LIVE Cheapest: GLM-4.7-Flash $0.000/Mtok in 153 models tracked Updated Jun 25, 2026
Jun 25, 2026
ModelPriceWatch$/Mtok
Pricing / Compare / Nemotron 70B Instruct vs Llama Nemotron Ultra 253B

Nemotron 70B Instruct vs Llama Nemotron Ultra 253B

Side-by-side API pricing comparison · NVIDIA vs NVIDIA

🏆 Nemotron 70B Instruct is 2000% cheaper on blended cost ($0.100 vs $2.10/Mtok)

Nemotron 70B Instruct

by NVIDIA

Current open weights Open weights
Input
$0.100/Mtok
Output
$0.100/Mtok
✓ Cheaper
Blended avg$0.100/Mtok
Context128K tokens
Modalitytext
Parameters70B
ReleasedJun 1, 2025
Full details →

Llama Nemotron Ultra 253B

by NVIDIA

Current open weights Open weights
Input
$0.600/Mtok
Output
$3.60/Mtok
Blended avg$2.10/Mtok
Context128K tokens
Modalitytext
Parameters253B
ReleasedJan 1, 2025
Full details →

Cost at scale — 1M tokens (50/50 input/output)

VolumeNemotron 70B InstructLlama Nemotron Ultra 253BSavings
1M tokens $0.1 $2.1 $2 (95.2%)
10M tokens $1 $21 $20 (95.2%)
100M tokens $10 $210 $200 (95.2%)
1000M tokens $100 $2100 $2000 (95.2%)

Summary

Nemotron 70B Instruct by NVIDIA costs $0.100/Mtok input and $0.100/Mtok output, with a 128K-token context window. It supports text input.

Llama Nemotron Ultra 253B by NVIDIA costs $0.600/Mtok input and $3.60/Mtok output, with a 128K-token context window. It supports text input.

On a blended cost basis, Nemotron 70B Instruct is 2000% cheaper than Llama Nemotron Ultra 253B.

Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.