openai/gpt-5-search-api

openai/gpt-5-search-api
VisionToolsJSON
by openai

GPT-5 Search API: Powerful text and image model via OrcaRouter. 128K output tokens, competitive pricing.

Max output128K
Inputtext + image
p50 TTFT9.53 s
INPUT$1.25/ 1M tokens
OUTPUT$10.00/ 1M tokens
p50 TTFT9.53 s7d
p95 TTFT9.53 s7d
TRAFFIC22.6Ktokens / 7d

The GPT-5 Search API is a model from OpenAI, accessible through OrcaRouter’s OpenAI-compatible API at https://api.orcarouter.ai/v1 with model ID "openai/gpt-5-search-api". It accepts text and image…

What is the GPT-5 Search API?

Who is this model designed for?

How do I access the GPT-5 Search API?

What input modalities does it support?

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-search-api",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • max_tokens
  • response_format
  • service_tier
  • stop
  • stream
  • structured_outputs
  • tool_choice
  • tools
  • top_p
  • web_search_options

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
9.53 s
Output speed
379 tok/s
p95 TTFT
9.53 s
Error rate
0%

Public benchmarks

Source: Design Arena

How it compares

openai/gpt-5-search-apiGPT-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
Context400K1.1M
Quality7/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost of using GPT-5 Search API?
Input tokens cost $1.25 per 1M tokens; output tokens cost $10.00 per 1M tokens. These are provider rates with zero markup from OrcaRouter.
What is the maximum output context window?
The model can generate up to 128,000 tokens per output. Input context size is not specified.
What are the main strengths of GPT-5 Search API?
It combines a high output token limit with multimodal text and image input, and is optimized for search-augmented generation tasks.
How does it compare to GPT-4o?
It has a larger output limit (128K vs 16K), supports images, and is search-focused. It is more expensive per token.
How do I call it via OrcaRouter?
Use the OpenAI-compatible API at https://api.orcarouter.ai/v1 with model "openai/gpt-5-search-api" and your OrcaRouter API key.
Does OrcaRouter add any markup on pricing?
No, OrcaRouter passes through provider rates with zero markup. You pay exactly $1.25/$10 per 1M tokens.
Can I use images as input?
Yes, the model accepts both text and image inputs via the standard chat completions format.
Are there any benchmark results available?
No specific benchmark scores are provided in the given facts. Performance should be evaluated on your own tasks.
What are the limitations?
No public benchmarks, potentially high cost for long outputs, and image processing may add latency. Input context limit is unknown.
How do I migrate from another model?
Change the base URL to OrcaRouter’s and update the model ID to "openai/gpt-5-search-api". Adjust max_tokens if needed.

Embed this badge

openai/gpt-5-search-api$1.25/M in9532ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-5-search-api" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-5-search-api.svg" alt="openai/gpt-5-search-api on OrcaRouter" /> </a>
Markdown [![openai/gpt-5-search-api](https://www.orcarouter.ai/embed/openai/gpt-5-search-api.svg)](https://www.orcarouter.ai/models/openai/gpt-5-search-api)

Model card as data

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