ModelBench
xAI logo
Models/xAI

Grok 4.3

xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk

Source-linked grok Closed weights Released 2026-04-17
API data Report
Input modalitiesT
Output modalitiesT
Input price$1.25/1M tokens
Output price$2.5/1M tokens
Context window1M
Max output30K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
✓ Structured output Yes
✓ Attachments Yes
✓ Vision input Yes
× Open weights No
Creator
xAI
Model family
grok
Knowledge cutoff
Not documented
License
Not documented
Release date
2026-04-17
Model ID
xai/grok-4.3
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering Grok 4.3
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
AnyAPI xai/grok-4.3 1M Not listed Not listed - ReasoningToolsJSON Docs
Kenari grok-4-3 1M Not listed Not listed - ReasoningToolsJSON Docs
Vercel AI Gateway xai/grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
xAI grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
Auriko grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
ZenMux x-ai/grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
Merge Gateway xai/grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
OrcaRouter grok/grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
LLM Gateway grok-4-3 1M $1.25 $2.5 $0.312 ReasoningToolsJSON Docs
Abacus grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
DaoXE grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
Amazon Bedrock xai.grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
FrogBot grok-4-3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
OpenRouter x-ai/grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
FastRouter x-ai/grok-4.3 1M $1.25 $2.5 - ReasoningToolsJSON Docs
AIHubMix grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
CrossModel x-ai/grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
Ofox x-ai/grok-4.3 1M $1.25 $2.5 $0.2 ReasoningToolsJSON Docs
Venice AI grok-4-3 1M $1.42 $2.83 $0.23 ReasoningToolsJSON Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
Artificial Analysis Intelligence Index - 4.0 - index scoreTop 1 reported models
Grok 4.3
53.0
GDPval-AA - Unversioned - EloTop 4 reported models
Claude Fable 5
1932.0
Gemini 3.5 Flash
1656.0
Grok 4.3
1500.0
Gemini 3.1 Pro Preview
1314.0
IFBench - Unversioned - accuracyTop 2 reported models
Nemotron 3 Ultra 550B A55B
81.7
Grok 4.3
81.0
τ²-Bench Telecom - Unversioned - success rateTop 3 reported models
Grok 4.3
98.0
GPT-5.5
98.0
North Mini Code
37.0
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
No recent changes detected

This record has not changed in the retained import history.

Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/xai/grok-4.3
curl
curl "https://www.modelbench.lol/api/v1/models/xai/grok-4.3"