Grok 4.3 vs Grok 4.6
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by xAI
|
by xAI
|
|---|---|---|
| Overview | ||
| Status | Current flagship | Current flagship |
| Released | Apr 30, 2026 | Aug 12, 2026 |
| Pricing per million tokens | ||
| Input | $1.25/Mtok | $2.00/Mtok |
| Output | $2.50/Mtok | $6.00/Mtok |
| Blended avg | $1.56/Mtok | $3.00/Mtok |
| Cached input | — | $0.500/Mtok |
| Specifications | ||
| Context window | 1M tokens | 500K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks sources: xAI model card, Artificial Analysis / Artificial Analysis | ||
| Independent composite scores measured for both models — each on its own scale | ||
| AA Intelligence Index | 37.9 | 60.9 |
| AA Agentic Index | 24.2 | 58.7 |
| AA-Omniscience Index (−100–100) | 18 | 30.5 |
| LMSYS Chatbot Arena | 1441.5 ELO | 1463.6 ELO |
| GDPval-AA v2 | — | 1749.2 ELO |
| Per-benchmark results published for Grok 4.3 only — no independent per-benchmark scores exist for Grok 4.6 yet | ||
| Avg benchmark score | 72.4 | — |
| Perf / dollar | 46.3 | — |
| GPQA Diamond | 80 | — |
| SWE-Bench Verified | 65 | — |
| Humanity's Last Exam | 38 | — |
| ARC-AGI 2 | 42 | — |
| AIME 2025 | 85 | — |
| MMMLU | 86 | — |
| BFCL | 78 | — |
| HumanEval | 90 | — |
| MATH 500 | 88 | — |
| Providers | ||
| Available from |
xAI — $1.25/$2.50/Mtok
|
xAI — $2.00/$6.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Grok 4.3 | Grok 4.6 | Savings |
|---|---|---|---|
| 1M tokens | $1.56 | $3 | $1.44 (48%) |
| 10M tokens | $15.63 | $30 | $14.38 (47.9%) |
| 100M tokens | $156.25 | $300 | $143.75 (47.9%) |
| 1000M tokens | $1562.5 | $3000 | $1437.5 (47.9%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $1.56/Mtok blended vs $3.00 — 47.9% less on the same 50/50 token mix
- you need the longer context: 1M tokens vs 500K (2×)
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.500/Mtok — 75% off its list input price, a discount Grok 4.3 doesn't offer
The cheaper option here — Grok 4.3 costs $1.56/Mtok blended on xAI.
Summary
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.
Grok 4.6 by xAI costs $2.00/Mtok input and $6.00/Mtok output, with a 500K-token context window. It supports text, image input.
On a blended cost basis, Grok 4.3 is 47.9% cheaper than Grok 4.6.It also has a larger context window.
The two aren't directly comparable on average benchmark score: Grok 4.3 has published per-benchmark results, while Grok 4.6 does not yet — it is measured today on independent composites (see the table above).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.