Grok 4.6 Xhigh vs MiniMax-M3.1-Flash compared

If you only looked at the intelligence index, Grok 4.6 (Xhigh) and MiniMax-M3.1-Flash would be hard to tell apart. Cost is where they split the most, with MiniMax-M3.1-Flash working out at about 9% of Grok 4.6 Xhigh's blended rate. Everything below is read from the benchmark, price and speed data in Franklin AI's catalogue; nothing here comes from a hands-on test.

Token pricing and a sample bill

Grok 4.6 Xhigh lists $2.00 per million input tokens and $6.00 per million output tokens; MiniMax-M3.1-Flash lists $0.15 and $0.60. Grok 4.6 Xhigh costs 10 times as much per output token.

Take 1 million input tokens and 200,000 output tokens: that comes to $3.20 on Grok 4.6 Xhigh and $0.27 on MiniMax-M3.1-Flash. For an agent that reads 50 million tokens and writes 5 million in a month, MiniMax-M3.1-Flash would come in 92% lower: $130 for Grok 4.6 Xhigh against $10.50 for MiniMax-M3.1-Flash. Blended at three input tokens per output token, the effective rates are $3.00 for Grok 4.6 Xhigh and $0.262 for MiniMax-M3.1-Flash.

Which is newer

The release dates are August 12, 2026 for Grok 4.6 Xhigh and October 19, 2026 for MiniMax-M3.1-Flash, about 2 months apart.

Benchmark scores

On the intelligence index, Grok 4.6 Xhigh scores 31.0 against 29.1 for MiniMax-M3.1-Flash. The lead is visible but narrow, so it should not decide the choice on its own. In relative terms, Grok 4.6 Xhigh scores 7% higher.

For context, that places Grok 4.6 Xhigh 49th and MiniMax-M3.1-Flash 59th out of 109 scored models still on offer.

Specialist coding and math indexes are missing for both, so treat the overall score as the only capability signal here.

Score per dollar

Dividing the blended price by the intelligence index gives a rough cost per point: $0.097 for Grok 4.6 Xhigh and $0.0090 for MiniMax-M3.1-Flash, per million tokens. So Grok 4.6 Xhigh buys its higher score at a premium, while MiniMax-M3.1-Flash is the value pick, paying 91% less per point.

How fast they respond

Grok 4.6 Xhigh generates about 62 tokens per second and MiniMax-M3.1-Flash about 147 tokens per second. MiniMax-M3.1-Flash is ahead by 137% on throughput. Before any text appears, Grok 4.6 Xhigh takes 47 seconds and MiniMax-M3.1-Flash 1.0 seconds. MiniMax-M3.1-Flash gets to its first token 46 times as fast. A first-token wait of that length suits background work better than live conversation.

For a 1,000-token response, first token plus generation comes to roughly 63 seconds on Grok 4.6 Xhigh and 7.8 seconds on MiniMax-M3.1-Flash.