Codex Mini
codex-miniPricing
List prices at Azure OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.50 | $6.00 | |
| Cached input 75% off input | $0.375 | 75% off input |
What it costs a month
At Azure OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$799
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$666
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,215
- Overnight batch20,000 requests a day, 4K in / 0.4K out$5,040
Where to run it
2 hosts serve Codex Mini. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Azure OpenAICloud codex-mini | $1.50 / $6.00 | codex-mini | |
Azure AI FoundryCloud codex-mini | $1.50 / $6.00 | codex-mini |
Show 2 more listings: regions, snapshots and variantsHide regional listings
| Azure OpenAI | |||||||
| eu codex-mini | $1.65 / $6.60 +10% vs headline | codex-mini | |||||
| us codex-mini | $1.65 / $6.60 +10% vs headline | codex-mini | |||||
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 Azure OpenAI.
Smaller OpenAI models
- 24% less
- 36% less
- 82% less
Other frontier labs
- 43% less
- 52% less
- 92% less
- 68% less
Open-weight picks
- 14% less
- 34% less
- 74% less
- 80% less
Call it
Using Azure OpenAI's API.
from litellm import completion
response = completion(
model="azure/codex-mini",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Codex Mini cost?
On Azure OpenAI, Codex Mini costs $1.50 per million input tokens and $6.00 per million output tokens. Cached input costs $0.375 per million tokens.
Which APIs offer Codex Mini?
Codex Mini runs on 2 APIs: Azure OpenAI and Azure AI Foundry.
What is Codex Mini's context window?
200K tokens, with up to 100K tokens in one reply.
Is Codex Mini being retired?
It has been retired: Azure OpenAI retired it on 15 Nov 2026.
What are cheaper alternatives to Codex Mini?
Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (24% less), Gemini 3.8 Flash on Google AI Studio (43% less), Grok Build 0.1 on xAI (52% less) and Qwen4 Max on Alibaba DashScope (14% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Codex Mini's API model id?
Use codex-mini with Azure OpenAI.
Sources
Raw catalog entry for codex-mini on Azure OpenAI
{
"cache_read_input_token_cost": 3.75e-7,
"deprecation_date": "2026-11-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
"input_cost_per_token": 0.0000015,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"mode": "responses",
"output_cost_per_token": 0.000006,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
}