xAI's flagship reasoning model for agentic tool calling, instruction following, and multimodal text generation.
Specifications
Context
1000K
Maximum Output
128K
Inputtext, image
Outputtext
Performance (7-day Average)
Collecting…
Collecting…
Collecting…
Pricing
< 200K
Input$1.375/MTokens
Cached Input$0.22/MTokens
Output$2.75/MTokens
200K+
Input$2.75/MTokens
Cached Input$0.44/MTokens
Output$5.50/MTokens
Availability Trend (24h)
Performance Metrics (24h)
Similar Models
$0.22/$0.55/M
ctx2.0Mmax128Kavail—tps—
InOutCap
A frontier multimodal model with built-in reasoning for fast agentic workflows and tool use.
$0.22/$0.55/M
ctx2.0Mmax128Kavail—tps—
InOutCap
A frontier multimodal model optimized for fast tool use, structured outputs, and low-latency workflows.
$1.375/$2.75/M
ctx1.0Mmax128Kavail—tps—
InOutCap
A reasoning-enabled Grok 4.20 snapshot for long-context multimodal problem solving.
$1.375/$2.75/M
ctx1.0Mmax128Kavail—tps—
InOutCap
A non-reasoning Grok 4.20 snapshot for fast multimodal chat, tool use, and structured outputs.