What this model supports
ReasoningYes
Tool callingYes
Structured outputYes
AttachmentsYes
Temperature controlYes
Open weightsNo
- Creator
- xAI
- Family
- grok
- Modalities
- Image, Pdf, Text
- License
- Not documented
- Release date
- 2026-04-17
- Model ID
xai/grok-4.3
Grok 4.3
xai/grok-4.3xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk
Source-linkedgrokClosed weightsReleased 2026-04-17
Context window1M
Maximum output30K
Provider offers16
Knowledge cutoffUndisclosed
Market availability
Report price →Provider pricing
| Provider | Provider model ID | Context | Input / 1M | Output / 1M | Cached / 1M | Features | All pricing |
|---|---|---|---|---|---|---|---|
 Kenari | grok-4-3 | 1M | $0.000 | $0.000 | — | R T S | View{
"input": 0,
"output": 0
} |
 AnyAPI | xai/grok-4.3 | 1M | — | — | — | R T S | View{} |
 Vercel AI Gateway | xai/grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"input": 1.25,
"output": 2.5
} |
 xAI | grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"context_over_200k": {
"cache_read": 0.4,
"input": 2.5,
"output": 5
},
"input": 1.25,
"output": 2.5,
"tiers": [
{
"cache_read": 0.4,
"input": 2.5,
"output": 5,
"tier": {
"size": 200000,
"type": "context"
}
}
]
} |
 Auriko | grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"context_over_200k": {
"cache_read": 0.4,
"input": 2.5,
"output": 5
},
"input": 1.25,
"output": 2.5,
"tiers": [
{
"cache_read": 0.4,
"input": 2.5,
"output": 5,
"tier": {
"size": 200000,
"type": "context"
}
}
]
} |
 ZenMux | x-ai/grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"cache_write": 0,
"context_over_200k": {
"cache_read": 0.4,
"cache_write": 0,
"input": 2.5,
"output": 5
},
"input": 1.25,
"output": 2.5,
"tiers": [
{
"cache_read": 0.4,
"cache_write": 0,
"input": 2.5,
"output": 5,
"tier": {
"size": 200000,
"type": "context"
}
}
]
} |
 FastRouter | x-ai/grok-4.3 | 1M | $1.250 | $2.500 | — | R T S | View{
"input": 1.25,
"output": 2.5
} |
 OpenRouter | x-ai/grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"context_over_200k": {
"cache_read": 0.4,
"input": 2.5,
"output": 5
},
"input": 1.25,
"output": 2.5,
"tiers": [
{
"cache_read": 0.4,
"input": 2.5,
"output": 5,
"tier": {
"size": 200000,
"type": "context"
}
}
]
} |
 AIHubMix | grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"context_over_200k": {
"cache_read": 0.4,
"input": 2.5,
"output": 5
},
"input": 1.25,
"output": 2.5,
"tiers": [
{
"cache_read": 0.4,
"input": 2.5,
"output": 5,
"tier": {
"size": 200000,
"type": "context"
}
}
]
} |
 Merge Gateway | xai/grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"context_over_200k": {
"cache_read": 0.4,
"input": 2.5,
"output": 5
},
"input": 1.25,
"output": 2.5,
"tiers": [
{
"cache_read": 0.4,
"input": 2.5,
"output": 5,
"tier": {
"size": 200000,
"type": "context"
}
}
]
} |
 OrcaRouter | grok/grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"context_over_200k": {
"cache_read": 0.4,
"input": 2.5,
"output": 5
},
"input": 1.25,
"output": 2.5,
"tiers": [
{
"cache_read": 0.4,
"input": 2.5,
"output": 5,
"tier": {
"size": 200000,
"type": "context"
}
}
]
} |
 LLM Gateway | grok-4-3 | 1M | $1.250 | $2.500 | $0.312 | R T S | View{
"cache_read": 0.3125,
"context_over_200k": {
"cache_read": 0.4,
"input": 2.5,
"output": 5
},
"input": 1.25,
"output": 2.5,
"tiers": [
{
"cache_read": 0.4,
"input": 2.5,
"output": 5,
"tier": {
"size": 200000,
"type": "context"
}
}
]
} |
 Abacus | grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"input": 1.25,
"output": 2.5
} |
 Amazon Bedrock | xai.grok-4.3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"input": 1.25,
"output": 2.5
} |
 FrogBot | grok-4-3 | 1M | $1.250 | $2.500 | $0.200 | R T S | View{
"cache_read": 0.2,
"input": 1.25,
"output": 2.5
} |
 Venice AI | grok-4-3 | 1M | $1.420 | $2.830 | $0.230 | R T S | View{
"cache_read": 0.23,
"context_over_200k": {
"cache_read": 0.45,
"input": 2.83,
"output": 5.67
},
"input": 1.42,
"output": 2.83,
"tiers": [
{
"cache_read": 0.45,
"input": 2.83,
"output": 5.67,
"tier": {
"size": 200000,
"type": "context"
}
}
]
} |
Published benchmark results
Artificial Analysis Intelligence Index
vs top 5 models
GDPval-AA
vs top 5 models
IFBench
vs top 2 models
τ²-Bench Telecom
vs top 3 models