Last refreshed 2026-06-04. Next refresh: weekly.
Why use GPT-5.1 Codex Mini on OpenAI API?
OpenAI API offers GPT-5.1 Codex Mini with pay-as-you-go pricing at $0.25/1M 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-5.1 Codex Mini across 3 providers to find the best fit for your use caseInput / 1M
$0.25
Output / 1M
$2.00
Cache
read $0.025
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-5.1-codex-miniRequest example
import os
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY from env
response = client.chat.completions.create(
model="gpt-5.1-codex-mini",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- 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-5.1 Codex Mini Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Vercel AI Gateway | $0.25 | $2.00 |
| OpenRouter | $0.25 | $2.00 |
| OpenAI API | $0.25 | $2.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.25 |
| Output tokens | $2.00 |
Capabilities
VisionMultimodalReasoningJSON / Tool use
About GPT-5.1 Codex Mini
GPT-5.1 Codex Mini is a smaller, faster, and more cost-efficient agentic coding model in the GPT-5.1 Codex lineup. Delivers approximately 4x more usage within ChatGPT subscriptions compared to GPT-5.1 Codex Max at a slight capability tradeoff. Priced at $0.25 per 1M input tokens and $2 per 1M output tokens via API. Available in the Codex CLI and IDE extension, where it is offered automatically when users approach their usage limit.
Get Started
Model Specs
Released2025-11-13
Context400k
ArchitectureDecoder Only
Knowledge cutoff2024-09