Command R 35B

Built for grounded citation. On canary until it holds p99 under 90 ms for a fortnight.

$argosy up --model command-r-35b

ttft29ms

p50 from the nearest warm region

Throughput288tok/s

Single stream, no batching

Context128K

Full window, no sliding truncation

Price$0.19

Per million tokens served

Tuned for retrieval-augmented generation and grounded citation. Currently on canary — five per cent of traffic, and it will go live once it has held p99 under 90 ms for a fortnight.

Deploymentdep_c74d97

Parameters35B

Quantisationfp8

LicenceCC-BY-NC

Home regionyyz1

Extra replicas3

p50 latency31ms

p99 latency76ms

Requests / s1940

Figures are illustrative — this is a demonstration site.

Last 30 minutesyyz1

cache hitqueue 0ms errors 0

Also in the catalogue

LL Llama 3.1 8B Instruct 19ms $0.06 QW Qwen2.5 72B Instruct 41ms $0.36 QC Qwen2.5 Coder 32B 27ms $0.18 DS DeepSeek V3 58ms $0.58

Put the model next to the user.

One command, thirty-one regions, and an invoice that matches what you actually served.

Deploy a model Talk to an engineer