Models, measured side by side
DeepSeek V4.1 Flash vs MiMo-V2.6-Pro
Compare DeepSeek V4.1 Flash, MiMo-V2.6-Pro by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
DeepSeek V4.1 Flash
$7.00 / mo
MiMo-V2.6-Pro
$13 / mo
Performance comparison
DeepSeek V4.1 Flash
39.5
MiMo-V2.6-Pro
46.3
Overview
Pricing & capacity
| Pricing & capacity | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| Input / 1M tokens | $0.05 | $0.43 |
| Output / 1M tokens | $1.20 | $0.87 |
| Cached input / 1M | $0.02 | $0.0036 |
| Monthly cost | $7.00 | $13 |
| Context window | 1M | 1.1M |
| Maximum output | 944K | 131K |
Input / 1M tokens
- DeepSeek V4.1 Flash
- $0.05
- MiMo-V2.6-Pro
- $0.43
Output / 1M tokens
- DeepSeek V4.1 Flash
- $1.20
- MiMo-V2.6-Pro
- $0.87
Cached input / 1M
- DeepSeek V4.1 Flash
- $0.02
- MiMo-V2.6-Pro
- $0.0036
Monthly cost
- DeepSeek V4.1 Flash
- $7.00
- MiMo-V2.6-Pro
- $13
Context window
- DeepSeek V4.1 Flash
- 1M
- MiMo-V2.6-Pro
- 1.1M
Maximum output
- DeepSeek V4.1 Flash
- 944K
- MiMo-V2.6-Pro
- 131K
Benchmarks & performance
| Benchmarks & performance | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| Intelligence Index | 39.5 | 46.3 |
| Humanity’s Last Exam | 39.2% | 49.4% |
| SciCode | 51.9% | 60.9% |
| Output speed | 213 tokens/s | 41 tokens/s |
| Time to first token | 1.05 s | 4.19 s |
| DesignArena rating | 1,325 | Not listed |
| DesignArena win rate | 52.1% | Not listed |
Intelligence Index
- DeepSeek V4.1 Flash
- 39.5
- MiMo-V2.6-Pro
- 46.3
Humanity’s Last Exam
- DeepSeek V4.1 Flash
- 39.2%
- MiMo-V2.6-Pro
- 49.4%
SciCode
- DeepSeek V4.1 Flash
- 51.9%
- MiMo-V2.6-Pro
- 60.9%
Output speed
- DeepSeek V4.1 Flash
- 213 tokens/s
- MiMo-V2.6-Pro
- 41 tokens/s
Time to first token
- DeepSeek V4.1 Flash
- 1.05 s
- MiMo-V2.6-Pro
- 4.19 s
DesignArena rating
- DeepSeek V4.1 Flash
- 1,325
- MiMo-V2.6-Pro
- Not listed
DesignArena win rate
- DeepSeek V4.1 Flash
- 52.1%
- MiMo-V2.6-Pro
- Not listed
Tools & features
| Tools & features | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| Function calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Log probabilities | Supported | Not listed |
| Deterministic seed | Supported | Supported |
| Prompt caching | Supported | Supported |
Function calling
- DeepSeek V4.1 Flash
- Supported
- MiMo-V2.6-Pro
- Supported
Structured outputs
- DeepSeek V4.1 Flash
- Supported
- MiMo-V2.6-Pro
- Supported
JSON mode
- DeepSeek V4.1 Flash
- Supported
- MiMo-V2.6-Pro
- Supported
Reasoning
- DeepSeek V4.1 Flash
- Supported
- MiMo-V2.6-Pro
- Supported
Log probabilities
- DeepSeek V4.1 Flash
- Supported
- MiMo-V2.6-Pro
- Not listed
Deterministic seed
- DeepSeek V4.1 Flash
- Supported
- MiMo-V2.6-Pro
- Supported
Prompt caching
- DeepSeek V4.1 Flash
- Supported
- MiMo-V2.6-Pro
- Supported
API & availability
| API & availability | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| API identifier | deepseek-v4.1-flash | mimo-v2.6-pro |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- DeepSeek V4.1 Flash
deepseek-v4.1-flash- MiMo-V2.6-Pro
mimo-v2.6-pro
Prices checked
- DeepSeek V4.1 Flash
- Oct 8, 2026
- MiMo-V2.6-Pro
- Oct 8, 2026
About the models
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Full pricing & detailsMiMo-V2.6-Pro
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...
Full pricing & detailsComparison FAQ
DeepSeek V4.1 Flash: $0.05 input and $1.20 output per million tokens. MiMo-V2.6-Pro: $0.43 input and $0.87 output per million tokens. The cheaper choice depends on your input-to-output ratio; a model can have a lower input rate but a higher output rate.