Grok 4.20 Non-Reasoning

Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adhe…

vercelAIGatewayCatalog/spacexai/grok-4.20-non-reasoning

Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.

Specifications & capabilities

Input
text, image, pdf
Output
text
Context window · tokens
2000000
Max output · tokens
2000000
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Published prices

21–23 / 23

spacexai/grok-4.20-non-reasoning ↗

$2.50

Inference provider
vercelAIGatewayCatalog
Platform
xai
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
xai | spacexai/grok-4.20-non-reasoning
model_type
language
billing_scope
via Vercel AI Gateway
context_tokens
max_exclusive
200001
min_inclusive
0
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

spacexai/grok-4.20-non-reasoning ↗

$5.00

Inference provider
vercelAIGatewayCatalog
Platform
xai
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
xai | spacexai/grok-4.20-non-reasoning
model_type
language
service_tier
priority
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

spacexai/grok-4.20-non-reasoning ↗

$0.01

Inference provider
vercelAIGatewayCatalog
Platform
xai
Unit
request
Currency
USD
Billing conditions
charge
web_search
endpoint
xai | spacexai/grok-4.20-non-reasoning
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Web search
Pricing via
Vercel AI Gateway

Provider specifications & access

1–1 / 1

Grok 4.20 Non-Reasoning ↗

source model id
spacexai/grok-4.20-non-reasoning
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
2000000
max output tokens
2000000
architecture
input_modalities
  • text
  • image
  • pdf
output_modalities
  • text
capabilities
  • promptCaching
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

14 / 100

source id
stanfordFMTI
canonical model id
vercelAIGatewayCatalog/spacexai/grok-4.20-non-reasoning
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
xAI
assessment type
organization-level disclosure
metric
disclosure_score
result label
14 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Source specification observations

1–2 / 2

vercelAIGatewayCatalog ↗

field
context_length
value
2000000
normalized value
2000000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
2000000
normalized value
2000000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

Original sources

1–3 / 3

Vercel AI Gateway · Model page ↗

GitHub · Catalog ↗

Vercel AI Gateway · Catalog ↗

Source links

1–2 / 2

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace