impulse

Codex Mini

Frontier lab
API id codex-mini
Input / 1M
$1.50
at Azure OpenAI
Output / 1M
$6.00
at Azure OpenAI
Context window
200K
tokens
Max output
100K
tokens per reply
Hosts
2
4 listings
Released
-
date not published

Pricing

List prices at Azure OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.50$6.00
Cached input
75% off input
$0.375

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
Use your own numbers

Where to run it

2 hosts serve Codex Mini. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
codex-mini
$1.50 / $6.00
codex-mini
$1.50 / $6.00
Show 2 more listings: regions, snapshots and variants
Azure OpenAI
eu
codex-mini
$1.65 / $6.60
+10% vs headline
us
codex-mini
$1.65 / $6.60
+10% vs headline

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

  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    24% less
  • GPT-5.4 Mini
    OpenAI · on OpenAI
    $0.75 / $4.50
    Has every key capability
    36% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    82% less

Other frontier labs

  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    43% less
  • Grok Build 0.1
    xAI · on xAI
    $1.00 / $2.00
    Has every key capability
    52% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    92% less
  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    68% less

Open-weight picks

  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    14% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    34% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    74% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    80% less

Call it

Using Azure OpenAI's API.

Python
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
}