LiteLLMModels

Databricks Grok 4.6 API Pricing

As of October 10, 2026, Databricks Grok 4.6 costs $2.50 per 1M input tokens and $7.50 per 1M output tokens on Databricks, with cache reads at $0.625 and cache writes at $2.50 per 1M tokens. It has a 500,000-token context window.

Model ID databricks/databricks-grok-4-6Prices updated Checked
Input
$2.50 / 1M tokens
Output
$7.50 / 1M tokens
Cache read
$0.625 / 1M tokens
Context window
500,000 tokens
Providers
1
Added to LiteLLM
September 4, 2026

Databricks Grok 4.6 pricing by provider

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

ProviderModel name in LiteLLMInputOutputCache readCache writeContext
Databricksdatabricks/databricks-grok-4-6$2.50$7.50$0.625$2.50500K

What Databricks Grok 4.6 costs in practice

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

Databricks$8.75

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

Databricks$26.50

Databricks Grok 4.6 features

Input: text. Output: text.

Use Databricks Grok 4.6 with LiteLLM

Call Databricks Grok 4.6 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="databricks/databricks-grok-4-6",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: databricks-grok-4-6
    litellm_params:
      model: databricks/databricks-grok-4-6
      # 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": "databricks-grok-4-6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Databricks Grok 4.6 FAQ

How much does Databricks Grok 4.6 cost?

Databricks Grok 4.6 costs $2.50 per 1M input tokens and $7.50 per 1M output tokens on Databricks, with cache reads at $0.625 and cache writes at $2.50 per 1M tokens.

What is the context window of Databricks Grok 4.6?

Databricks Grok 4.6 has a 500,000-token context window.

Which providers offer Databricks Grok 4.6?

Databricks Grok 4.6 is available from Databricks through LiteLLM, using the model name databricks/databricks-grok-4-6.

How do I call Databricks Grok 4.6 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="databricks/databricks-grok-4-6", 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 Databricks Grok 4.6 support?

Databricks Grok 4.6 supports function calling, reasoning and prompt caching. It does not support image input.

When did LiteLLM add Databricks Grok 4.6?

Databricks Grok 4.6 was added to LiteLLM's model price file on September 4, 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: Databricks.

Provider pages: Databricks.