Compare

Bytedance Seedance 2.0 (Text To Video) vs Nemotron-3-120b-A12b

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Nemotron-3-120b-A12b
nvidia/nemotron-3-120b-a12b
Provider
ByteDance
Nvidia
Family
Modality
video
text
Context window
131,072 tok
Max output
4,096 tok
Released
2026-05-17
2026-02-24
License
Open-weight
Open-weight
Input price
$0.500 /1M
Output price
$1.20 /1M
Per output second
$0.014 /sec
Tools
yes
Streaming
yes
Vision
JSON mode
yes
Reasoning
yes
Prompt caching
Batch API
Try it
Open in playground →
Open in playground →
Bytedance Seedance 2.0 (Text To Video)
bytedance/seedance-2.0
Full spec →

ByteDance's next-generation video model with a unified multimodal architecture. Generates high-quality video with synchronized audio from text, images, video clips, and audio inputs. Supports multimodal references (up to 9 images, 3 videos, 3 audio files), native audio generation, video editing, video extension, intelligent duration, and adaptive aspect ratio.

Strengths
  • Text-to-video generation
  • Cinematic motion
Use cases
AdsStoryboardsDemos
Nemotron-3-120b-A12b
nvidia/nemotron-3-120b-a12b
Full spec →

NVIDIA Nemotron 3 Super is a hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows

Compare with another

GPT-5.5 Pro vs Bytedance Seedance 2.0 (Text To Video)
openai/gpt-5.5-pro · bytedance/seedance-2.0
GPT-5.5 Pro vs Nemotron-3-120b-A12b
openai/gpt-5.5-pro · nvidia/nemotron-3-120b-a12b
GPT-5.5 vs Bytedance Seedance 2.0 (Text To Video)
openai/gpt-5.5 · bytedance/seedance-2.0
GPT-5.5 vs Nemotron-3-120b-A12b
openai/gpt-5.5 · nvidia/nemotron-3-120b-a12b
Claude Opus 4.7 vs Bytedance Seedance 2.0 (Text To Video)
anthropic/claude-opus-4.7 · bytedance/seedance-2.0
Claude Opus 4.7 vs Nemotron-3-120b-A12b
anthropic/claude-opus-4.7 · nvidia/nemotron-3-120b-a12b
Claude Sonnet 4.6 vs Bytedance Seedance 2.0 (Text To Video)
anthropic/claude-sonnet-4.6 · bytedance/seedance-2.0
Claude Sonnet 4.6 vs Nemotron-3-120b-A12b
anthropic/claude-sonnet-4.6 · nvidia/nemotron-3-120b-a12b
Grok 4 vs Bytedance Seedance 2.0 (Text To Video)
xai/grok-4 · bytedance/seedance-2.0
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Bytedance Seedance 2.0 (Text To Video)
client.chat.completions.create(
    model="bytedance/seedance-2.0",
    messages=[{"role":"user","content":"hello"}],
)

# Nemotron-3-120b-A12b
client.chat.completions.create(
    model="nvidia/nemotron-3-120b-a12b",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →