LiteLLMModels

Grok 4.20 Non Reasoning API Pricing

As of October 10, 2026, Grok 4.20 Non Reasoning costs $1.25 per 1M input tokens and $2.50 per 1M output tokens on xAI, with cache reads at $0.20 per 1M tokens. Across 5 providers on LiteLLM, the input price ranges from $1.25 to $2.00. It has a 1,000,000-token context window and returns up to 1,000,000 tokens per response.

By xAIModel ID xai/grok-4.20-non-reasoningPrices updated Checked
Input
$1.25 / 1M tokens
Output
$2.50 / 1M tokens
Cache read
$0.20 / 1M tokens
Context window
1,000,000 tokens
Max output
1,000,000 tokens
Providers
5
Added to LiteLLM
May 2026

Grok 4.20 Non Reasoning pricing by provider

6 listings across 5 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readBatch inBatch outContext
xAIxai/grok-4.20-non-reasoning$1.25$2.50$0.20$1.00$2.001M
xAIlatest aliasxai/grok-4.20-non-reasoning-latest$1.25$2.50$0.20$1.00$2.001M
AIHubMixaihubmix/grok-4-20-non-reasoning$2.00$6.00$0.20––1M
Azure AI Foundryazure_ai/grok-4-20-non-reasoning$1.25$2.50$1.25––262K
Google Vertex AIvertex_ai/xai/grok-4.20-non-reasoning$1.25$2.50$0.20––2M
Perplexityperplexity/xai/grok-4.20-non-reasoning$1.25$2.50$0.20–––

Other Grok 4.20 Non Reasoning prices on xAI

Input above 200K tokens$2.50 per 1M tokens
Output above 200K tokens$5.00 per 1M tokens
Cache read above 200K tokens$0.40 per 1M tokens

What Grok 4.20 Non Reasoning costs in practice

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

xAI$3.75
Azure AI Foundry$3.75
Google Vertex AI$3.75
Perplexity$3.75
xAI batch$3.00

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

xAI$13.00
Azure AI Foundry$13.00
Google Vertex AI$13.00
Perplexity$13.00

Grok 4.20 Non Reasoning features

Use Grok 4.20 Non Reasoning with LiteLLM

Call Grok 4.20 Non Reasoning 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="xai/grok-4.20-non-reasoning",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: grok-4.20-non-reasoning
    litellm_params:
      model: xai/grok-4.20-non-reasoning
      api_key: os.environ/XAI_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": "grok-4.20-non-reasoning",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Grok 4.20 Non Reasoning FAQ

How much does Grok 4.20 Non Reasoning cost?

Grok 4.20 Non Reasoning costs $1.25 per 1M input tokens and $2.50 per 1M output tokens on xAI, with cache reads at $0.20 per 1M tokens. Batch requests cost $1.00 per 1M input tokens and $2.00 per 1M output tokens. Above 200K input tokens, input costs $2.50 and output costs $5.00 per 1M tokens. Across 5 providers on LiteLLM, the input price ranges from $1.25 to $2.00.

What is the context window of Grok 4.20 Non Reasoning?

Grok 4.20 Non Reasoning has a 1,000,000-token context window and returns up to 1,000,000 tokens per response.

Which providers offer Grok 4.20 Non Reasoning?

Grok 4.20 Non Reasoning is available from 5 providers through LiteLLM: xAI, AIHubMix, Azure AI Foundry, Google Vertex AI and Perplexity. The lowest price is on xAI.

How do I call Grok 4.20 Non Reasoning with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="xai/grok-4.20-non-reasoning", 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 4.20 Non Reasoning support?

Grok 4.20 Non Reasoning supports function calling, structured output, image input, reasoning, prompt caching and web search.

When did LiteLLM add Grok 4.20 Non Reasoning?

Grok 4.20 Non Reasoning was added to LiteLLM's model price file in May 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: xAI, AIHubMix, Azure AI Foundry, Google Vertex AI, Perplexity.

Provider pages: xAI, AIHubMix, Azure AI Foundry, Google Vertex AI, Perplexity.