openai/gpt-5-mini-2025-08-07

openai/gpt-5-mini-2025-08-07
VisionToolsJSONReasoning
by openai
Endpoints:/v1/chat/completions/v1/responses
ctx400K tokens
Max output128K
Inputtext + image + file
Outputtext
p50 TTFT791 ms
INPUT$0.25/ 1M tokens
OUTPUT$2.00/ 1M tokens
p50 TTFT791 ms7d
p95 TTFT1.54 s7d
TRAFFIC3.4Ktokens / 7d
Get the openai/gpt-5-mini-2025-08-07 API →▶ Try in playground</> Use via API

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="openai/gpt-5-mini-2025-08-07",
    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

Pricing
Input / 1M tokens$0.250
Output / 1M tokens$2.00
Cache read / 1M$0.025
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $7.75 · With prompt caching $6.96

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.001005

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

Performance

last 7 days
p50 TTFT
791 ms
Output speed
62.4 tok/s
p95 TTFT
1.54 s
Error rate
0%

Public benchmarks

Last evaluated 2025-08-07
15.6
AA Coding
Better than 9% of models compared
#125 of 138
16.8
AA Intelligence
Better than 26% of models compared
#108 of 148
90.7
AA Math
Better than 78% of models compared
#17 of 82
AIME 2025
90.7
GPQA Diamond
82.8
Humanity's Last Exam
21.5
IFBench
75.4
LiveCodeBench
83.8
Long-Context Recall
72.3
MMLU-Pro
83.7
SciCode
39.0
tau_banking
15.5
TerminalBench Hard
33.3
terminalbench_v2_1
3.7
τ²-Bench
68.4
Source: artificialanalysis.ai

Community buzz

What developers are saying this week

Hacker News0 mentions · 7d

How it compares

openai/gpt-5-mini-2025-08-07GPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$0.25$21.00$60.00$5.00
Output $/M$2.00$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

Browse AI model comparisons →

More from openai

See all models from openai →
GPT-5.5 ProFlagship
openai/gpt-5.5-pro
$30.00 in · $180.00 out / 1M
· quality 10/10
 Compare side-by-side
GPT-5.2Cheapest
openai/gpt-5.2
$1.75 in · $14.00 out / 1M
400K ctx· quality 9/10
 Compare side-by-side
openai/gpt-5.2-chat-latest
openai/gpt-5.2-chat-latest
$1.75 in · $14.00 out / 1M
· quality 9/10
 Compare side-by-side

FAQ

How much does openai/gpt-5-mini-2025-08-07 cost on OrcaRouter?
openai/gpt-5-mini-2025-08-07 is priced at $0.25 per 1M input tokens and $2.00 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
What is openai/gpt-5-mini-2025-08-07's context window?
openai/gpt-5-mini-2025-08-07 supports a context window of 400K tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call openai/gpt-5-mini-2025-08-07 via the OpenAI SDK?
Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="openai/gpt-5-mini-2025-08-07" in the chat.completions.create call.
Does OrcaRouter rate-limit openai/gpt-5-mini-2025-08-07?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.

Embed this badge

Paste into your blog post
openai/gpt-5-mini-2025-08-07•$0.25/M in•791ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-5-mini-2025-08-07" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-5-mini-2025-08-07.svg" alt="openai/gpt-5-mini-2025-08-07 on OrcaRouter" /> </a>
Markdown [![openai/gpt-5-mini-2025-08-07](https://www.orcarouter.ai/embed/openai/gpt-5-mini-2025-08-07.svg)](https://www.orcarouter.ai/models/openai/gpt-5-mini-2025-08-07)

Model card as data

GET /api/public/models/openai/gpt-5-mini-2025-08-07Open
Machine-readable:/llms.txt/llms-full.txt