Grok 3 API Pricing
As of October 10, 2026, Grok 3 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens from Oracle Cloud (OCI), the lowest of 3 providers. It has a 131,072-token context window and returns up to 131,072 tokens per response.
- Input
- $3.00 / 1M tokens
- Output
- $15.00 / 1M tokens
- Context window
- 131,072 tokens
- Max output
- 131,072 tokens
- Providers
- 3
- Added to LiteLLM
- May 2025
Grok 3 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 |
|---|---|---|---|---|
| Oracle Cloud (OCI) | oci/xai.grok-3 | $3.00 | $15.00 | 128K |
| Azure AI Foundry | azure_ai/grok-3 | $3.00 | $15.00 | – |
| Vercel AI Gateway | vercel_ai_gateway/xai/grok-3 | $3.00 | $15.00 | 128K |
What Grok 3 costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Oracle Cloud (OCI) | $13.50 |
| Azure AI Foundry | $13.50 |
| Vercel AI Gateway | $13.50 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Oracle Cloud (OCI) | $33.00 |
| Azure AI Foundry | $33.00 |
| Vercel AI Gateway | $33.00 |
Grok 3 features
- Function calling
- Structured output
Use Grok 3 with LiteLLM
Call Grok 3 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="oci/xai.grok-3",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: grok-3
litellm_params:
model: oci/xai.grok-3
# 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",
"messages": [{"role": "user", "content": "Hello!"}]
}'Grok 3 FAQ
How much does Grok 3 cost?
Grok 3 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens from Oracle Cloud (OCI), the lowest of 3 providers.
What is the context window of Grok 3?
Grok 3 has a 131,072-token context window and returns up to 131,072 tokens per response.
Which providers offer Grok 3?
Grok 3 is available from 3 providers through LiteLLM: Oracle Cloud (OCI), Azure AI Foundry and Vercel AI Gateway.
How do I call Grok 3 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="oci/xai.grok-3", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Grok 3 support?
Grok 3 supports function calling. It does not support structured output.
When did LiteLLM add Grok 3?
Grok 3 was added to LiteLLM's model price file in May 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
LiteLLM docs: Oracle Cloud (OCI), Azure AI Foundry, Vercel AI Gateway.
Provider pages: Oracle Cloud (OCI), Azure AI Foundry, Vercel AI Gateway.
