MiniMax-M2.5 vs Mixtral-8x22B-Instruct-v0.1
Specs, VRAM requirements and download trends — updated 24 October 2026.
mistralai · B · Open weights
Params
140.6 B
Context
65,536
30d
46 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | MiniMax-M2.5 | Mixtral-8x22B-Instruct-v0.1 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 228.7 B | 140.6 B |
| Architecture | MiniMaxM2ForCausalLM | MixtralForCausalLM |
| Context length | 196,608 | 65,536 |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | — | 5 |
| Downloads 30d | 893,342 | 46,472 |
| Downloads all time | 5.8 M | 6.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-12 | 2024-04-16 |
| API input price / 1M tokens | $0.27 | $2.00 |
| API output price / 1M tokens | $0.95 | $6.00 |
| Est. cost per 1M input + 1M output tokens | $1.22 | $8.00 |
| Cached input / 1M tokens | $0.03 | $0.20 |
| AA Intelligence Index | 22.8 | 5.7 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 32,768 | 52,428 |
| API providers | 7 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
MiniMax-M2.5
$1.22
Mixtral-8x22B-Instruct-v0.1
$8.00
MiniMax-M2.5 is 6.6× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
893 K44 K
MiniMax-M2.5
Mixtral-8x22B-Instruct-v0.1
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Mixtral-8x22B-Instruct-v0.1 · fp16
331.0 GB / 24 GB
MiniMax-M2.5 · fp16 @ 192K ctx
1,077.0 GB / 24 GB