Grok 4.20 API

Grok 4.20 is a large language model by xAI, available on the Venice API as grok-4-20. It runs privately, with zero data retention.Grok 4.20 is xAI’s latest multimodal reasoning model with strong tool use, structured output support, and a 2M-token context window.

Grok 4.20 API pricing

Model ID	Variant	Privacy	Price
`grok-4-20`	Standard	Private	$1.42 input /$ 2.83 output per 1M tokens

Grok 4.20 specifications

Spec	Value
Provider	xAI
Released	Mar 12, 2026
Privacy	Private
Context window	2M tokens
Max output	125K tokens
Reasoning effort	Not adjustable

How to use the Grok 4.20 API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "grok-4-20" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4-20",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'

Grok 4.20 API FAQ

How much does the Grok 4.20 API cost?

1.42 per 1M input tokens and

2.83 per 1M output tokens, with cached input at $0.23 per 1M. Prices are in USD and can be paid in DIEM at parity.

What is the Grok 4.20 model ID?

Use grok-4-20 as the model parameter.

Is the Grok 4.20 API private?

Grok 4.20 is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

What is the context window of Grok 4.20?

2M tokens of context, with up to 125K output tokens per response.

What does Grok 4.20 support?

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

Which endpoint does the Grok 4.20 API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

Grok 4.7 API: $2.27 input /$ 6.80 output per 1M tokens
Grok 4.6 API: $2.27 input /$ 6.80 output per 1M tokens
Grok 4.5 API: $2.27 input /$ 6.80 output per 1M tokens
Grok 4.3 API: $1.42 input /$ 2.83 output per 1M tokens
GLM 5 Turbo API: $1.20 input /$ 4.00 output per 1M tokens
Qwen 3.5 397B API: $0.75 input /$ 4.50 output per 1M tokens
GLM 5 API: $1.00 input /$ 3.20 output per 1M tokens
GPT-5.4 Mini API: $0.94 input /$ 5.63 output per 1M tokens

Explore

By modality