Saltar al contenido principal

xAIAdded Mar 12, 2026Private

Grok 4.20

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

grok-4-20POST https://api.venice.ai/api/v1/chat/completions
Input / output
$1.42 / $2.83
per 1M tokens
Context
2M
128K max output
Reasoning
On
fixed effort
Cached input
$0.23
84% off input
Modalities
Text, image
out: text

Pricing

USD per 1M tokens
Input
$1.42
$2.83 above 200K
Cached input
$0.23
$0.45 above 200K
Output incl. reasoning
$2.83
$5.67 above 200K
Similar modelsInputOutputOutput price, relative
Grok 4.20$1.42$2.83
GPT-5.4 Mini$0.75$4.50
GLM 5 Turbo$1.20$4.00
Qwen 3.5 397B$0.75$4.50
GLM 5$1.00$3.20

Prompt caching is automatic; see Prompt caching.

Specs

Model ID
grok-4-20
Endpoint
POST /api/v1/chat/completions
Context window
2,000,000 tokens
Max output
128,000 tokens
Reasoning effort
On at a fixed effort; send "reasoning": { "enabled": false } to turn it off where the model allows · guide
Served precision
Not disclosed
Added
Mar 12, 2026

Capabilities

Modalities
Text
Input and output
Image
Input only · up to 10
Audio
Not supported
Video
Not supported
Features
Streaming (SSE)
Supported
Function calling
Supported
Structured output (json_schema)
Supported
Reasoning effort
Not adjustable
Prompt caching
Supported
Web search
venice_parameters
X search
venice_parameters
Log probabilities
Not supported
Fine-tuning
Not supported
Image generation
Not supported
POST/api/v1/chat/completionsRecommended
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." }]
}'

Privacy

Tier 1
Anonymized

Included

Tier 2 · this model
Private

Zero data retention, enforced by contract. Prompts and outputs aren’t stored.

Tier 3
TEE

Not available

Tier 4
End-to-end encrypted

Not available