GPT-5.1 Codex Mini
GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
gpt-5.1-codex-miniReleased 13 Nov 2025 (Nov 2025)Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.25 | $2.00 | |
| Cached input 90% off input | $0.025 | 90% off input |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$205
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$138
- Coding agent1,000 requests a day, 40K in / 2K out, cached$231
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,080
Where to run it
2 hosts serve GPT-5.1 Codex Mini. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-5.1-codex-mini | $0.25 / $2.00 | gpt-5.1-codex-mini | |
Azure OpenAICloud gpt-5.1-codex-mini | $0.25 / $2.00 Retires 15 May 2027 | gpt-5.1-codex-mini | Retires 15 May 2027 |
ChatGPTSubscription gpt-5.1-codex-mini | In the subscription | gpt-5.1-codex-mini |
Show 4 more listings: regions, snapshots and variantsHide regional listings
| Azure OpenAI | |||||||
| global gpt-5.1-codex-mini | $0.25 / $2.00 Retires 15 May 2027 | gpt-5.1-codex-mini | Retires 15 May 2027 | ||||
| 2025-11-13 gpt-5.1-codex-mini-2025-11-13 | $0.25 / $2.00 Retires 15 May 2027 | gpt-5.1-codex-mini-2025-11-13 | Retires 15 May 2027 | ||||
| eu gpt-5.1-codex-mini | $0.275 / $2.20 +10% vs headline Retires 15 May 2027 | gpt-5.1-codex-mini | Retires 15 May 2027 | ||||
| us gpt-5.1-codex-mini | $0.275 / $2.20 +10% vs headline Retires 15 May 2027 | gpt-5.1-codex-mini | Retires 15 May 2027 | ||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- ImagesTextPDFs
- Produces
- Text
- Features
- Parallel tool callsPDF inputPrompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than OpenAI.
Smaller OpenAI models
- 33% less
- 71% less
- 62% less
Other frontier labs
- 71% less
Open-weight picks
- 0% less
- 7% less
- 24% less
- 30% less
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-5.1-codex-mini", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-5.1-codex-mini", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-5.1-codex-mini",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-5.1 Codex Mini cost?
On OpenAI, GPT-5.1 Codex Mini costs $0.25 per million input tokens and $2.00 per million output tokens. Cached input costs $0.025 per million tokens.
Which APIs offer GPT-5.1 Codex Mini?
GPT-5.1 Codex Mini runs on 2 APIs: OpenAI and Azure OpenAI.
What is GPT-5.1 Codex Mini's context window?
400K tokens, with up to 128K tokens in one reply.
Is GPT-5.1 Codex Mini being retired?
Azure OpenAI retires it on 15 May 2027. 1 host keeps serving it.
What are cheaper alternatives to GPT-5.1 Codex Mini?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (33% less), Claude Haiku 5.5 on Anthropic (71% less) and Kimi K2.7 Code on CLF AI Gateway (0% less). Savings are on a mix of 3 input tokens to 1 output token.
When was GPT-5.1 Codex Mini released?
OpenAI released it on 13 Nov 2025.
What is GPT-5.1 Codex Mini's API model id?
Use gpt-5.1-codex-mini with OpenAI.
Sources
Raw catalog entry for gpt-5.1-codex-mini on OpenAI
{
"cache_read_input_token_cost": 2.5e-8,
"deprecation_date": "2026-07-23",
"deprecation_source": "https://developers.openai.com/api/docs/deprecations",
"successor_model": "gpt-5.6-terra",
"input_cost_per_token": 2.5e-7,
"litellm_provider": "openai",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 0.000002,
"fedramp_uplift_multiplier": 1.1,
"source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini",
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
}