minimax
Mi:dm K 3.0 Pro vs MiniMax M3.1 Flash
63.7 overall · $0.262 / 1M
// kt
Mi:dm K 3.0 Pro
kt/midm-k-3.0-pro
Mi:dm K 3.0 Pro costs $0.200 per 1M input tokens and $0.800 per 1M output tokens with a 262K-token context window.
A reasoning model from kt, released Nov 5, 2026. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $0.200
- Output / 1M
- $0.800
- Context
- 262K
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $0.200 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $0.800 |
| Blended price 3:1 input:output — #111 cheapest of 352 listed models | $0.350 |
| Cached input read Blank means not priced separately — not free | $0.040 |
| Cache write | — |
| Context window | 261,795 tokens |
| Max output | 235,615 tokens |
| Input modalities | text |
| Tool calling | No |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Nov 5, 2026 |
What Mi:dm K 3.0 Pro costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $100.48/mo |
| RAG assistant 8K in / 600 out × 100K requests | $144.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $134.40/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $252.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $500.00/mo |
Compare Mi:dm K 3.0 Pro with
Benchmarked models at a similar price.
Mi:dm K 3.0 Pro vs Gemma 4 31B
32.4 overall · $0.250 / 1M
nvidia
Mi:dm K 3.0 Pro vs Nemotron 3.5 Super VL
47.0 overall · $0.230 / 1M
xiaomi
Mi:dm K 3.0 Pro vs MiMo-V2.6-Pro
66.1 overall · $0.544 / 1M
qwen
Mi:dm K 3.0 Pro vs Qwen3.8 27B
54.0 overall · $0.581 / 1M
anthropic
Mi:dm K 3.0 Pro vs Claude Haiku 5.5
68.9 overall · $0.200 / 1M
Mi:dm K 3.0 Pro FAQ
How much does Mi:dm K 3.0 Pro cost?
Mi:dm K 3.0 Pro lists at $0.200 per 1M input tokens and $0.800 per 1M output tokens, with cached input reads at $0.040 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $144.00 at list price.
What is the context window of Mi:dm K 3.0 Pro?
Mi:dm K 3.0 Pro accepts up to 261,795 tokens of context and can return up to 235,615 output tokens per response.
Does Mi:dm K 3.0 Pro support tool calling?
Mi:dm K 3.0 Pro does not list tool (function) calling support and exposes extended reasoning. It accepts text input.
How does Mi:dm K 3.0 Pro score on benchmarks?
LiveBench has not published a run for Mi:dm K 3.0 Pro yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for Mi:dm K 3.0 Pro?
On OpenRouter the model ID is "kt/midm-k-3.0-pro". It was listed on Nov 5, 2026.
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-11-06. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.