29
6225 votes
- Category
- longer_query
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,467.95 rating
Confidence interval: 1,447.56 – 1,488.34
804 votes
- Category
- math
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,448.42 rating
Confidence interval: 1,434.98 – 1,461.85
2103 votes
- Category
- multi_turn
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,431.62 rating
Confidence interval: 1,424.56 – 1,438.68
9026 votes
- Category
- non_english
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,441.15 rating
Confidence interval: 1,435.24 – 1,447.07
15038 votes
- Category
- overall
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,422.97 rating
Confidence interval: 1,385.00 – 1,460.94
214 votes
- Category
- polish
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,441.18 rating
Confidence interval: 1,427.36 – 1,454.99
1938 votes
- Category
- russian
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
GPT-6 Astra
1,418.52 rating
Confidence interval: 1,391.59 – 1,445.45
479 votes
- Category
- spanish
- Evaluated configuration
- GPT-6 Astra (Max)
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
GPT-6 Astra
1,492.99 rating
Confidence interval: 1,473.87 – 1,512.10
917 votes
- Category
- chinese
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
GPT-6 Astra
1,489.11 rating
Confidence interval: 1,477.54 – 1,500.68
2744 votes
- Category
- coding
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
GPT-6 Astra
1,421.13 rating
Confidence interval: 1,408.95 – 1,433.30
2718 votes
- Category
- creative_writing
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,447.86 rating
Confidence interval: 1,438.97 – 1,456.76
4918 votes
- Category
- english
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
GPT-6 Astra
1,438.48 rating
Confidence interval: 1,430.30 – 1,446.67
8981 votes
- Category
- exclude_ties
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
GPT-6 Astra
1,487.86 rating
Confidence interval: 1,470.57 – 1,505.15
1166 votes
- Category
- expert
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,444.41 rating
Confidence interval: 1,412.48 – 1,476.35
357 votes
- Category
- french
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,457.05 rating
Confidence interval: 1,414.98 – 1,499.13
192 votes
- Category
- german
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
GPT-6 Astra
1,464.05 rating
Confidence interval: 1,456.52 – 1,471.57
7400 votes
- Category
- hard_prompts
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,463.12 rating
Confidence interval: 1,451.92 – 1,474.33
2983 votes
- Category
- hard_prompts_english
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
GPT-6 Astra
1,438.98 rating
Confidence interval: 1,425.94 – 1,452.02
2136 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
GPT-6 Astra
1,429.36 rating
Confidence interval: 1,418.02 – 1,440.70
3101 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
GPT-6 Astra
1,461.45 rating
Confidence interval: 1,443.02 – 1,479.88
1043 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
GPT-6 Astra
1,450.45 rating
Confidence interval: 1,437.12 – 1,463.77
2069 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,478.11 rating
Confidence interval: 1,455.76 – 1,500.47
696 votes
- Category
- industry_mathematical
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
GPT-6 Astra
1,425.76 rating
Confidence interval: 1,405.44 – 1,446.07
880 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
GPT-6 Astra
1,474.41 rating
Confidence interval: 1,465.11 – 1,483.72
4364 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
GPT-6 Astra
1,439.08 rating
Confidence interval: 1,428.29 – 1,449.88
3414 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
GPT-6 Astra
1,454.65 rating
Confidence interval: 1,444.74 – 1,464.57
3832 votes
- Category
- instruction_following
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
GPT-6 Astra
1,392.32 rating
Confidence interval: 1,349.81 – 1,434.83
224 votes
- Category
- japanese
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,429.59 rating
Confidence interval: 1,388.79 – 1,470.38
215 votes
- Category
- korean
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,461.46 rating
Confidence interval: 1,452.50 – 1,470.42
5102 votes
- Category
- longer_query
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,464.61 rating
Confidence interval: 1,441.40 – 1,487.82
618 votes
- Category
- math
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,449.54 rating
Confidence interval: 1,434.72 – 1,464.36
1669 votes
- Category
- multi_turn
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,432.47 rating
Confidence interval: 1,424.89 – 1,440.05
7240 votes
- Category
- non_english
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,442.69 rating
Confidence interval: 1,436.40 – 1,448.99
12163 votes
- Category
- overall
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,419.53 rating
Confidence interval: 1,375.42 – 1,463.64
168 votes
- Category
- polish
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,437.03 rating
Confidence interval: 1,422.02 – 1,452.03
1590 votes
- Category
- russian
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
GPT-6 Astra
1,422.62 rating
Confidence interval: 1,392.07 – 1,453.16
365 votes
- Category
- spanish
- Evaluated configuration
- gpt-6-astra-max
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
GPT-6 Astra
GPT-6 Astra / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| OpenAIgpt-6-astraBatch long_context | Cached input | USD | 1 / 1M tokens |
| Input | USD | 10 / 1M tokens | |
| Output | USD | 37.5 / 1M tokens | |
| OpenAIgpt-6-astraBatch | Cached input | USD | 0.5 / 1M tokens |
| Input | USD | 5 / 1M tokens | |
| Output | USD | 25 / 1M tokens | |
| OpenAIgpt-6-astraFlex long_context | Cached input | USD | 1 / 1M tokens |
| Input | USD | 10 / 1M tokens | |
| Output | USD | 37.5 / 1M tokens | |
| OpenAIgpt-6-astraFlex | Cached input | USD | 0.5 / 1M tokens |
| Input | USD | 5 / 1M tokens | |
| Output | USD | 25 / 1M tokens | |
| OpenAIgpt-6-astraPriority | Cached input | USD | 2 / 1M tokens |
| Input | USD | 20 / 1M tokens | |
| Output | USD | 100 / 1M tokens | |
| OpenAIgpt-6-astraPriority long_context | Cached input | USD | 4 / 1M tokens |
| Input | USD | 40 / 1M tokens | |
| Output | USD | 150 / 1M tokens | |
| OpenAIgpt-6-astraStandard long_context | Cached input | USD | 2 / 1M tokens |
| Input | USD | 20 / 1M tokens | |
| Output | USD | 75 / 1M tokens | |
| OpenAIgpt-6-astraStandard | Cached input | USD | 1 / 1M tokens |
| Input | USD | 10 / 1M tokens | |
| Output | USD | 50 / 1M tokens |
Capabilities
- Context window
- 1,050,000 tokens
- Maximum input
- 922,000 tokens*
- Maximum output
- 128,000 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes*
- Open weights
- No
- Knowledge cutoff
- 2026-04-30
- API mode
- Chat*
- Declared context window
- 1.05M*
- Model type
- Reasoning / agentic*
- Declared modalities
- Text, vision*
- Image input
- Yes*
- PDF input
- Yes*
- Parallel tool calls
- Yes*
- Prompt caching
- Yes*
- System messages
- Yes*
- Tool choice
- Yes*
- Web search
- Yes*
- Model license
- Proprietary
Input modalities
- text
- image
Output modalities
- text
System configuration
Detailed specifications
Specifications 1 · 13 fields
- api providers
- OpenAI API, Microsoft Azure, AWS Bedrock*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- context window
- 1.05M*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- developer
- OpenAI*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- input price
- 10*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- intelligence
- 61*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- license
- Proprietary*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- max output
- 128K*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- modality
- Text, vision*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- model type
- Reasoning / agentic*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- name
- GPT-6 Astra*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- open weights
- no*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- output price
- 50*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- release date
- 2026-09*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- OpenAI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
Specifications 2 · 69 fields
- cache creation input token cost
- 1.25e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache creation input token cost above 272k tokens
- 2.5e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache creation input token cost above 272k tokens batches
- 1.25e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache creation input token cost above 272k tokens flex
- 1.25e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache creation input token cost above 272k tokens priority
- 5.0e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache creation input token cost above 272k tokens ultrafast
- 0.00015*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache creation input token cost batches
- 6.25e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache creation input token cost flex
- 6.25e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache creation input token cost priority
- 2.5e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache creation input token cost ultrafast
- 7.5e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost
- 1.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost above 272k tokens
- 2.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost above 272k tokens batches
- 1.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost above 272k tokens flex
- 1.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost above 272k tokens priority
- 4.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost above 272k tokens ultrafast
- 1.2e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost batches
- 5.0e-7*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost flex
- 5.0e-7*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost priority
- 2.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost ultrafast
- 6.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token
- 1.0e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token above 272k tokens
- 2.0e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token above 272k tokens batches
- 1.0e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token above 272k tokens flex
- 1.0e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token above 272k tokens priority
- 4.0e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token above 272k tokens ultrafast
- 0.00012*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token batches
- 5.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token flex
- 5.0e-6*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token priority
- 2.0e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token ultrafast
- 6.0e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- litellm provider
- openai*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- max input tokens
- 922,000*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- max output tokens
- 128,000*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- max tokens
- 128,000*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- mode
- chat*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token
- 5.0e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token above 272k tokens
- 7.5e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token above 272k tokens batches
- 3.75e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token above 272k tokens flex
- 3.75e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token above 272k tokens priority
- 0.00015*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token above 272k tokens ultrafast
- 0.00045*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token batches
- 2.5e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token flex
- 2.5e-5*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token priority
- 0.0001*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token ultrafast
- 0.0003*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- regional processing uplift multiplier eu
- 1.1*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- regional processing uplift multiplier us
- 1.1*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- search context cost per query
- search_context_size_high
- 0.01*
- search_context_size_low
- 0.01*
- search_context_size_medium
- 0.01*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supported endpoints
- /v1/chat/completions*
- /v1/batch*
- /v1/responses*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supported modalities
- text*
- image*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supported output modalities
- text*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports computer use
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports function calling
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports max reasoning effort
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports minimal reasoning effort
- No*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports native streaming
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports none reasoning effort
- No*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports parallel function calling
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports pdf input
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports prompt cache breakpoint
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports prompt caching
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports reasoning
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports response schema
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports system messages
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports tool choice
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports tool search
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports vision
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports web search
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports xhigh reasoning effort
- Yes*
Scope and conditions
- native_context
- provider
- openai*
- mode
- chat*
- full_native_model_id
- gpt-6-astra*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
0 selected Compare 0
* Provisional data