Friday, August 21, 2026 · No. 390Prices synced 5 hours ago
All·AI·Model

The AI Model Price Index

Nemotron 3 Ultra

by Weights & Biases · family nemotron · listed Jun 2026RTW

Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.

Current rates USD per 1M tokens

Input$0.75
Output$2.75
Cache read$0.15
Cache write—

Against the market

Input price vs. maker flagships ($/1M tokens)
DeepSeek V4 ProDeepSeek V4 Pro: $0.435 per 1M tokens$0.435Nemotron 3 UltraNemotron 3 Ultra: $0.75 per 1M tokens$0.75Gemini 3.7 FlashGemini 3.7 Flash: $0.75 per 1M tokens$0.75Mistral Medium 3.5Mistral Medium 3.5: $1.50 per 1M tokens$1.50Grok 4.6Grok 4.6: $2.00 per 1M tokens$2.00Qwen3.8 MaxQwen3.8 Max: $2.00 per 1M tokens$2.00Claude Opus 5Claude Opus 5: $5.00 per 1M tokens$5.00GPT-5.6 SolGPT-5.6 Sol: $5.00 per 1M tokens$5.00
Output price vs. maker flagships ($/1M tokens)
DeepSeek V4 ProDeepSeek V4 Pro: $0.87 per 1M tokens$0.87Nemotron 3 UltraNemotron 3 Ultra: $2.75 per 1M tokens$2.75Gemini 3.7 FlashGemini 3.7 Flash: $3.75 per 1M tokens$3.75Grok 4.6Grok 4.6: $6.00 per 1M tokens$6.00Qwen3.8 MaxQwen3.8 Max: $6.00 per 1M tokens$6.00Mistral Medium 3.5Mistral Medium 3.5: $7.50 per 1M tokens$7.50Claude Opus 5Claude Opus 5: $25.00 per 1M tokens$25.00GPT-5.6 SolGPT-5.6 Sol: $30.00 per 1M tokens$30.00

On the record

Model id
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
Context window
262K tokens
Max output
262K tokens
Input modalities
text
Output modalities
text
Reasoning
yes
Tool calls
yes
Open weights
yes
Knowledge cutoff
—
Released
2026-06-04
Last updated
2026-06-04
Provider docs
docs.wandb.ai/guides/integrations/inference/

Back of the envelope

≈

Also listed at

← All Weights & Biases listings