SpaceXAI's Grok 4.20 flagship release with tool calling, multimodal input support, and a 2M-token context window. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.
Added Mar 31, 2026
Context Window
2.0M
Max Output
131.1K
Avg output tokens (7d)
1.5K tokens
Input Price (Auto)
$2.10/1M
Output Price (Auto)
$6.30/1M
Cache Read (Auto)
$1.05/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
37.0
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
91.1%
Better than 97% of models compared
HLE
Humanity's Last Exam
32.2%
Better than 94% of models compared
IFBench
Instruction-following benchmark
81.2%
Better than 99% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
93.0%
Better than 89% of models compared
AA-LCR
Long context reasoning evaluation
58.0%
Better than 72% of models compared
Coding
SciCode
Python programming for scientific computing
45.6%
Better than 90% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
37.9%
Better than 86% of models compared
Last updated Jun 28, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare Grok 4.20 with similar models from the same provider or model family.
Grok 4.6
x-ai/grok-4.6Grok 4.6 is SpaceXAI's frontier reasoning model for coding, knowledge work, and STEM. It supports text, image, and file inputs with tool calling and structured outputs. Reasoning is always active, and requests above 200k input tokens use higher long-context rates. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.
Grok 4.5
x-ai/grok-4.5Grok 4.5 is SpaceXAI's frontier reasoning model for coding, knowledge work, and STEM. It supports text, image, and file inputs with tool calling and structured outputs. Reasoning is always active. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.
Grok Build 0.1
x-ai/grok-build-0.1Grok Build 0.1 is SpaceXAI's fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. Currently in early access. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.
Grok Latest
x-ai/grok-latestCompatibility alias that routes to the newest Grok model. Currently routes to Grok 4.6. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.
Grok 4.3
x-ai/grok-4.3Grok 4.3 is SpaceXAI's reasoning model for text and image inputs, built for agentic workflows, instruction following, factual accuracy, long-document analysis, and deep research. Reasoning is always active and requests above 200k total tokens are charged at the higher long-context rate. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.
Grok 4.20 Multi-Agent
x-ai/grok-4.20-multi-agentGrok 4.20 Multi-Agent is tuned for collaborative agentic workflows while keeping the same 2M-token context window and multimodal support. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.