GPT-5

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.

openai/gpt-5

Organization: OpenAI
Family: gpt
Providers: 35
Context: 400,000
Output limit: 128,000
Knowledge: 2024-09-30
Release: 2025-08-07
Updated: —
Weights: Closed
Input: text, image/jpeg, image/png, image/gif, image/webp
Output: text
Capabilities: —

Providers

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

40 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	gpt-5-thinking	400,000	128,000	— / —	—	—	—	View
302.AI	gpt-5	400,000	128,000	— / —	—	—	—	View
Abacus	gpt-5	400,000	128,000	— / —	—	—	—	View
AIHubMix	gpt-5	400,000	128,000	— / —	—	—	—	View
AI/ML API	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
AnyAPI	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Cloudflare AI Gateway	openai/gpt-5	128,000	128,000	— / —	—	—	—	View
Cortecs	gpt-5	400,000	128,000	— / —	—	—	—	View
Databricks	databricks-gpt-5	400,000	128,000	— / —	—	—	—	View
DevPass (LLM Gateway)	gpt-5	400,000	128,000	— / —	—	—	—	View
DigitalOcean	openai-gpt-5	400,000	128,000	— / —	—	—	—	View
Eden AI	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
FastRouter	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Helicone	gpt-5	400,000	128,000	— / —	—	—	—	View
Impossibl	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Kilo Gateway	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
LLM Gateway	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
LLM Gateway	azure/gpt-5	400,000	128,000	— / —	—	—	—	View
LowRouter	auto/openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Merge Gateway	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Model Oracle AI	gpt-5	400,000	128,000	— / —	—	—	—	View
NanoGPT	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
NEAR AI Cloud	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Neon	gpt-5	400,000	128,000	— / —	—	—	—	View
Ofox	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
OpenAI	gpt-5	400,000	128,000	— / —	—	—	—	View
OpenCode	gpt-5	400,000	128,000	— / —	—	—	—	View
Azurevia OpenRouter	openai/gpt-5 unknown	400,000	128,000	$1.25 / $10.00	Yes	Yes	Yes	View
Azurevia OpenRouter	openai/gpt-5 unknown	400,000	128,000	$1.375 / $11.00	Yes	Yes	Yes	View
OpenAIvia OpenRouter	openai/gpt-5 unknown	400,000	128,000	$1.25 / $10.00	Yes	Yes	Yes	View
OrcaRouter	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Poe	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Prime Inference	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Qiniu	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
Requesty	gpt-5@eu	400,000	128,000	— / —	—	—	—	View
SAP AI Core	gpt-5	400,000	128,000	— / —	—	—	—	View
Snowflake Cortex	openai-gpt-5	272,000	8,192	— / —	—	—	—	View
Vercel AI Gateway	openai/gpt-5-fast	400,000	128,000	— / —	—	—	—	View
Vercel AI Gateway	openai/gpt-5	400,000	128,000	— / —	—	—	—	View
ZenMux	openai/gpt-5	400,000	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$1.25Per 1M input tokens

Output from$10.00Per 1M output tokens

Available offers40Across 35 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 · 3 lowest-priced configurations

InputOutput

Azureazure

$1.25$10.00

OpenAIopenai/default

$1.25$10.00

Azureazure/swedencentral

$1.375$11.00

openai/gpt-5Observed Oct 10, 2026, 11:31 AM UTC

Input: $1.25
Output: $10.00
Cache read: $0.125

Additional fees and pricing conditions

web search: $0.01 / search

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Azureazure	$1.25	$10.00	$0.125	—
Azureazure/swedencentral	$1.375	$11.00	$0.1375	—
OpenAIopenai/default	$1.25	$10.00	$0.125	—

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 · 2 endpoints

P50P75P90P99

Azureazure

9,132–44,750.76 ms

OpenAIopenai/default

3,382–28,753.88 ms

All latency percentiles 2 endpoints

Endpoint	P50	P75	P90	P99
Azureazure	9,132 ms	12,998 ms	16,408.8 ms	44,750.76 ms
OpenAIopenai/default	3,382 ms	5,883 ms	10,084.6 ms	28,753.88 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 2 endpoints

P50P75P90P99

Azureazure

74.5–105.96 t/s

OpenAIopenai/default

66–123 t/s

All throughput percentiles 2 endpoints

Endpoint	P50	P75	P90	P99
Azureazure	74.5 t/s	85 t/s	90 t/s	105.96 t/s
OpenAIopenai/default	66 t/s	85 t/s	99 t/s	123 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 · 3 endpoints

Endpoint5 minutes30 minutes24 hours

AzureazureObserved Oct 10, 2026, 11:31 AM UTC

100%

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

—

100%

OpenAIopenai/defaultObserved 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-5Observed Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 40

Coding

37.8

Intelligence

Design Arena	Category	Elo	Win rate	Rank
models	3d	1,061	41.3%	96
models	asciiart	1,147	49%	44
models	codecategories	1,172	54.5%	68
models	dataviz	1,225	60.5%	46
models	gamedev	1,192	59.3%	55
models	svg	1,188	64.1%	29
models	uicomponent	1,183	57.4%	60
models	website	1,189	53.7%	67

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

tau bench verified airlineOpenAI: GPT-5

68.919%

gpqa diamondOpenAI: GPT-5

85.69%

Evaluation	Configuration	Source	Results	Details
models · gamedev	GPT-5 (Minimal)openai/gpt-5-2025-08-07	Design Arena	1,155 Elo	Details
tau bench verified airline	OpenAI: GPT-5openai/gpt-5-2025-08-07	OpenRouter	68.919%	Details
models · gamedev	GPT-5 (High)openai/gpt-5-2025-08-07	Design Arena	1,185 Elo	Details
models · codecategories	GPT-5 (High)openai/gpt-5-2025-08-07	Design Arena	1,168 Elo	Details
models · website	GPT-5 (High)openai/gpt-5-2025-08-07	Design Arena	1,182 Elo	Details
models · codecategories	GPT-5 (Minimal)openai/gpt-5-2025-08-07	Design Arena	1,165 Elo	Details
models · 3d	GPT-5 (Minimal)openai/gpt-5-2025-08-07	Design Arena	1,056 Elo	Details
models · dataviz	GPT-5 (Minimal)openai/gpt-5-2025-08-07	Design Arena	1,176 Elo	Details
models · website	GPT-5 (Minimal)openai/gpt-5-2025-08-07	Design Arena	1,184 Elo	Details
models · uicomponent	GPT-5 (Minimal)openai/gpt-5-2025-08-07	Design Arena	1,142 Elo	Details
models · uicomponent	GPT-5 (High)openai/gpt-5-2025-08-07	Design Arena	1,177 Elo	Details
models · svg	GPT-5 (Minimal)openai/gpt-5-2025-08-07	Design Arena	1,128 Elo	Details
Composite indices	GPT-5 (High)openai/gpt-5-2025-08-07	Artificial Analysis	Intelligence 23 · Coding 37.8 · Agentic —	Details
gpqa diamond	OpenAI: GPT-5openai/gpt-5-2025-08-07	OpenRouter	85.69%	Details
models · svg	GPT-5 (High)openai/gpt-5-2025-08-07	Design Arena	1,189 Elo	Details
models · asciiart	GPT-5 (Minimal)openai/gpt-5-2025-08-07	Design Arena	1,141 Elo	Details
models · 3d	GPT-5 (High)openai/gpt-5-2025-08-07	Design Arena	1,026 Elo	Details
models · dataviz	GPT-5 (High)openai/gpt-5-2025-08-07	Design Arena	1,221 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Technical details & API

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

Current route specifications

openai/gpt-5Observed Oct 10, 2026, 11:31 AM UTC

Context: 400,000
Maximum output: 128,000
Tokenizer: GPT
Input: text, image, file
Output: text
Moderation: Yes
Knowledge cutoff: 2024-09-30
Added to OpenRouter: 2025-08-07

Base URLhttps://openrouter.ai/api/v1

Model IDopenai/gpt-5

Version IDopenai/gpt-5-2025-08-07

Reasoning

Required: Yes
Enabled by default: Not reported
Default effort: medium
Supported efforts: high, medium, low, minimal

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-5 cost?

Listed rates start at $1.25 per million input tokens and $10.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GPT-5?

There are 40 cataloged offers across 35 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 400,000 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 · d7bf12e87744
Sep 14, 2026 · 7de30b9eb5ac
Sep 12, 2026 · 0e927a998ed8