Last refreshed 2026-05-20. Next refresh: weekly.
Why use GPT-5.3 Chat on OpenAI API?
OpenAI API offers GPT-5.3 Chat with pay-as-you-go pricing at $1.75/1M input tokens. OpenAI is a leading AI research and deployment company dedicated to developing safe and beneficial artificial general intelligence (AGI) for humanity.
Compare GPT-5.3 Chat across 3 providers to find the best fit for your use caseInput / 1M
$1.75
Output / 1M
$14.00
Cache
read $0.175
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export OPENAI_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY from env
response = client.chat.completions.create(Model ID
gpt-5.3-chat-latestRequest example
import os
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY from env
response = client.chat.completions.create(
model="gpt-5.3-chat-latest",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "gpt-5.3-chat-latest", not the LLMReference slug "gpt-5.3-chat".
- Use the model slug directly, e.g. "gpt-4o" or "gpt-4.1-mini".
- The examples expect OPENAI_API_KEY; rename it only if your application config maps the new variable.
Compare GPT-5.3 Chat Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenAI API | $1.75 | $14.00 |
| Vercel AI Gateway | $1.75 | $14.00 |
| OpenRouter | $1.75 | $14.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.75 |
| Output tokens | $14.00 |
Capabilities
VisionMultimodalJSON / Tool useStructured OutputsPrompt Caching
About GPT-5.3 Chat
GPT-5.3's conversational model, marketed as GPT-5.3 Instant. Available via the OpenAI API as gpt-5.3-chat-latest and in Azure AI Foundry as gpt-5.3-chat preview. Released March 3, 2026 as an update to ChatGPT's default model with reduced hallucinations, anti-sycophancy alignment, and faster short-prompt responses. GPT-5.5 Instant succeeded it as ChatGPT's default model on May 5, 2026.
Get Started
Model Specs
Released2026-03-03
Context128k
ArchitectureDecoder Only
Knowledge cutoff2025-08