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.
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.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Azure AI Foundry | azure_ai/grok-3-mini | $0.25 | $1.27 | – |
| Oracle Cloud (OCI) | oci/xai.grok-3-mini | $0.30 | $0.50 | 128K |
| Vercel AI Gateway | vercel_ai_gateway/xai/grok-3-mini | $0.30 | $0.50 | 128K |
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
- Function calling
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.
from litellm import completion
response = completion(
model="azure_ai/grok-3-mini",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: grok-3-mini
litellm_params:
model: azure_ai/grok-3-mini
# credentials: see the provider's LiteLLM docs pagecurl 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 $1.27 per 1M output tokens from Azure AI Foundry, the lowest of 3 providers.
What is the context window of Grok 3 Mini?
Grok 3 Mini has a 131,072-token context window and returns up to 131,072 tokens per response.
Which providers offer Grok 3 Mini?
Grok 3 Mini is available from 3 providers through LiteLLM: Azure AI Foundry, Oracle Cloud (OCI) and Vercel AI Gateway. The lowest price is on Azure AI Foundry.
How do I call Grok 3 Mini with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="azure_ai/grok-3-mini", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Grok 3 Mini support?
Grok 3 Mini supports function calling.
When did LiteLLM add Grok 3 Mini?
Grok 3 Mini was added to LiteLLM's model price file in June 2025.
Is Grok 3 Mini being deprecated?
Azure AI Foundry deprecated azure_ai/grok-3-mini on May 1, 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
- www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing
LiteLLM docs: Azure AI Foundry, Oracle Cloud (OCI), Vercel AI Gateway.
Provider pages: Azure AI Foundry, Oracle Cloud (OCI), Vercel AI Gateway.
