Nomic Embed Text v1.5

Vectors, not text. Truncate to 256 dimensions and keep most of the quality.

$argosy up --model nomic-embed-text-v1-5

ttft6ms

p50 from the nearest warm region

Throughput—tok/s

Single stream, no batching

Context8K

Full window, no sliding truncation

Price$0.01

Per million tokens served

Matryoshka embeddings, so you can truncate the vector to 256 or 512 dimensions and keep most of the quality. Priced on input tokens only, because there is no output to price.

Deploymentdep_70efdf

Parameters137M

Quantisationfp16

LicenceApache 2.0

Home regioniad1

Extra replicas20

p50 latency7ms

p99 latency14ms

Requests / s18400

Figures are illustrative — this is a demonstration site.

Last 30 minutesiad1

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 MX Mixtral 8x7B Instruct 31ms $0.22

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