BazaarLinkBazaarLink
Sign in

GPT 4o API Pricing & Quick Start

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...

Intelligence#405 / 638
8
Artificial Analysis Intelligence Index
Speed#89 / 329
138.7
Output tokens per second (median)
Input Price#367 / 437
$2.50NT$ 79
USD / 1M tokens
Output Price#335 / 437
$10.00NT$ 316
USD / 1M tokens
First-token latency#52 / 329
0.95s
Time to first token (AA median)
ProviderOpenAI
ReleasedMay 2024
Model IDopenai/gpt-4o

Technical specifications

Context window
128K tokens
Reasoning
No
Input
TextImageFile
Output
Text

Pricing comparison

BazaarLink retail price alongside AA's observed market standard.

BazaarLink price our site

Input$2.50NT$ 79
Output$10.00NT$ 316
Cache read$1.25NT$ 39
Cache write
3:1 blended (est.)$4.38NT$ 138
All prices per 1M tokens. Supports TWD credit card / official invoice.

Market reference Artificial Analysis

Input$2.50
Output$10.00
Cache readAA not tracked
Cache writeAA not tracked
3:1 blended$4.38
✓ Matches market reference — BazaarLink does not mark up.
Source: artificialanalysis.ai

Independent benchmarks

Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.

Intelligence 8
Coding
Math 6
MMLU 75
GPQA 54
This modelCategory leader
Overall intelligence
#405out of 638 models
Aggregated across academic benchmarks
Time to first token
#52out of 329 models
AA 全球 p50:0.95 秒
Intelligence
8
Mid-tier
This model
8
Category leader
53
Median
12
Math
6
This model
6
Category leader
99
Median
53
MMLU Pro
75%
This model
75%
Category leader
90%
Median
75%
GPQA
54%
This model
54%
Category leader
94%
Median
69%
LiveCodeBench
31%
This model
31%
Category leader
42%
Median
42%
HLE
3%
This model
3%
Category leader
53%
Median
7%
SciCode
33%
This model
33%
Category leader
60%
Median
34%
IFBench
34%
This model
34%
Category leader
83%
Median
44%
τ²-Bench Telecom
25%
This model
25%
Category leader
99%
Median
46%
AA-LCR
0%
This model
0%
Category leader
76%
Median
40%
Terminal-Bench Hard
8%
This model
8%
Category leader
66%
Median
14%

Top 5 — CodingCoding Index leaderboard

2Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)?/claude-fable-5-1-xhigh81$10 / $50
3Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)?/claude-fable-5-1-high79$10 / $50
4GPT-5.6 Sol (xhigh)openai/gpt-5-6-sol-xhigh78$4 / $20
AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →

Quick Start

Use GPT 4o via BazaarLink API — just change the base_url:

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.bazaarlink.ai/v1",
    api_key="sk-bl-YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
TypeScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.bazaarlink.ai/v1",
  apiKey: "sk-bl-YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Why use GPT 4o via BazaarLink?

  • USD billing (TWD-quoted) + unified invoices — no foreign credit card needed for Taiwan teams
  • OpenAI-compatible API — zero code changes required
  • Automatic failover — multi-provider redundancy for the same model
  • Chinese-language support — local team, instant help
Try Now← All Models

Frequently Asked Questions

What is GPT 4o?

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...

How much does the GPT 4o API cost?

GPT 4o costs $2.50 per 1M input tokens and $10.00 per 1M output tokens when accessed through BazaarLink.

How do I use GPT 4o with the OpenAI SDK?

Set base_url to "https://api.bazaarlink.ai/v1" and use model ID "openai/gpt-4o". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.

What is the context window for GPT 4o?

GPT 4o supports a context window of 128,000 tokens.

Is GPT 4o available for free?

GPT 4o is a paid model. BazaarLink offers free trial credits on registration so you can test it without a credit card.

Relay integrity checks

Tested endpoints
20 runs
Independent hosts
15
Model-family fingerprint match
45%
Anomalies detected
2 runs
Data range
past 90 days

BazaarLink Probe verifies endpoints that claim to serve this model and flags behavior that differs from the reference baseline.

View the full integrity report →

Related models and links

More from this provider: OpenAI

GPT 5.3 CodexGPT 5 MiniGPT 5.1GPT 5.4GPT 5.6 SolText Embedding Ada 002
ModelsAPI documentationAPI latency probe
Support
Support
Hi! How can we help you?
Send a message and we'll get back to you soon.