Xiaomi: MiMo-V2.6-Flash
by XiaomiXiaomi: MiMo-V2.6-Flash is a large language model from Xiaomi. It costs $0.140 per million input tokens and $0.280 per million output tokens. Its context window is 1.1M tokens.
- Input / 1M tokens
- $0.140
- Output / 1M tokens
- $0.280
- Cached input / 1M
- $0.0028
- Context window
- 1.1M
On repeated prefixes
tokens
Who serves it cheapest
10 hosts serve MiMo-V2.6-Flash. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DarkbloomCheapestfp4 | $0.100 | $0.280 | 1.0M | - | 99.5% |
| DeepInfrafp8 | $0.133 | $0.266 | 1.0M | - | 97.4% |
| Makorafp8 | $0.130 | $0.280 | 1.0M | - | 96.5% |
| Relacemxfp4 | $0.130 | $0.280 | 1.0M | - | 99.8% |
| Cohere | $0.140 | $0.280 | 1.0M | - | 90.0% |
| Novitafp8 | $0.140 | $0.280 | 1.0M | - | 99.4% |
| GMICloudbf16 | $0.140 | $0.280 | 1.1M | - | 95.2% |
| Xiaomifp8 | $0.140 | $0.280 | 1.0M | - | 100.0% |
| Io Netfp8 | $0.150 | $0.290 | 1.0M | - | 99.2% |
| Venicefp8 | $0.175 | $0.350 | 1M | - | 98.6% |
The spread between Darkbloom and Venice is 1.5× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 37.9
About MiMo-V2.6-Flash
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...
Specifications
| Model ID | xiaomi/mimo-v2.6-flash |
|---|---|
| Provider | Xiaomi |
| Context window | 1.1M tokens |
| Max output | 131K tokens |
| Input modalities | text, image, video, audio |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - XiaomiMiMo/MiMo-V2.6-Flash-RL |
| Released | September 21, 2026 |
Cheaper alternatives
Models that cost less than MiMo-V2.6-Flash while keeping at least half its context window and every input modality it supports.
Gemini 2.5 Flash Lite
$0.100 in · $0.400 out
about the same cheaperMiMo-V2.5
$0.119 in · $0.238 out
1.2× cheaperJev Router
$-1000000.0000 in · $-1000000.0000 out
about the same cheaperAuto Router (Beta)
$-1000000.0000 in · $-1000000.0000 out
about the same cheaperAuto Router
$-1000000.0000 in · $-1000000.0000 out
about the same cheaperFrequently asked
How much does Xiaomi: MiMo-V2.6-Flash cost?
$0.140 per million input tokens and $0.280 per million output tokens. Cached input reads cost $0.0028 per million tokens.
What is the context window of Xiaomi: MiMo-V2.6-Flash?
1.1M tokens, with up to 131K tokens of output per request.
Which provider serves Xiaomi: MiMo-V2.6-Flash cheapest?
Darkbloom at $0.100 per million input tokens - 1.5× cheaper than Venice, the most expensive of the 10 hosts serving it.