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: 37
Context: 1,050,000
Output limit: 128,000
Knowledge: 2026-04-30
Release: 2026-09-04
Updated: —
Weights: Closed
Input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf
Output: text
Capabilities: —

Providers

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

49 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
AIHubMix	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
AI/ML API	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Aixy	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Amazon Bedrock	global.openai.gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Amazon Bedrock	us.openai.gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Amazon Bedrock	openai.gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Azure	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Cloudflare AI Gateway	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
CommandCode	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Cortecs	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
CrossModel	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
DevPass (LLM Gateway)	gpt-6-astra	1,050,000	1,050,000	— / —	—	—	—	View
DigitalOcean	openai-gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Eden AI	openai/gpt-latest	1,050,000	128,000	— / —	—	—	—	View
Eden AI	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
GitHub Copilot	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
GitLab Duo	duo-chat-gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Infer by Flow7	infer/gpt-6-astra:official	271,999	128,000	— / —	—	—	—	View
Kilo Gateway	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
LLM Gateway	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
LLM Gateway	aws-mantle/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
LLM Gateway	azure/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
LowRouter	auto/openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Merge Gateway	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
NanoGPT	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
NEAR AI Cloud	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Neon	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Ofox	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
OpenAI	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
OpenCode	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Amazon Bedrockvia OpenRouter	openai/gpt-6-astra unknown	1,050,000	128,000	$11.00 / $55.00	Yes	Yes	Yes	View
Azurevia OpenRouter	openai/gpt-6-astra unknown	1,050,000	128,000	$10.00 / $50.00	Yes	Yes	Yes	View
Azurevia OpenRouter	openai/gpt-6-astra unknown	1,050,000	128,000	$11.00 / $55.00	Yes	Yes	Yes	View
OpenAIvia OpenRouter	openai/gpt-6-astra unknown	1,050,000	128,000	$10.00 / $50.00	Yes	Yes	Yes	View
OpenAIvia OpenRouter	openai/gpt-6-astra unknown	1,050,000	128,000	$60.00 / $300.00	Yes	Yes	Yes	View
OpenAIvia OpenRouter	openai/gpt-6-astra unknown	1,050,000	128,000	$20.00 / $100.00	Yes	Yes	Yes	View
OpenAIvia OpenRouter	openai/gpt-6-astra unknown	1,050,000	128,000	$5.00 / $25.00	Yes	Yes	Yes	View
Opper	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Perplexity Agent	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Prime Inference	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Requesty	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
SAP AI Core	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Standard Compute	openai/gpt-6-astra	1,050,000	50,000	— / —	—	—	—	View
Venice AI	openai-gpt-6-astra-pro	1,050,000	128,000	— / —	—	—	—	View
Venice AI	openai-gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Vercel AI Gateway	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
Vivgrid	gpt-6-astra	1,050,000	128,000	— / —	—	—	—	View
ZenMux	openai/gpt-6-astra	1,050,000	128,000	— / —	—	—	—	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$5.00Per 1M input tokens

Output from$25.00Per 1M output tokens

Available offers49Across 37 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 Oct 10, 2026, 11:31 AM UTC

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

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache 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

5,125.5–11,860.9 ms

Azureazure

5,465–108,893.6 ms

Azureazure/us

6,680.5–41,815.66 ms

OpenAIopenai

4,316.5–104,661.27 ms

OpenAIopenai/fast

6,500–54,466.72 ms

OpenAIopenai/flex

2,744–51,132 ms

All latency percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Amazon Bedrockamazon-bedrock/us-west-2	5,125.5 ms	5,983.5 ms	6,635.5 ms	11,860.9 ms
Azureazure	5,465 ms	9,796 ms	18,810 ms	108,893.6 ms
Azureazure/us	6,680.5 ms	11,676.75 ms	20,327.3 ms	41,815.66 ms
OpenAIopenai	4,316.5 ms	10,321 ms	22,964.8 ms	104,661.27 ms
OpenAIopenai/fast	6,500 ms	13,127 ms	24,748.8 ms	54,466.72 ms
OpenAIopenai/flex	2,744 ms	5,635 ms	13,172 ms	51,132 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Amazon Bedrockamazon-bedrock/us-west-2

39.5–90 t/s

Azureazure

25–64 t/s

Azureazure/us

35–62.52 t/s

OpenAIopenai

44–85 t/s

OpenAIopenai/fast

33–94.46 t/s

OpenAIopenai/flex

55–97.95 t/s

All throughput percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Amazon Bedrockamazon-bedrock/us-west-2	39.5 t/s	62 t/s	76 t/s	90 t/s
Azureazure	25 t/s	35 t/s	46 t/s	64 t/s
Azureazure/us	35 t/s	42 t/s	53.4 t/s	62.52 t/s
OpenAIopenai	44 t/s	54 t/s	66 t/s	85 t/s
OpenAIopenai/fast	33 t/s	47.5 t/s	67 t/s	94.46 t/s
OpenAIopenai/flex	55 t/s	68 t/s	79.5 t/s	97.95 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-2Observed Oct 10, 2026, 11:31 AM UTC

—

AzureazureObserved Oct 10, 2026, 11:31 AM UTC

100%

96.67%

99.79%

Azureazure/usObserved Oct 10, 2026, 11:31 AM UTC

—

100%

OpenAIopenaiObserved Oct 10, 2026, 11:31 AM UTC

100%

OpenAIopenai/ultrafastObserved Oct 10, 2026, 11:31 AM UTC

—

100%

OpenAIopenai/fastObserved Oct 10, 2026, 11:31 AM UTC

—

100%

OpenAIopenai/flexObserved Oct 10, 2026, 11:31 AM UTC

100%

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 Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 80

Coding

76.9

Agentic

Intelligence

52.7

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%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	OpenAI: GPT-6 Astraopenai/gpt-6-astra-20260903	OpenRouter	94.444%	Details
tau bench verified airline	OpenAI: GPT-6 Astraopenai/gpt-6-astra-20260903	OpenRouter	68%	Details
Composite indices	GPT-6 Astra (Max)openai/gpt-6-astra-20260903	Artificial Analysis	Intelligence 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 24, 2026.

Apps & session costs

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

30-day sample · through Oct 18, 2026

Application	Model route	Turns	Median cost / session	Details
Codex	openai/gpt-6-astra-20260903	2–9 turns	$0.583983	Details
Claude Code	openai/gpt-6-astra-20260903	10–49 turns	$2.596314	Details
Hermes Agent	openai/gpt-6-astra-20260903	2–9 turns	$0.442734	Details
Claude Code	openai/gpt-6-astra-20260903	1 turn	$0.166736	Details
Codex	openai/gpt-6-astra-20260903	1 turn	$0.138768	Details
Hermes Agent	openai/gpt-6-astra-20260903	10–49 turns	$2.784148	Details
Codex	openai/gpt-6-astra-20260903	10–49 turns	$2.790099	Details
Codex	openai/gpt-6-astra-20260903	50+ turns	$16.780794	Details
Claude Code	openai/gpt-6-astra-20260903	2–9 turns	$0.479032	Details
Hermes Agent	openai/gpt-6-astra-20260903	50+ turns	$17.762053	Details
Hermes Agent	openai/gpt-6-astra-20260903	1 turn	$0.010071	Details

Source: OpenRouter, as of Oct 20, 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 usage6,224,302,237,598 reported tokens · 45 days with observations

830B0

2026-09-05
70,859,008,840 tokens

2026-09-06
63,153,928,501 tokens

2026-09-07
87,279,302,620 tokens

2026-09-08
124,263,411,024 tokens

2026-09-09
121,801,308,844 tokens

2026-09-10
131,369,910,231 tokens

2026-09-11
113,330,598,063 tokens

2026-09-12
82,829,044,083 tokens

2026-09-13
62,568,636,733 tokens

2026-09-14
101,283,239,623 tokens

2026-09-15
107,608,562,554 tokens

2026-09-16
220,000,343,457 tokens

2026-09-17
829,913,991,437 tokens

2026-09-18
242,873,840,090 tokens

2026-09-19
140,045,736,102 tokens

2026-09-20
109,287,445,254 tokens

2026-09-21
161,600,991,288 tokens

2026-09-22
145,161,485,408 tokens

2026-09-23
172,713,762,950 tokens

2026-09-24
140,329,908,175 tokens

2026-09-25
143,094,194,120 tokens

2026-09-26
181,874,010,759 tokens

2026-09-27
88,331,382,797 tokens

2026-09-28
112,820,888,941 tokens

2026-09-29
83,155,418,525 tokens

2026-09-30
157,018,240,974 tokens

2026-10-01
459,821,328,032 tokens

2026-10-02
428,855,567,490 tokens

2026-10-03
83,802,429,787 tokens

2026-10-04
83,292,627,530 tokens

2026-10-05
92,245,988,970 tokens

2026-10-06
73,924,134,158 tokens

2026-10-07
86,750,162,615 tokens

2026-10-08
84,386,833,649 tokens

2026-10-09
98,569,196,260 tokens

2026-10-10
82,018,558,538 tokens

2026-10-11
64,669,665,022 tokens

2026-10-12
74,150,982,234 tokens

2026-10-13
61,247,699,987 tokens

2026-10-16
61,764,770,432 tokens

2026-10-19
61,608,514,696 tokens

2026-10-20
78,695,332,987 tokens

2026-10-21
90,684,278,823 tokens

2026-10-22
80,290,813,449 tokens

2026-10-23
82,954,761,546 tokens

Jul 26, 2026Oct 23, 2026

Daily observations · 45 days

Date (UTC)	Reported tokens	Reported routes
Oct 23, 2026	82,954,761,546	1
Oct 22, 2026	80,290,813,449	1
Oct 21, 2026	90,684,278,823	1
Oct 20, 2026	78,695,332,987	1
Oct 19, 2026	61,608,514,696	1
Oct 16, 2026	61,764,770,432	1
Oct 13, 2026	61,247,699,987	1
Oct 12, 2026	74,150,982,234	1
Oct 11, 2026	64,669,665,022	1
Oct 10, 2026	82,018,558,538	1
Oct 9, 2026	98,569,196,260	1
Oct 8, 2026	84,386,833,649	1
Oct 7, 2026	86,750,162,615	1
Oct 6, 2026	73,924,134,158	1
Oct 5, 2026	92,245,988,970	1
Oct 4, 2026	83,292,627,530	1
Oct 3, 2026	83,802,429,787	1
Oct 2, 2026	428,855,567,490	1
Oct 1, 2026	459,821,328,032	1
Sep 30, 2026	157,018,240,974	1
Sep 29, 2026	83,155,418,525	1
Sep 28, 2026	112,820,888,941	1
Sep 27, 2026	88,331,382,797	1
Sep 26, 2026	181,874,010,759	1
Sep 25, 2026	143,094,194,120	1
Sep 24, 2026	140,329,908,175	1
Sep 23, 2026	172,713,762,950	1
Sep 22, 2026	145,161,485,408	1
Sep 21, 2026	161,600,991,288	1
Sep 20, 2026	109,287,445,254	1
Sep 19, 2026	140,045,736,102	1
Sep 18, 2026	242,873,840,090	1
Sep 17, 2026	829,913,991,437	1
Sep 16, 2026	220,000,343,457	1
Sep 15, 2026	107,608,562,554	1
Sep 14, 2026	101,283,239,623	1
Sep 13, 2026	62,568,636,733	1
Sep 12, 2026	82,829,044,083	1
Sep 11, 2026	113,330,598,063	1
Sep 10, 2026	131,369,910,231	1
Sep 9, 2026	121,801,308,844	1
Sep 8, 2026	124,263,411,024	1
Sep 7, 2026	87,279,302,620	1
Sep 6, 2026	63,153,928,501	1
Sep 5, 2026	70,859,008,840	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 24, 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 Oct 10, 2026, 11:31 AM UTC

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 $5.00 per million input tokens and $25.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GPT-6 Astra?

There are 49 cataloged offers across 37 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: Not reported. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 3 recorded revisions

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

Oct 20, 2026 · 01ca8e3c5390
Sep 14, 2026 · d6742d07d1c5
Sep 12, 2026 · 8ef9b7ddf957