LiteLLMModels

Grok 3 Mini API Pricing

As of October 10, 2026, Grok 3 Mini costs $0.25 per 1M input tokens and $1.27 per 1M output tokens from Azure AI Foundry, the lowest of 3 providers. It has a 131,072-token context window and returns up to 131,072 tokens per response.

By xAIModel ID azure_ai/grok-3-miniPrices updated Checked
Deprecated: Azure AI Foundry lists May 1, 2026 as the deprecation date for azure_ai/grok-3-mini.
Input
$0.25 / 1M tokens
Output
$1.27 / 1M tokens
Context window
131,072 tokens
Max output
131,072 tokens
Providers
3
Added to LiteLLM
June 2025

Grok 3 Mini pricing by provider

3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputContext
Azure AI Foundryazure_ai/grok-3-mini$0.25$1.27–
Oracle Cloud (OCI)oci/xai.grok-3-mini$0.30$0.50128K
Vercel AI Gatewayvercel_ai_gateway/xai/grok-3-mini$0.30$0.50128K

What Grok 3 Mini costs in practice

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

Azure AI Foundry$1.135
Oracle Cloud (OCI)$0.85
Vercel AI Gateway$0.85

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

Azure AI Foundry$2.754
Oracle Cloud (OCI)$3.10
Vercel AI Gateway$3.10

Grok 3 Mini features

Use Grok 3 Mini with LiteLLM

Call Grok 3 Mini through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="azure_ai/grok-3-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: grok-3-mini
    litellm_params:
      model: azure_ai/grok-3-mini
      # credentials: see the provider's LiteLLM docs page
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": "grok-3-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Grok 3 Mini FAQ

How much does Grok 3 Mini cost?

Grok 3 Mini costs $0.25 per 1M input tokens and $1.27 per 1M output tokens from Azure AI Foundry, the lowest of 3 providers.

What is the context window of Grok 3 Mini?

Grok 3 Mini has a 131,072-token context window and returns up to 131,072 tokens per response.

Which providers offer Grok 3 Mini?

Grok 3 Mini is available from 3 providers through LiteLLM: Azure AI Foundry, Oracle Cloud (OCI) and Vercel AI Gateway. The lowest price is on Azure AI Foundry.

How do I call Grok 3 Mini with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure_ai/grok-3-mini", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Grok 3 Mini support?

Grok 3 Mini supports function calling.

When did LiteLLM add Grok 3 Mini?

Grok 3 Mini was added to LiteLLM's model price file in June 2025.

Is Grok 3 Mini being deprecated?

Azure AI Foundry deprecated azure_ai/grok-3-mini on May 1, 2026.

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 AI Foundry, Oracle Cloud (OCI), Vercel AI Gateway.

Provider pages: Azure AI Foundry, Oracle Cloud (OCI), Vercel AI Gateway.