Question 1

What input types does Nemotron 3 Nano Omni accept on Chutes?

Accepted Answer

Text, images (image_url), video (video_url), and audio (audio_url), combined freely in one chat request using standard OpenAI-style content arrays. Output is always text, optionally with reasoning_content thinking blocks. The model card states language support is English only.

Question 2

What is the context window?

Accepted Answer

This chute serves 131,072 tokens (SGLang --context-length). The upstream model supports up to 256K tokens per NVIDIA's model card, with max_position_embeddings of 262,144 in the config.

Question 3

Does it support function calling and streaming?

Accepted Answer

Yes to both. Tool calls are parsed with the qwen3_coder parser and returned in the standard OpenAI tool_calls format, and both /v1/chat/completions and /v1/completions support streaming.

Question 4

How do I call it from the OpenAI SDK?

Accepted Answer

Set base_url to https://llm.chutes.ai/v1, api_key to your Chutes API key, and model to Nemotron-3-Nano-Omni-30B-TEE. Everything else is standard chat completions, including multimodal content arrays.

Question 5

What does the TEE suffix mean?

Accepted Answer

The model runs inside a Trusted Execution Environment: attested confidential-compute hardware that processes your prompts and outputs in an encrypted enclave. The model weights and behavior are unchanged; TEE is a serving-level security property.

Question 6

How do I control or disable the reasoning mode?

Accepted Answer

Reasoning (thinking) is on by default and the deployment uses the nemotron_3 reasoning parser. You can disable it via the chat template's enable_thinking switch as documented in NVIDIA's model card. For reasoning tasks, NVIDIA recommends temperature 0.6, top_p 0.95, and a generous max_tokens (their thinking-mode budget is 20,480).

Question 7

Can I use it commercially?

Accepted Answer

Yes. The model ships under the NVIDIA Open Model License Agreement and NVIDIA's card explicitly states it is available for commercial use. Review the license text on the Hugging Face repo for redistribution terms.

Question 8

Why does the chute default to max_tokens 1024?

Accepted Answer

That is just the endpoint default. Because reasoning mode emits thinking tokens before the answer, set max_tokens much higher (NVIDIA's thinking-mode reference is 20,480 total) or long analyses will truncate.

Nemotron 3 Nano Omni 30B

Sign in to use the playground

Nemotron 3 Nano Omni 30B

Sign in to use the playground