riva-translate-4b-instruct-v2

nvidia/riva-translate-4b-instruct-v2

NVIDIA Build Card

Translation model in 37 languages with few-shots example prompts capability.

Context Length

Not published

Input Pricing

$0.18 / 1M

Output Pricing

$0.18 / 1M

Recent Latency

No probes

Model Architecture & Limits

Canonical IDnvidia/riva-translate-4b-instruct-v2

Publisher / Originatornvidia

Model FamilyMistral

ArchitectureTransformer (Decoder-only)

Context Window LimitNot published

Max Output TokensNot published

Endpoint Protocolopenai-chat

Capabilities & Modal Surfaces

Chat Conversation✓ Yes

Tool / Function Calling✕ No

Reasoning / Thinking✕ No

Structured Output (JSON)✓ Yes

Vision / Multimodal✕ No

Audio Processing✕ No

License & Restrictions

GOVERNING TERMS: This trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-u

Commercial and research use permitted under governing model and API terms.