Mi:dm K 3.0 Pro
by Kt · kt/midm-k-3.0-pro · #132 cheapest of 452 paid models
Prices updated Nov 17, 2026, 5:42 PM UTC · refreshed nightly
Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.20
per 1M tokens
Output
$0.80
per 1M tokens
Blended (3:1)
$0.35
3 input : 1 output
Cache read
$0.04
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Mi:dm K 3.0 Pro with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.35 | $0.0212 | — |
| 50% | $0.29 | $0.0132 | −38% |
| 90% | $0.242 | $0.0068 | −68% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00034 | $0.34 |
| Document summary | 8,000 | 1,000 | $0.0024 | $2.40 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0076 | $7.60 |
| Long-context analysis | 150,000 | 5,000 | $0.034 | $34.00 |
Specs
Context window
262K
tokens
Max output
236K
tokens
Input modalities
text
Tokenizer
Other