Grok 4.3 (batch)
by xAI · x-ai/grok-4.3:batch · #254 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$1.00
per 1M tokens
Output
$2.00
per 1M tokens
Blended (3:1)
$1.25
3 input : 1 output
Cache read
$0.16
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Grok 4.3 (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.25 | $0.104 | — |
| 50% | $0.935 | $0.062 | −40% |
| 90% | $0.683 | $0.0284 | −73% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.0011 | $1.10 |
| Document summary | 8,000 | 1,000 | $0.01 | $10.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.034 | $34.00 |
| Long-context analysis | 150,000 | 5,000 | $0.16 | $160.00 |
Performance
Intelligence Index
25.4
AA composite quality
Coding Index
42.2
Math Index
—
Agentic Index
17.2
Output speed
0 tok/s
median
Time to first token
0s
median
Time to first answer
0s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 90.1% |
| Humanity's Last Exam | 37.2% |
| SciCode | 48.3% |
| IFBench | 81.3% |
| AA-LCR (Long Context Reasoning) | 73.0% |
| Terminal-Bench Hard | 37.9% |
| Terminal-Bench 2.1 | 39.7% |
| τ²-Bench (Telecom) | 97.7% |
| τ³-Bench Banking | 12.4% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,207 |
| Web apps | 1,144 |
| Full-stack | 1,017 |
| Mobile apps | 1,091 |
| Android native | 972 |
| UI components | 1,206 |
| Data viz | 1,196 |
| SVG | 1,109 |
| 3D | 1,154 |
| Game dev | 1,198 |
| Agentic game dev | 1,007 |
| Godot game dev | 1,035 |
| HTML slides | 1,011 |
| PPTX slides | 1,071 |
| Python→PPTX slides | 1,072 |
| Agentic slides | 1,072 |
| Agentic HTML slides | 1,066 |
| Agentic slides (HTML) | 1,066 |
| Agentic slides (Python PPTX) | 1,068 |
| Code categories | 1,202 |
| ASCII art | 1,158 |
Specs
Context window
1M
tokens
Max output
900K
tokens
Input modalities
text, image, file
Tokenizer
Grok