Where is the GPT-5 documentation?

The GPT-5 documentation on OpenRouter includes the GPT-5 is now live blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does GPT-5 cost?

GPT-5 costs $1.25/M input tokens and $10.00/M output tokens, with separate rates for Cache Read at $0.125/M tokens.

What is the context length of GPT-5?

GPT-5 has a 400,000 token context window. It supports up to 128,000 completion tokens.

Does GPT-5 support tool calling and structured outputs?

Yes. GPT-5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does GPT-5 support?

GPT-5 accepts text, images, and files such as PDFs as input and returns text.

Which providers serve GPT-5?

GPT-5 is served by 2 providers on OpenRouter: Azure and OpenAI. 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-5 released?

GPT-5 was released on August 7, 2025. Its knowledge cutoff is September 30, 2024.

OpenAI: GPT-5

openai/gpt-5

Compare

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.

Modalities

In / out price

$1.25 / $10per 1M

Context

400K

Released

Aug 7, 2025

Knowledge cutoff

Sep 2024

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


	$1.25	$10.00	$0.125	5.29s	87 tok/s	100.00%
	$1.25	$10.00	$0.125	4.34s	71 tok/s	100.00%
Not used in Standard routing:Why these endpoints are not used
	$1.375	$11.00	$0.1375	3.78s	44 tok/s	100.00%

Input $1.25Output $10.00
87 tok/s100.00% uptime
Input $1.25Output $10.00
71 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $1.375Output $11.00
44 tok/s100.00% 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

$0.7241/M tokens

Output

$10.01/M tokens

GPT-5 — Price history

Price history

No effective price data for this selection

	$0.604	$10.00	57.4%	74.6%
	$1.114	$10.00	12.0%	22.3%
Not used in Standard routing:Why these endpoints are not used
	$1.243	$11.00	10.7%	3.0%

Effective in $0.604Effective out $10.00
Token share
74.6%
Effective in $1.114Effective out $10.00
Token share
22.3%
Not used in Standard routing:Why these endpoints are not used
Effective in $1.243Effective out $11.00
Token share
3.0%

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)

100.00%

Availability (3d)

99.91%

Availability over the last 3 days

Last 72 hours

Availability 99.91%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.93%

Without Routing

98.81%

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-5 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GPT-5 (Minimal) GPQA Diamond	67.3%
Artificial Analysis	GPT-5 (Minimal) HLE	6.0%
Artificial Analysis	GPT-5 (Minimal) IFBench	45.6%
Artificial Analysis	GPT-5 (Minimal) τ²-Bench Telecom	67.0%
Artificial Analysis	GPT-5 (Minimal) CritPt	0.0%
Artificial Analysis	GPT-5 (Minimal) LiveCodeBench	55.8%
Artificial Analysis	GPT-5 (Minimal) Terminal-Bench Hard	18.2%
Artificial Analysis	GPT-5 (Minimal) MMLU-Pro	80.6%
Artificial Analysis	GPT-5 (Minimal) AIME 2025	31.7%
Artificial Analysis	GPT-5 (Minimal) AIME	36.7%
Artificial Analysis	GPT-5 (Minimal) MATH-500	86.1%
Artificial Analysis	GPT-5 (High) Coding Index	37.8
Artificial Analysis	GPT-5 (High) GPQA Diamond	85.4%
Artificial Analysis	GPT-5 (High) HLE	28.5%
Artificial Analysis	GPT-5 (High) IFBench	73.1%
Artificial Analysis	GPT-5 (High) τ²-Bench Telecom	84.8%
Artificial Analysis	GPT-5 (High) AA-LCR	78.2%
Artificial Analysis	GPT-5 (High) τ-Bench Banking	22.1%
Artificial Analysis	GPT-5 (High) GDPval-AA	21.3%
Artificial Analysis	GPT-5 (High) CritPt	5.7%
Artificial Analysis	GPT-5 (High) LiveCodeBench	84.6%
Artificial Analysis	GPT-5 (High) Terminal-Bench Hard	32.6%
Artificial Analysis	GPT-5 (High) Terminal-Bench 2.1	35.2%
Artificial Analysis	GPT-5 (High) MMLU-Pro	87.1%
Artificial Analysis	GPT-5 (High) AIME 2025	94.3%
Artificial Analysis	GPT-5 (High) AIME	95.7%
Artificial Analysis	GPT-5 (High) MATH-500	99.4%
Artificial Analysis	GPT-5 (Medium) GPQA Diamond	84.2%
Artificial Analysis	GPT-5 (Medium) HLE	25.4%
Artificial Analysis	GPT-5 (Medium) IFBench	70.6%
Artificial Analysis	GPT-5 (Medium) τ²-Bench Telecom	86.5%
Artificial Analysis	GPT-5 (Medium) AA-LCR	76.0%
Artificial Analysis	GPT-5 (Medium) CritPt	0.0%
Artificial Analysis	GPT-5 (Medium) LiveCodeBench	70.3%
Artificial Analysis	GPT-5 (Medium) Terminal-Bench Hard	37.9%
Artificial Analysis	GPT-5 (Medium) MMLU-Pro	86.7%
Artificial Analysis	GPT-5 (Medium) AIME 2025	91.7%
Artificial Analysis	GPT-5 (Medium) AIME	91.7%
Artificial Analysis	GPT-5 (Medium) MATH-500	99.1%
Artificial Analysis	GPT-5 (Low) GPQA Diamond	80.8%
Artificial Analysis	GPT-5 (Low) HLE	19.6%
Artificial Analysis	GPT-5 (Low) IFBench	66.6%
Artificial Analysis	GPT-5 (Low) τ²-Bench Telecom	84.2%
Artificial Analysis	GPT-5 (Low) CritPt	1.1%
Artificial Analysis	GPT-5 (Low) LiveCodeBench	76.3%
Artificial Analysis	GPT-5 (Low) Terminal-Bench Hard	26.5%
Artificial Analysis	GPT-5 (Low) MMLU-Pro	86.0%
Artificial Analysis	GPT-5 (Low) AIME 2025	83.0%
Artificial Analysis	GPT-5 (Low) AIME	83.0%
Artificial Analysis	GPT-5 (Low) MATH-500	98.7%
Design Arena	GPT-5 (Minimal) Models Arena 3D Elo	1035
Design Arena	GPT-5 (Minimal) Models Arena Asciiart Elo	1136
Design Arena	GPT-5 (Minimal) Models Arena Code Categories Elo	1154
Design Arena	GPT-5 (Minimal) Models Arena Data Visualization Elo	1173
Design Arena	GPT-5 (Minimal) Models Arena Game Development Elo	1144
Design Arena	GPT-5 (Minimal) Models Arena SVG Elo	1116
Design Arena	GPT-5 (Minimal) Models Arena UI Component Elo	1135
Design Arena	GPT-5 (Minimal) Models Arena Website Elo	1176
Vals AI	GPT 5 AIME	93.4%
Vals AI	GPT 5 CaseLaw v2	66.5%
Vals AI	GPT 5 CorpFin v2	61.1%
Vals AI	GPT 5 Finance Agent v1.1	52.2%
Vals AI	GPT 5 GPQA Diamond	85.6%
Vals AI	GPT 5 IOI v1	20.0%
Vals AI	GPT 5 LiveCodeBench	85.9%
Vals AI	GPT 5 LegalBench	86.0%
Vals AI	GPT 5 MATH 500	96.0%
Vals AI	GPT 5 MedCode	49.6%
Vals AI	GPT 5 MedQA	96.3%
Vals AI	GPT 5 MedScribe	83.7%
Vals AI	GPT 5 MGSM	92.8%
Vals AI	GPT 5 MMLU Pro	86.5%
Vals AI	GPT 5 MMMU Pro	81.5%
Vals AI	GPT 5 MortgageTax	65.5%
Vals AI	GPT 5 ProofBench v1	18.0%
Vals AI	GPT 5 SAGE v1	43.7%
Vals AI	GPT 5 SWE-bench	69.0%
Vals AI	GPT 5 TaxEval v2	73.4%
Vals AI	GPT 5 Terminal-Bench 2.0	37.1%
Vals AI	GPT 5 Vals Index	49.0%
Vals AI	GPT 5 Vals Multimodal Index	49.9%
Vals AI	GPT 5 Vibe Code Bench v1.1	20.1%

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.

Sparkfire

new

1.43Btokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

773Mtokens

Lead Qualification Agent

new

612Mtokens

Codex

A coding agent that helps you build and ship with AI

592Mtokens

wm-backend-ai-review

new

533Mtokens

Rest of OpenRouter

535M

Top 5 Apps

50.5M

Available through EU in-region routing

OpenAI: GPT-5 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe

Azure

Prices in Europe

Azure: $1.375/M tokens input, $11/M tokens output

Base URL

https://eu.openrouter.ai/api/v1

Plan

Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. 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-5

Providers