Home/Models
Models/OpenAI

GPT-6 Astra

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.

openai/gpt-6-astra
Organization
OpenAI
Family
gpt-astra
Providers
27
Context
1,050,000
Output limit
128,000
Knowledge
2026-04-30
Release
2026-09-04
Updated
2026-09-04
Weights
Closed
Input
text, image, pdf
Output
text
Capabilities
Tools, Reasoning, Structured

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

37 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
302.AI
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
AIHubMix
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Amazon Bedrock
global.openai.gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Amazon Bedrock
us.openai.gpt-6-astra
1,050,000128,000$11.00 / $55.00YesYesYes
View
Amazon Bedrock
openai.gpt-6-astra
1,050,000128,000$11.00 / $55.00YesYesYes
View
Azure
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Azure Cognitive Services
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Cloudflare AI Gateway
openai/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
CrossModel
openai/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
DigitalOcean
openai-gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Eden AI
openai/gpt-latest
1,050,000128,000$10.00 / $50.00YesYesYes
View
Eden AI
openai/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
GitHub Copilot
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
GitLab Duo
duo-chat-gpt-6-astra
1,050,000128,000$0.00 / $0.00YesYesYes
View
Infer by Flow7
infer/gpt-6-astra:official
271,999128,000$12.50 / $62.50YesYesYes
View
Kilo Gateway
openai/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
LLM Gateway
aws-mantle/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
LLM Gateway
azure/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Merge Gateway
openai/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
NanoGPT
openai/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Neon
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Ofox
openai/gpt-6-astra
1,050,000128,000$8.00 / $40.00YesYesYes
View
OpenAI
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
OpenCode Zen
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Amazon Bedrockvia OpenRouter
openai/gpt-6-astra
unknown		1,050,000128,000$11.00 / $55.00YesYesYes
View
Azurevia OpenRouter
openai/gpt-6-astra
unknown		1,050,000128,000$10.00 / $50.00YesYesYes
View
Azurevia OpenRouter
openai/gpt-6-astra
unknown		1,050,000128,000$11.00 / $55.00YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-astra
unknown		1,050,000128,000$10.00 / $50.00YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-astra
unknown		1,050,000128,000$60.00 / $300.00YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-astra
unknown		1,050,000128,000$20.00 / $100.00YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-astra
unknown		1,050,000128,000$5.00 / $25.00YesYesYes
View
Opper
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Requesty
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Venice AI
openai-gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Vercel AI Gateway
openai/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
Vivgrid
gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View
ZenMux
openai/gpt-6-astra
1,050,000128,000$10.00 / $50.00YesYesYes
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.00Per 1M input tokens
Output from$0.00Per 1M output tokens
Available offers37Across 27 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 7 lowest-priced configurations
InputOutput
OpenAIopenai/flex
$5.00$25.00
Azureazure
$10.00$50.00
OpenAIopenai
$10.00$50.00
Amazon Bedrockamazon-bedrock/us-west-2
$11.00$55.00
Azureazure/us
$11.00$55.00
OpenAIopenai/fast
$20.00$100.00
OpenAIopenai/ultrafast
$60.00$300.00
openai/gpt-6-astraObserved
Input
$10.00
Output
$50.00
Cache read
$1.00
Cache write
$12.50
Additional fees and pricing conditions
web search
$0.01 / search

overrides · USD per token for token prices; time windows use UTC.

[
  {
    "prompt": "0.00002",
    "completion": "0.000075",
    "input_cache_read": "0.000002",
    "input_cache_write": "0.000025",
    "min_prompt_tokens": 272000
  }
]
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Amazon Bedrockamazon-bedrock/us-west-2$11.00$55.00$1.10$13.75
Azureazure$10.00$50.00$1.00$12.50
Azureazure/us$11.00$55.00$1.10$13.75
OpenAIopenai$10.00$50.00$1.00$12.50
OpenAIopenai/ultrafast$60.00$300.00$6.00$75.00
OpenAIopenai/fast$20.00$100.00$2.00$25.00
OpenAIopenai/flex$5.00$25.00$0.50$6.25

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock/us-west-2
4,371.5–14,238.18 ms
Azureazure
1,886–30,052.93 ms
Azureazure/us
18,054–89,108.48 ms
OpenAIopenai
2,797–61,792.63 ms
OpenAIopenai/fast
4,444–22,369.46 ms
OpenAIopenai/flex
2,753–83,734.2 ms
All latency percentiles 6 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/us-west-24,371.5 ms8,522.25 ms12,214.8 ms14,238.18 ms
Azureazure1,886 ms3,393.75 ms7,267.5 ms30,052.93 ms
Azureazure/us18,054 ms48,402 ms67,180.4 ms89,108.48 ms
OpenAIopenai2,797 ms6,336 ms14,928.7 ms61,792.63 ms
OpenAIopenai/fast4,444 ms7,252 ms11,324.2 ms22,369.46 ms
OpenAIopenai/flex2,753 ms6,665 ms11,817 ms83,734.2 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock/us-west-2
52–80.1 t/s
Azureazure
32–73 t/s
Azureazure/us
25–54 t/s
OpenAIopenai
42–84 t/s
OpenAIopenai/fast
48–106.74 t/s
OpenAIopenai/flex
62–120 t/s
All throughput percentiles 6 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/us-west-252 t/s65 t/s72 t/s80.1 t/s
Azureazure32 t/s41 t/s49 t/s73 t/s
Azureazure/us25 t/s33.5 t/s41 t/s54 t/s
OpenAIopenai42 t/s51 t/s61 t/s84 t/s
OpenAIopenai/fast48 t/s67 t/s83 t/s106.74 t/s
OpenAIopenai/flex62 t/s76 t/s93 t/s120 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 7 endpoints
Endpoint5 minutes30 minutes24 hours
Amazon Bedrockamazon-bedrock/us-west-2
Azureazure
Azureazure/us
OpenAIopenai
OpenAIopenai/ultrafast
OpenAIopenai/fast
OpenAIopenai/flex

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations
openai/gpt-6-astraObserved
Benchmark profileArtificial Analysis · shared source scale from 0 to 80
Coding76.9
Agentic51
Intelligence52.7

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondOpenAI: GPT-6 Astra
94.444%
tau bench verified airlineOpenAI: GPT-6 Astra
68%
EvaluationConfigurationSourceResultsDetails
gpqa diamondOpenAI: GPT-6 Astraopenai/gpt-6-astra-20260903OpenRouter94.444%
Details
tau bench verified airlineOpenAI: GPT-6 Astraopenai/gpt-6-astra-20260903OpenRouter68%
Details
Composite indicesGPT-6 Astra (max)openai/gpt-6-astra-20260903Artificial AnalysisIntelligence 52.7 · Coding 76.9 · Agentic 51
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Codexopenai/gpt-6-astra-2026090310–49 turns
$2.933723
Details
Kilo Codeopenai/gpt-6-astra-2026090310–49 turns
$2.708043
Details
Claude Codeopenai/gpt-6-astra-2026090350+ turns
$15.19952
Details
Kilo Codeopenai/gpt-6-astra-202609032–9 turns
$0.822546
Details
Hermes Agentopenai/gpt-6-astra-202609031 turn
$0.038019
Details
Codexopenai/gpt-6-astra-202609031 turn
$0.118082
Details
Hermes Agentopenai/gpt-6-astra-2026090310–49 turns
$3.052718
Details
Claude Codeopenai/gpt-6-astra-2026090310–49 turns
$2.78885
Details
Hermes Agentopenai/gpt-6-astra-2026090350+ turns
$19.333462
Details
Codexopenai/gpt-6-astra-202609032–9 turns
$0.572655
Details
Claude Codeopenai/gpt-6-astra-202609031 turn
$0.265323
Details
Claude Codeopenai/gpt-6-astra-202609032–9 turns
$0.518383
Details
Codexopenai/gpt-6-astra-2026090350+ turns
$19.557594
Details
Hermes Agentopenai/gpt-6-astra-202609032–9 turns
$0.529349
Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage4,967,047,916,702 reported tokens · 29 days with observations
Jul 6, 2026Oct 3, 2026
Daily observations · 29 days
Date (UTC)Reported tokensReported routes
Oct 3, 202683,802,429,7871
Oct 2, 2026428,855,567,4901
Oct 1, 2026459,821,328,0321
Sep 30, 2026157,018,240,9741
Sep 29, 202683,155,418,5251
Sep 28, 2026112,820,888,9411
Sep 27, 202688,331,382,7971
Sep 26, 2026181,874,010,7591
Sep 25, 2026143,094,194,1201
Sep 24, 2026140,329,908,1751
Sep 23, 2026172,713,762,9501
Sep 22, 2026145,161,485,4081
Sep 21, 2026161,600,991,2881
Sep 20, 2026109,287,445,2541
Sep 19, 2026140,045,736,1021
Sep 18, 2026242,873,840,0901
Sep 17, 2026829,913,991,4371
Sep 16, 2026220,000,343,4571
Sep 15, 2026107,608,562,5541
Sep 14, 2026101,283,239,6231
Sep 13, 202662,568,636,7331
Sep 12, 202682,829,044,0831
Sep 11, 2026113,330,598,0631
Sep 10, 2026131,369,910,2311
Sep 9, 2026121,801,308,8441
Sep 8, 2026124,263,411,0241
Sep 7, 202687,279,302,6201
Sep 6, 202663,153,928,5011
Sep 5, 202670,859,008,8401

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
openai/gpt-6-astraObserved
Context
1,050,000
Maximum output
128,000
Tokenizer
GPT
Input
file, image, text
Output
text
Moderation
Yes
Added to OpenRouter
2026-09-04
Base URLhttps://openrouter.ai/api/v1
Model IDopenai/gpt-6-astra
Version IDopenai/gpt-6-astra-20260903

Reasoning

Required
Yes
Enabled by default
Yes
Default effort
medium
Supported efforts
max, xhigh, high, medium, low

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • seed
  • structured_outputs
  • tool_choice
  • tools
  • verbosity

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does GPT-6 Astra cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GPT-6 Astra?

There are 37 cataloged offers across 27 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,050,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · d6742d07d1c5
  • · 8ef9b7ddf957