LLM Perks

Riva Translate 4B Instruct V2

NVIDIA
Free right now Small Translation

Riva Translate 4B Instruct V2 is a translation model with 4B parameters from NVIDIA. It is currently free at 2 providers with up to 8K tokens of context.

Developer
NVIDIA
Parameters
4B
Context
8K tokens
Type
Translation

Where to use Riva Translate 4B Instruct V2 for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
NVIDIA Build
nvidia/riva-translate-4b-instruct-v2
— Free serverless inference for development; limits and model availability may change. No Open
UnoRouter
riva-translate-4b-instruct-v2:free
8K No-card free models use shared capacity and per-model limits; availability can change. No Open

Quick start

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/riva-translate-4b-instruct-v2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for NVIDIA Build. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

This model is not on the Artificial Analysis leaderboard yet. We do not publish our own estimates.

FAQ

Is Riva Translate 4B Instruct V2 free?

Yes. As of September 26, 2026, Riva Translate 4B Instruct V2 is free at NVIDIA Build, UnoRouter. Each provider has its own limits — see the table above.

What is the context window of Riva Translate 4B Instruct V2?

The largest context among free routes is 8,192 tokens. Some providers cap it lower.

How do I call Riva Translate 4B Instruct V2 via API?

Use any OpenAI-compatible client with base URL https://integrate.api.nvidia.com/v1, model ID nvidia/riva-translate-4b-instruct-v2, and a NVIDIA Build key.