Skip to main content
xAIMar 12, 2026

Grok 4.20

grok-4-20Private

Grok 4.20 is xAI’s multimodal reasoning model with strong tool use, structured output support, and a 2M-token context window.

$1.42/$2.83
per 1M in / out
2M
context window
128K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 78%91.9%
Blended pricecheaper than 49%$1.77
Context windowlarger than 99%2M
Max outputlarger than 55%128K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InTextImage
OutText

Not supportedvideo input, audio input and log probabilities

Benchmarks

GPQA Diamond
91.9%29th of 139 · Pareto scores higher for less

Specs

Model ID
grok-4-20
Endpoint
POST /api/v1/chat/completions
Context window
2,000,000 tokens
Max output
128,000 tokens
Reasoning
Always on
Precision
Not disclosed
Privacy
Private
Weights
Closed
Added
Mar 12, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Grok 4.20$1.42$2.8391.9%2M128K——
GPT-5.4 Mini$0.75$4.5082.8%400K128K——
GLM 5 Turbo$1.20$4.0079.3%200K32K——
Qwen 3.5 397B$0.75$4.5055.4%128K32K——
GLM 5$1.00$3.2084.3%198K32K——

Other versions

  1. Grok 4.20Mar 2026
  2. Grok 4.3Apr 2026
  3. Grok 4.5Jul 2026
  4. Grok 4.6Aug 2026
  5. Grok 4.7Sep 2026

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$1.42per 1M tokens
Cached input$0.2384% off input
Output$2.83per 1M tokens

Estimate a workload

$0.0043per request
$42.55for 10,000 requests

Blended price against similar models

Grok 4.20$1.77
GLM 5$1.55

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice 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." }]
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelgrok-4-20Required
messagestext · image_urlContent parts the model reads
max_completion_tokensUp to 128,000Counts reasoning tokens
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations
venice_parameters.enable_x_searchtrue | falsePosts from X