LiteLLMModels

Codex Mini API Pricing

As of October 10, 2026, Codex Mini costs $1.50 per 1M input tokens and $6.00 per 1M output tokens from Azure OpenAI, the lowest of 2 providers, with cache reads at $0.375 per 1M tokens. It has a 200,000-token context window and returns up to 100,000 tokens per response.

By OpenAIModel ID azure/codex-miniPrices updated Checked
Scheduled for deprecation: Azure OpenAI lists November 15, 2026 as the deprecation date for azure/codex-mini.
Input
$1.50 / 1M tokens
Output
$6.00 / 1M tokens
Cache read
$0.375 / 1M tokens
Context window
200,000 tokens
Max output
100,000 tokens
Providers
2
Added to LiteLLM
June 2025

Codex Mini pricing by provider

4 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readContext
Azure OpenAIazure/codex-mini$1.50$6.00$0.375200K
Azure AI Foundryazure_ai/codex-mini$1.50$6.00$0.375200K
Azure OpenAIeuazure/eu/codex-mini$1.65$6.60$0.413–
Azure OpenAIusazure/us/codex-mini$1.65$6.60$0.413–

What Codex Mini costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Azure OpenAI$6.00
Azure AI Foundry$6.00

100 long-document requests with 100,000 input and 2,000 output tokens each

Azure OpenAI$16.20
Azure AI Foundry$16.20

Codex Mini features

Input: text, image. Output: text.

Use Codex Mini with LiteLLM

Call Codex Mini through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/responses. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="azure/codex-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: codex-mini
    litellm_params:
      model: azure/codex-mini
      api_base: os.environ/AZURE_API_BASE
      api_key: os.environ/AZURE_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "codex-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Codex Mini FAQ

How much does Codex Mini cost?

Codex Mini costs $1.50 per 1M input tokens and $6.00 per 1M output tokens from Azure OpenAI, the lowest of 2 providers, with cache reads at $0.375 per 1M tokens.

What is the context window of Codex Mini?

Codex Mini has a 200,000-token context window and returns up to 100,000 tokens per response.

Which providers offer Codex Mini?

Codex Mini is available from 2 providers through LiteLLM: Azure OpenAI and Azure AI Foundry.

How do I call Codex Mini with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure/codex-mini", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/responses from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Codex Mini support?

Codex Mini supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning and prompt caching.

When did LiteLLM add Codex Mini?

Codex Mini was added to LiteLLM's model price file in June 2025.

Is Codex Mini being deprecated?

Azure OpenAI lists a deprecation date of November 15, 2026 for azure/codex-mini.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Azure OpenAI, Azure AI Foundry.

Provider pages: Azure OpenAI, Azure AI Foundry.