GPT-5

openai/gpt-5
VisionToolsJSONReasoning
by OpenAI · 2025-08-07

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...

ctx400K tokens
Max output128K
Inputtext + image + file
Outputtext
p50 TTFT10.00 s
INPUT$1.25/ 1M tokens
OUTPUT$10.00/ 1M tokens
p50 TTFT10.00 s7d
p95 TTFT10.00 s7d
TRAFFIC86.4Ktokens / 7d

OpenAI GPT-5 is a large language model developed by OpenAI, supporting a context window of 400,000 tokens and a maximum output of 128,000 tokens. It accepts text, image, and file inputs, allowing…

What is OpenAI GPT-5?

Who is GPT-5 designed for?

What input modalities does GPT-5 support?

How does GPT-5's context window compare to earlier models?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • response_format
  • seed
  • stream
  • structured_outputs
  • tool_choice
  • tools

Pricing

Input / 1M tokens$1.25
Output / 1M tokens$10.00
Cache read / 1M$0.125
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $38.75 · With prompt caching $34.81

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.005025

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
10.00 s
Output speed
296 tok/s
p95 TTFT
10.00 s
Error rate
0%

Public benchmarks

37.8
AA Coding
Better than 39% of models compared
#72 of 123
34.7
AA Intelligence
Better than 46% of models compared
#63 of 125
94.3
AA Math
Better than 88% of models compared
#8 of 81
AIME
95.7
AIME 2025
94.3
GPQA Diamond
85.4
Humanity's Last Exam
26.5
IFBench
73.1
LiveCodeBench
84.6
Long-Context Recall
75.6
MATH-500
99.4
MMLU-Pro
87.1
SciCode
42.9
tau_banking
19.6
TerminalBench Hard
32.6
terminalbench_v2_1
35.2
τ²-Bench
84.8
Source: artificialanalysis.ai

How it compares

GPT-5GPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$1.25$21.00$60.00$5.00
Output $/M$10.00$168.00$270.00$30.00
Context400K400K1.1M
Quality7/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

How much does GPT-5 cost per token on OrcaRouter?
GPT-5 is priced at $1.25 per 1 million input tokens and $10 per 1 million output tokens. OrcaRouter adds zero markup, so you pay exactly the provider rate.
What is the context window size of GPT-5?
GPT-5 supports a context window of 400,000 tokens. This means it can process inputs of up to 400k tokens (including text, images, and files) and generate outputs of up to 128,000 tokens.
What are GPT-5's main strengths?
GPT-5 excels in mathematical reasoning (99.4 on MATH-500), long-context comprehension (400k tokens), and multimodal processing (text, image, file inputs). It is ideal for complex analytical tasks.
How does GPT-5 compare to GPT-4o?
GPT-5 has a larger context window (400k vs 128k), a higher MATH-500 score (99.4 vs ~90), and lower input pricing ($1.25 vs $2.50 per 1M tokens) via OrcaRouter. Output pricing is the same at $10 per 1M tokens.
Does OrcaRouter store my data when using GPT-5?
Data handling follows OpenAI's terms of service for the GPT-5 model. OrcaRouter does not store prompts or responses beyond what is necessary to route requests. For specific data policies, refer to OpenAI's privacy policy and OrcaRouter's terms.
How do I call GPT-5 through OrcaRouter's API?
Use the OpenAI-compatible API at https://api.orcarouter.ai/v1 with model ID "openai/gpt-5". Authenticate with your OrcaRouter API key. You can use standard OpenAI parameters including streaming.
What input modalities does GPT-5 support?
GPT-5 accepts text, image, and file inputs. You can include images and files in the API request alongside text, enabling multimodal reasoning within the 400k-token context.
Is there any markup on GPT-5 pricing?
No. OrcaRouter bills GPT-5 at the provider rate with zero markup. You pay exactly $1.25 per 1M input tokens and $10 per 1M output tokens.
Can I use GPT-5 for real-time applications?
Yes, the OrcaRouter API supports streaming (set stream=true) to reduce perceived latency. However, for low-latency requirements, consider using a smaller model unless the 400k context is essential.
What is the maximum output length of GPT-5?
GPT-5 can generate up to 128,000 tokens in a single response. This allows long-form content such as reports, code, or detailed analyses.

Embed this badge

OpenAI: GPT-5$1.25/M in10000ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-5" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-5.svg" alt="OpenAI: GPT-5 on OrcaRouter" /> </a>
Markdown [![OpenAI: GPT-5](https://www.orcarouter.ai/embed/openai/gpt-5.svg)](https://www.orcarouter.ai/models/openai/gpt-5)

Model card as data

GET /api/public/models/openai/gpt-5Open
Machine-readable:/llms.txt/llms-full.txt