impulse

NVIDIA

Models
47
not retired
Lineup
5
last 18 months
Hosts
15
Retiring
2
next 12 months

Current lineup

General-purpose models released in the last 18 months, newest first. Prices are the lab's own, per million tokens.

Compare them
ModelIn / out per 1M
$0.30 / $0.90
via Nebius AI Studio
$0.06 / $0.24
via Nebius AI Studio
-
-
$0.05 / $0.20
via DeepInfra

Being retired

Dates announced by an API host in the next 12 months.

All retirements

Images, audio, search and more

ModelIn / out per 1M
Moderation
-
Embedding
-
Embedding
-
Embedding
-

Older models

Superseded or undated, but still served somewhere.

Show 38 older models
ModelIn / out per 1M
Chat
-
Chat
-
Chat
$0.50 / $2.15
via W&B Inference
Chat
$0.10 / $0.50
via GMI Cloud
Chat
$0.04 / $0.16
via DeepInfra
Chat
-
Chat
-
Chat
$0.07 / $0.20
via W&B Inference
Chat
$0.15 / $0.50
via DeepInfra
Chat
$0.66 / $2.64
via Azure AI Foundry
Chat
$0.06 / $0.22
via Azure AI Foundry
Chat
-
Chat
$0.10 / $0.40
via Nebius AI Studio
Chat
$0.10 / $0.40
via DeepInfra
Chat
$0.12 / $0.30
via Lambda AI
Chat
$0.50 / $1.50
via Cloudflare Workers AI
Embedding
-
Chat
$0.06 / $0.24
via Nebius AI Studio
Chat
-
Chat
$0.675 / $3.38
via Kyma API
Chat
-
Chat
$0.20 / $0.50
via Perplexity
Chat
-
Chat
-
Chat
-
Chat
$0.20 / $0.20
via DeepInfra
Chat
$0.20 / $0.60
via Amazon Bedrock
Chat
$0.06 / $0.24
via Amazon Bedrock
Chat
-
Chat
$0.06 / $0.23
via Amazon Bedrock
Chat
$0.10 / $0.10
via Fireworks AI
Chat
-
Chat
-
Chat
$0.15 / $0.65
via Amazon Bedrock
Chat
$0.06 / $0.24
via Nebius AI Studio
Chat
$0.075 / $0.40
via DeepInfra
Chat
$0.06 / $0.16
via DeepInfra
Chat
$0.20 / $0.20
via Fireworks AI

Where to run NVIDIA models

Hosts by how many of its models they serve.