MiMo-V2.6-Flash-RL vs GPT-5.6 Luna
API pricing, benchmark indices and specs — updated 19 October 2026.
XiaomiMiMo · A · Open weights
Params
310.8 B
Context
1,048,576
30d
92 K
mit · commercial OK
openai · B · API-only
Input / 1M
$0.20
Output / 1M
$1.20
AA index
37.3
proprietary · 1.0M context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | MiMo-V2.6-Flash-RL | GPT-5.6 Luna |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 310.8 B | n/a — API-only |
| Architecture | MiMoV2ForCausalLM | n/a — API-only |
| Context length | 1,048,576 | 1,050,000 |
| Licence | mit | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | 2 | n/a — API-only |
| Downloads 30d | 91,830 | n/a — API-only |
| Downloads all time | 110 K | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2026-09-21 | n/a — API-only |
| API input price / 1M tokens | $0.14 | $0.20 |
| API output price / 1M tokens | $0.28 | $1.20 |
| Est. cost per 1M input + 1M output tokens | $0.42 | $1.40 |
| Cached input / 1M tokens | $0.0028 | $0.02 |
| AA Intelligence Index | 37.9 | 37.3 |
| AA Coding Index | — | 71.4 |
| AA Agentic Index | — | 42.1 |
| Max output tokens | 131,072 | 128,000 |
| API providers | 10 | 3 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
MiMo-V2.6-Flash-RL
$0.42
GPT-5.6 Luna
$1.40
MiMo-V2.6-Flash-RL is 3.3× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
MiMo-V2.6-Flash-RL · fp16 @ 1024K ctx
6,162.5 GB / 24 GB