OpenAI
GPT-4 Turbo
model
gpt-4-turboPremiumStableVisionStreamingVisionToolsBatchLong contextUnited States
Context
128K
Input / 1M tokens
$10.00
Output / 1M tokens
$30.00
About this model
GPT-4 Turbo
GPT-4 Turbo — OpenAI's previous-generation flagship. Still strong for general-purpose chat + vision; superseded by GPT-4o and the 5.x family on quality-per-dollar but retained for customers pinned to specific model versions.
Released
2024-04
Training cutoff
2023-12
Parameters
Not disclosed
Best for
Use cases
- ✓Customers with version-pinned production deployments
- ✓Vision tasks with established prompts
Strengths
What it does well
- ●Battle-tested at production scale
- ●Vision support
- ●128K context window
Limitations
Know the trade-offs
- !Premium price for legacy generation
- !Newer models (GPT-4o, GPT-5.x) match or beat on quality at lower cost
Code example
Chat completion with GPT-4 Turbo
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="gpt-4-turbo",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Alternatives
Similar models in our catalog
Workloads that fit GPT-4 Turbo often fit these too. Compare benchmarks and pricing before locking in a default.