About
Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
Related Models
Pricing
Input
$1.25
per 1M tokens
Output
$2.50
per 1M tokens
Blended
$1.56
per 1M tokens
Cheaper than 28% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.56
Monthly
$46.88
vs. Similar Models
Qwen: Qwen3.6 27BQ:+0.1
$0.79-49%
DeepSeek V4 Flash (Reasoning, High Effort)Q:+0.4
$0.17-89%
Grok 4.20 0309 (Reasoning)Q:-0.5
$3.00+92%
xAI: Grok 4.3Q:+0.6
$1.560%
Performance
234
tokens/sec
Faster than 93% of models
11.58
seconds
Faster than 11% of models
11.58
seconds
Faster than 38% of models
Market Median
94 tok/s
148% faster
Median TTFT
1.11s
941% slower
Throughput/Dollar
150
tok/s per $/1M
Speed Comparison
OpenAI: gpt-oss-20b
232 tok/s-1%
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
232 tok/s-1%
LFM2.5-8B-A1B
231 tok/s-1%
Context Window
2.0M
tokens
Larger than 98% of models
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
91.1%
HLE
32.2%
LiveCodeBenchNot evaluated
SciCode
45.6%
TerminalBench Hard
37.9%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
81.2%
Long Context Recall
58.0%
Tau2
93.0%
Market AverageTop Score