Compare

Nemotron-3-120b-A12b vs Inworld TTS 2

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
IT
Inworld TTS 2
inworld/tts-2
Provider
Nvidia
Inworld
Family
Inworld TTS
Modality
text
audio-tts
Context window
131,072 tok
Max output
4,096 tok
Released
2026-02-24
2026-05-05
License
Open-weight
Proprietary
Input price
$0.500 /1M
Output price
$1.20 /1M
Per 1K chars
$0.035 /1K ch
Tools
yes
Streaming
yes
Vision
JSON mode
yes
Reasoning
yes
Prompt caching
Batch API
Try it
Open in playground →
Open in playground →
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
Inworld TTS 2
inworld/tts-2
Full spec →

Inworld's most powerful and expressive text-to-speech model. Builds on TTS 1.5 with rich expressive speech, real-time latency, natural language steering (e.g. [whisper], [say excitedly]), and stronger multilingual support across 15 production languages plus 90+ experimental languages.

Strengths
  • Natural speech synthesis
Use cases
VoiceoversIVRAudiobooks

Compare with another

GPT-5.5 Pro vs Nemotron-3-120b-A12b
openai/gpt-5.5-pro · nvidia/nemotron-3-120b-a12b
GPT-5.5 Pro vs Inworld TTS 2
openai/gpt-5.5-pro · inworld/tts-2
GPT-5.5 vs Nemotron-3-120b-A12b
openai/gpt-5.5 · nvidia/nemotron-3-120b-a12b
GPT-5.5 vs Inworld TTS 2
openai/gpt-5.5 · inworld/tts-2
Claude Opus 4.7 vs Nemotron-3-120b-A12b
anthropic/claude-opus-4.7 · nvidia/nemotron-3-120b-a12b
Claude Opus 4.7 vs Inworld TTS 2
anthropic/claude-opus-4.7 · inworld/tts-2
Claude Sonnet 4.6 vs Nemotron-3-120b-A12b
anthropic/claude-sonnet-4.6 · nvidia/nemotron-3-120b-a12b
Claude Sonnet 4.6 vs Inworld TTS 2
anthropic/claude-sonnet-4.6 · inworld/tts-2
Kimi-K2.6 vs Nemotron-3-120b-A12b
moonshot/kimi-k2.6 · nvidia/nemotron-3-120b-a12b
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-...",
)

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

# Inworld TTS 2
client.chat.completions.create(
    model="inworld/tts-2",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →