Context
1M
Max output
1M
Serving providers
1
Cheapest input
$1.25 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
113 t/s
tokens / second
Time to first token
17.26s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AA-Briefcase | 13% | — | — | |||||||||||||||||||||
| APEX Agents | 17% | default | — | |||||||||||||||||||||
| CritPt | 8% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| GDPval | 1096.0 | reasoning: false | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| GPQA Diamond | 90% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Humanity's Last Exam | 35% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| IFBench | 83% | medium | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| IT-Bench SRE | 33% | default | — | |||||||||||||||||||||
| Long-Context Reasoning | 65% | medium | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| MMMU-Pro | 78% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Omniscience | 18.3 | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| SciCode | 47% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| TerminalBench Hard | 38% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| TerminalBench v2.1 | 40% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| τ-bench Banking | 12% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
| τ²-bench | 98% | default | — | |||||||||||||||||||||
| ||||||||||||||||||||||||
Pricing detail
cost beyond the standard rate · source: models.devLong context (>200K)
$2.83 / $5.67
input / output · per 1M
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| xAICheapest | $1.25 | $2.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$450
estimated / month
Model IDs
copy the exact identifier for your platformxai/grok-4.3
Frequently asked questions
Grok 4.3 pricing, context and availabilityHow much does Grok 4.3 cost?
Grok 4.3 costs $1.25 per 1M input tokens and $2.50 per 1M output tokens at its cheapest provider via xAI.
What is the context window of Grok 4.3?
Grok 4.3 accepts up to 1M tokens of context and can return up to 1M output tokens.
What can Grok 4.3 do?
Grok 4.3 supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other xAI models
compare pricing across the xAI lineupGrok 4$3.00/1M · 5 providersGrok 4.1 Fast Non Reasoning$0.20/1M · 3 providersGrok 4.1 Fast Reasoning$0.20/1M · 3 providersGrok 3 Mini$0.25/1M · 3 providersGrok 3$3.00/1M · 3 providersGrok 4 Fast Non Reasoning$0.20/1M · 2 providersGrok 4 Fast Reasoning$0.20/1M · 2 providersGrok Code Fast 1$0.20/1M · 2 providers
Popular comparisons
head-to-head pages featuring Grok 4.3
Grok 4.3 vs Claude Fable 5side-by-side pricing & benchmarks Grok 4.3 vs Claude Opus 4.8side-by-side pricing & benchmarks Grok 4.3 vs Claude Sonnet 5side-by-side pricing & benchmarks
Grok 4.3 vs DeepSeek V4 Proside-by-side pricing & benchmarks
Grok 4.3 vs Gemini 3.1 Pro Previewside-by-side pricing & benchmarks Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI