Where is the GPT-6 Astra documentation?

The GPT-6 Astra documentation on OpenRouter includes the GPT-6 Migration Guide cookbook. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does GPT-6 Astra cost?

GPT-6 Astra costs $10.00/M input tokens and $50.00/M output tokens, with separate rates for Cache Read at $1.00/M tokens and Cache Write at $12.50/M tokens.

What is the context length of GPT-6 Astra?

GPT-6 Astra has a 1,050,000 token context window. It supports up to 128,000 completion tokens.

Does GPT-6 Astra support tool calling and structured outputs?

Yes. GPT-6 Astra accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Can I disable prompt caching for GPT-6 Astra?

Yes. OpenAI caches prompts of 1024 tokens or more automatically, and GPT-6 Astra bills a cache write on each cached prompt whether or not the cached prefix is read again. To turn caching off for a request, set prompt_cache_options.mode to "explicit" at the request root and do not mark any content block with prompt_cache_breakpoint. Explicit mode disables OpenAI-managed breakpoints, so a request with none of your own has no cacheable prefix and is billed at the plain input rate. See the prompt caching guide.

What inputs and outputs does GPT-6 Astra support?

GPT-6 Astra accepts files such as PDFs, images, and text as input and returns text.

Which providers serve GPT-6 Astra?

GPT-6 Astra is served by 3 providers on OpenRouter: OpenAI, Amazon Bedrock, and Azure. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was GPT-6 Astra released?

GPT-6 Astra was released on September 4, 2026.

OpenAI: GPT-6 Astra

openai/gpt-6-astra

Compare

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.

Modalities

In / out price

$10 / $50per 1M

Context

1.1M

Released

Sep 4, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$10.00	$50.00	$1.00	1.46s	62 tok/s	99.14%
	$10.00	$50.00	$1.00	4.80s	37 tok/s	99.79%
	$10.00	$50.00	$1.00	4.82s	35 tok/s	99.43%
Not used in Standard routing:Why these endpoints are not used
Flex	$5.00	$25.00	$0.50	5.28s	33 tok/s	100.00%
	$11.00	$55.00	$1.10	1.64s	28 tok/s	100.00%
	$11.00	$55.00	$1.10	2.25s	35 tok/s	99.56%
Fast	$20.00	$100.00	$2.00	1.62s	67 tok/s	100.00%
Ultrafast	$60.00	$300.00	$6.00	--	--	--

Input $10.00Output $50.00
62 tok/s99.14% uptime
Input $10.00Output $50.00
37 tok/s99.79% uptime
Input $10.00Output $50.00
35 tok/s99.43% uptime
Not used in Standard routing:Why these endpoints are not used
Input $5.00Output $25.00
Flex
33 tok/s100.00% uptime
Input $11.00Output $55.00
28 tok/s100.00% uptime
Input $11.00Output $55.00
35 tok/s99.56% uptime
Input $20.00Output $100.00
Fast
67 tok/s100.00% uptime
Input $60.00Output $300.00
Ultrafast
-- tok/s-- uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$2.202/M tokens

Output

$49.53/M tokens

GPT-6 Astra — Price history

Price history

No effective price data for this selection

		$2.03	$50.57	92.0%	45.7%
		$2.36	$50.47	89.5%	46.1%
		$2.63	$50.21	86.2%	2.0%
Not used in Standard routing:Why these endpoints are not used
	Flex	$1.23	$25.00	87.0%	4.0%
	Fast	$3.87	$100.00	91.3%	2.1%
		$5.59	$55.00	64.3%	0.0%
		$13.58	$55.00	0.0%	0.0%
	Ultrafast	$59.68	$300.00	22.2%	0.0%

Effective in $2.03Effective out $50.57
Token share
45.7%
Effective in $2.36Effective out $50.47
Token share
46.1%
Effective in $2.63Effective out $50.21
Token share
2.0%
Not used in Standard routing:Why these endpoints are not used
Effective in $1.23Effective out $25.00
FlexToken share
4.0%
Effective in $3.87Effective out $100.00
FastToken share
2.1%
Effective in $5.59Effective out $55.00
Token share
0.0%
Effective in $13.58Effective out $55.00
Token share
0.0%
Effective in $59.68Effective out $300.00
UltrafastToken share
0.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

99.99%

Availability (3d)

99.22%

Availability over the last 3 days

Last 72 hours

Availability 99.22%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.43%

Without Routing

93.91%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for OpenAI: GPT-6 Astra (Artificial Analysis and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GPT-6 Astra (Max) Intelligence Index	56.9
Artificial Analysis	GPT-6 Astra (Max) Coding Index	76.9
Artificial Analysis	GPT-6 Astra (Max) Agentic Index	51.0
Artificial Analysis	GPT-6 Astra (Max) GPQA Diamond	96.1%
Artificial Analysis	GPT-6 Astra (Max) HLE	54.7%
Artificial Analysis	GPT-6 Astra (Max) AA-LCR	80.7%
Artificial Analysis	GPT-6 Astra (Max) τ-Bench Banking	41.4%
Artificial Analysis	GPT-6 Astra (Max) GDPval-AA	54.3%
Artificial Analysis	GPT-6 Astra (Max) CritPt	31.7%
Artificial Analysis	GPT-6 Astra (Max) SciCode	56.5%
Artificial Analysis	GPT-6 Astra (Max) Terminal-Bench 4.0	59.1%
Artificial Analysis	GPT-6 Astra (Max) Terminal-Bench 2.1	88.4%
Artificial Analysis	GPT-6 Astra (Max) AA-Omniscience Accuracy	61.6%
Artificial Analysis	GPT-6 Astra (Max) AA-Omniscience Non-Hallucination Rate	50.2%
Artificial Analysis	GPT-6 Astra (Medium) Intelligence Index	51.6
Artificial Analysis	GPT-6 Astra (Medium) Coding Index	76.7
Artificial Analysis	GPT-6 Astra (Medium) Agentic Index	46.0
Artificial Analysis	GPT-6 Astra (Medium) GPQA Diamond	93.9%
Artificial Analysis	GPT-6 Astra (Medium) HLE	52.7%
Artificial Analysis	GPT-6 Astra (Medium) AA-LCR	79.7%
Artificial Analysis	GPT-6 Astra (Medium) τ-Bench Banking	35.5%
Artificial Analysis	GPT-6 Astra (Medium) GDPval-AA	49.9%
Artificial Analysis	GPT-6 Astra (Medium) CritPt	29.1%
Artificial Analysis	GPT-6 Astra (Medium) SciCode	54.2%
Artificial Analysis	GPT-6 Astra (Medium) Terminal-Bench 4.0	49.5%
Artificial Analysis	GPT-6 Astra (Medium) Terminal-Bench 2.1	89.5%
Artificial Analysis	GPT-6 Astra (Medium) AA-Omniscience Accuracy	59.6%
Artificial Analysis	GPT-6 Astra (Medium) AA-Omniscience Non-Hallucination Rate	54.8%
Artificial Analysis	GPT-6 Astra (Low) Intelligence Index	43.3
Artificial Analysis	GPT-6 Astra (Low) Coding Index	75.7
Artificial Analysis	GPT-6 Astra (Low) Agentic Index	38.8
Artificial Analysis	GPT-6 Astra (Low) GPQA Diamond	93.1%
Artificial Analysis	GPT-6 Astra (Low) HLE	49.2%
Artificial Analysis	GPT-6 Astra (Low) AA-LCR	80.0%
Artificial Analysis	GPT-6 Astra (Low) τ-Bench Banking	32.0%
Artificial Analysis	GPT-6 Astra (Low) GDPval-AA	45.2%
Artificial Analysis	GPT-6 Astra (Low) CritPt	26.3%
Artificial Analysis	GPT-6 Astra (Low) SciCode	54.1%
Artificial Analysis	GPT-6 Astra (Low) Terminal-Bench 4.0	41.9%
Artificial Analysis	GPT-6 Astra (Low) Terminal-Bench 2.1	88.0%
Artificial Analysis	GPT-6 Astra (Low) AA-Omniscience Accuracy	58.6%
Artificial Analysis	GPT-6 Astra (Low) AA-Omniscience Non-Hallucination Rate	55.8%
Artificial Analysis	GPT-6 Astra (Xhigh) Intelligence Index	55.3
Artificial Analysis	GPT-6 Astra (Xhigh) Coding Index	75.9
Artificial Analysis	GPT-6 Astra (Xhigh) Agentic Index	50.2
Artificial Analysis	GPT-6 Astra (Xhigh) GPQA Diamond	96.3%
Artificial Analysis	GPT-6 Astra (Xhigh) HLE	54.6%
Artificial Analysis	GPT-6 Astra (Xhigh) AA-LCR	80.0%
Artificial Analysis	GPT-6 Astra (Xhigh) τ-Bench Banking	43.1%
Artificial Analysis	GPT-6 Astra (Xhigh) GDPval-AA	53.5%
Artificial Analysis	GPT-6 Astra (Xhigh) CritPt	31.4%
Artificial Analysis	GPT-6 Astra (Xhigh) SciCode	55.7%
Artificial Analysis	GPT-6 Astra (Xhigh) Terminal-Bench 4.0	59.6%
Artificial Analysis	GPT-6 Astra (Xhigh) Terminal-Bench 2.1	89.1%
Artificial Analysis	GPT-6 Astra (Xhigh) AA-Omniscience Accuracy	61.0%
Artificial Analysis	GPT-6 Astra (Xhigh) AA-Omniscience Non-Hallucination Rate	55.4%
Artificial Analysis	GPT-6 Astra (High) Intelligence Index	54.8
Artificial Analysis	GPT-6 Astra (High) Coding Index	77.1
Artificial Analysis	GPT-6 Astra (High) Agentic Index	48.2
Artificial Analysis	GPT-6 Astra (High) GPQA Diamond	94.9%
Artificial Analysis	GPT-6 Astra (High) HLE	53.1%
Artificial Analysis	GPT-6 Astra (High) AA-LCR	80.0%
Artificial Analysis	GPT-6 Astra (High) τ-Bench Banking	40.0%
Artificial Analysis	GPT-6 Astra (High) GDPval-AA	51.8%
Artificial Analysis	GPT-6 Astra (High) CritPt	28.9%
Artificial Analysis	GPT-6 Astra (High) SciCode	55.4%
Artificial Analysis	GPT-6 Astra (High) Terminal-Bench 4.0	54.0%
Artificial Analysis	GPT-6 Astra (High) Terminal-Bench 2.1	89.9%
Artificial Analysis	GPT-6 Astra (High) AA-Omniscience Accuracy	61.1%
Artificial Analysis	GPT-6 Astra (High) AA-Omniscience Non-Hallucination Rate	57.5%
Vals AI	GPT-6 Astra BioMysteryBench	79.3%
Vals AI	GPT-6 Astra Code Migration v1.1	80.6%
Vals AI	GPT-6 Astra CyberBench v1.1	41.1%
Vals AI	GPT-6 Astra EMB v1.1	72.7%
Vals AI	GPT-6 Astra Finance Agent v2.1	60.4%
Vals AI	GPT-6 Astra Vals Finance Index	55.6%
Vals AI	GPT-6 Astra Financial Coaching Bench	67.5%
Vals AI	GPT-6 Astra HLAB-Vals-1.1	7.1%
Vals AI	GPT-6 Astra Immigration	67.7%
Vals AI	GPT-6 Astra IOI	100.0%
Vals AI	GPT-6 Astra Vals Legal Index	68.4%
Vals AI	GPT-6 Astra Legal Research Bench	39.4%
Vals AI	GPT-6 Astra MedCode	48.5%
Vals AI	GPT-6 Astra MedScribe	87.9%
Vals AI	GPT-6 Astra MysteryMechanism	53.2%
Vals AI	GPT-6 Astra ProgramBench	5.5%
Vals AI	GPT-6 Astra ProofBench v1.1	99.0%
Vals AI	GPT-6 Astra Robo-bench	23.3%
Vals AI	GPT-6 Astra Vals RSI Index	27.1%
Vals AI	GPT-6 Astra SAGE v1	46.4%
Vals AI	GPT-6 Astra Vals Science Index	65.1%
Vals AI	GPT-6 Astra SRE Bench	56.9%
Vals AI	GPT-6 Astra SWE-bench Multimodal	43.3%
Vals AI	GPT-6 Astra Tax Agent Bench	20.7%
Vals AI	GPT-6 Astra Terminal-Bench 4.0	59.6%
Vals AI	GPT-6 Astra Terminal-Bench-Science	62.9%
Vals AI	GPT-6 Astra Vals Index	65.0%
Vals AI	GPT-6 Astra Vibe Code Bench 1-100	27.6%
Vals AI	GPT-6 Astra Vibe Code Bench v1.1	89.6%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Codex

A coding agent that helps you build and ship with AI

493Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

53.9Btokens

Framer

Create a professional website with Framer’s no-code AI website builder. Design freely, manage CMS content, optimize SEO, collaborate, and publish fast.

49.7Btokens

There are many coding agents, but this one is yours.

30.8Btokens

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

30.1Btokens

Rest of OpenRouter

5.87B

Top 5 Apps

4.12B

OpenAI: GPT Astra versions

Not currently available through EU in-region routing. In-region routing docs

More models from OpenAI

GPT Image 2.6 Sunburst

GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next at medium or high quality, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Flare instead when speed matters more than fine detail.

Image$8 / $30

GPT Image 2.6 Flare

GPT Image 2.6 Flare is OpenAI's image generation and editing model optimized for speed: fast iteration and interactive text-to-image and image-to-image workflows, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Sunburst instead when detail and edit-to-edit consistency matter more than latency.

Image$8 / $30

GPT-6.1 Terra Pro

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Terra instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Terra Pro (batch)

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.50 / $2.50

GPT-6.1 Terra

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

Text1.1M context$1 / $5

GPT-6.1 Terra (batch)

Text1.1M context$0.50 / $2.50

GPT-6 Luna Decisions

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content.

Decisions$0.10 / $0

GPT-6.1 Sol Pro

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6.1 Sol Pro (batch)

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Sol

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

Text1.1M context$2 / $10

GPT-6.1 Sol (batch)

Text1.1M context$1 / $5

GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Luna instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.10 / $0.50

GPT-6 Luna Pro (batch)

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.05 / $0.25

GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

Text1.1M context$0.10 / $0.50

GPT-6 Luna (batch)

Text1.1M context$0.05 / $0.25

GPT-6 Sol Pro

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6 Sol Pro (batch)

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6 Sol

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

Text1.1M context$2 / $10

GPT-6 Sol (batch)

Text1.1M context$1 / $5

GPT Astra Latest

This model always redirects to the latest model in the GPT Astra family.

Text1.1M context

OpenAI: GPT-6 Astra

Providers