Cloud
Rent compute. Own the stack when you're ready.
Start on the API platform, bring agentic teams into Desktop, or rent dedicated Macs for unlimited usage and air-gapped privacy.
01 · Token-based
Build on the API today.
Pay by tier — Lite, Balanced, Frontier. Models and compute change underneath; your code does not. New accounts start with $5 free.
Lite
Gemma 4 E2B
lite- Input / M
- $0.08
- Output / M
- $0.40
Balanced
Gemma 4 26B A4B
balanced- Input / M
- $0.18
- Output / M
- $0.98
Frontier
Ornith 1.5 122B
frontier- Input / M
- $0.95
- Output / M
- $3.73
Embeddings
BGE-M3
midium- Input / M
- $0.012
- Output / M
- $0.036
System One
KnowLine 26B A4B Gen2
midium- Input / M
- $0.032
- Output / M
- $0.00
| API | Model name | Input / M | Output / M |
|---|---|---|---|
| LiteGemma 4 E2B | lite | $0.08 | $0.40 |
| BalancedGemma 4 26B A4B | balanced | $0.18 | $0.98 |
| FrontierOrnith 1.5 122B | frontier | $0.95 | $3.73 |
| EmbeddingsBGE-M3 | midium | $0.012 | $0.036 |
| System OneKnowLine 26B A4B Gen2 | midium | $0.032 | $0.00 |
02 · Team plans
Agentic use inside Midium Desktop.
Cloud models in Desktop for chat, code, and vault-grounded agents — with Hub licensing when the team needs shared vaults and members.
03 · Dedicated Cluster
Rent dedicated Macs out of our cloud.
Unlimited usage for your team, air-gapped privacy, and unlimited team vaults — flat monthly rate when traffic grows.
Up to Sonnet Class Intelligence
Monthly tokens
~709M
~648M in · ~61M out
Same tokens on Sonnet 5.5
~$1,907/mo
$2 / $10 per 1M
128 GB Mac Studio
$1,000/mo flat
1.9× cheaper
Cost vs usage
Usage-based pricing
Cluster
Usage-based pricing climbs. A cluster stays flat.
Cluster
Your own AI cluster. Flat monthly rate.
Usage-based pricing climbs as traffic grows. A Midium cluster is a flat monthly rate for hardware we host, so production scale does not raise the bill.
Throughput
What one Mac can actually serve
Measured on a single 128 GB M5 Max under sustained load, with simulated users based on real Midium usage.
| Model | Coding developers (Standard) | Chat users (Standard) | Background agents |
|---|---|---|---|
| Qwen3.6 35B | 4 (~6 at Relaxed) | 24 (~40 at Relaxed) | 2 at once, 238k tokens/h |
| Gemma 4 26B | ~5 | 16 | 2 at once, 225k tokens/h |
| Ornith 1.5 122B | 2 | 12 at Relaxed | 4 at once, 134k tokens/h |
Standard: coding 25 tok/s and first token within 5 s; chat 20 tok/s and 2 s. Relaxed: coding 15 tok/s and 10 s; chat 12 tok/s and 4 s.
- Generation stays fast (50–220 tok/s per user). Reading long prompts sets the limit.
- Qwen3.6 stays fast on long 128k-token coding sessions.
- M5 Ultra and M3 Ultra: testing now. Estimates unpublished until measured.