Grok 4 vs Grok 4.3
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by xAI
|
by xAI
|
|---|---|---|
| Overview | ||
| Status | Retired flagship | Current flagship |
| Released | Jul 9, 2025 | Apr 30, 2026 |
| Pricing per million tokens | ||
| Input | $3.00/Mtok | $1.25/Mtok |
| Output | $15.00/Mtok | $2.50/Mtok |
| Blended avg | $6.00/Mtok | $1.56/Mtok |
| Specifications | ||
| Context window | 256K tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks sources: Vellum LLM Leaderboard / xAI model card, Artificial Analysis | ||
| Avg benchmark score | 63 | 72.4 |
| Perf / dollar | 10.5 | 46.3 |
| GPQA Diamond | 87.5 | 80 |
| SWE-Bench Verified | 55 | 65 |
| Humanity's Last Exam | 25.4 | 38 |
| ARC-AGI 2 | 16 | 42 |
| AIME 2025 | 91.7 | 85 |
| MMMLU | 82 | 86 |
| BFCL | 72 | 78 |
| HumanEval | 75 | 90 |
| MATH 500 | 82 | 88 |
| Terminal-Bench 2.1 | 27.2 | — |
| LiveCodeBench | 79 | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| LMSYS Chatbot Arena | 1409.3 ELO | 1441.5 ELO |
| AA Intelligence Index | — | 37.9 |
| AA Agentic Index | — | 24.2 |
| AA-Omniscience Index (−100–100) | — | 18 |
| Providers | ||
| Available from |
xAI — $3.00/$15.00/Mtok
|
xAI — $1.25/$2.50/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Grok 4 | Grok 4.3 | Savings |
|---|---|---|---|
| 1M tokens | $6 | $1.56 | $4.44 (74%) |
| 10M tokens | $60 | $15.63 | $44.38 (74%) |
| 100M tokens | $600 | $156.25 | $443.75 (74%) |
| 1000M tokens | $6000 | $1562.5 | $4437.5 (74%) |
When to pick which
distilled from the pricing and spec data above- this pairing gives Grok 4 no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
- cost dominates: $1.56/Mtok blended vs $6.00 — 74% less on the same 50/50 token mix
- you need the longer context: 1M tokens vs 256K (3.9×)
- raw capability matters more than price: 72.4 vs 63 average benchmark score
The cheaper option here — Grok 4.3 costs $1.56/Mtok blended on xAI.
Summary
Grok 4 by xAI costs $3.00/Mtok input and $15.00/Mtok output, with a 256K-token context window. It supports text, image input.
Grok 4.3 by xAI costs $1.25/Mtok input and $2.50/Mtok output, with a 1M-token context window. It supports text, image input.
On a blended cost basis, Grok 4.3 is 74% cheaper than Grok 4.It also has a larger context window.
On benchmarks, Grok 4.3 scores higher (72.4 vs 63) on average. In terms of value, Grok 4.3 has better performance per dollar (46.3 vs 10.5).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.