Models · SeedInfer

List models via the API

GET https://seedinfer.com/v1/models returns the same catalog in OpenAI format; GET https://seedinfer.com/api/v1/pricing returns per-token prices.

3 models

Gemma 4 26B A4B NVFP4 — live

Live on network

Only Gemma 4 26B is currently active on the network, at $0.03 in / $0.20 out per 1M tokens (256K context, cached input free). Nemotron 3.5 Lightning and Qwen 3.6 35B are coming soon.

Test in API Console

Models & pricing · USD per 1M tokens

1 live · 2 coming soon Cached input is free (60s TTL, max 5 min)

google/gemma-4-26b-a4b-nvfp4

0 nodes

Gemma 4 26B A4B NVFP4

Live256K context · NVFP4

Input

$0.03 / 1M

Output

$0.20 / 1M

Cached input free · 60s TTL (max 5 min)

Providers: 0

Coming soon

seedinfer/nemotron-lightning-1m

Coming soon

Nemotron 3.5 Lightning 30B A3B NVFP4

1M context · NVFP4

Input

$0.02 / 1M

Output

$0.05 / 1M

Cached input free · 60s TTL (max 5 min)

Providers: —

qwen/qwen3.6-35b-a3b

Coming soon

Qwen 3.6 35B A3B NVFP4

256K context · NVFP4

Input

$0.06 / 1M

Output

$0.50 / 1M

Cached input free · 60s TTL (max 5 min)

Providers: —

OpenAI-compatible · https://seedinfer.com/v1Gemma 4 26B · $0.03 / $0.20 · 256KNemotron 3.5 Lightning · $0.02 / $0.05 · 1M · coming soonQwen 3.6 35B · $0.06 / $0.50 · 256K · coming soon