Llama-3.1-Nemotron-Ultra-253B-v1
Nebius Token FactoryOpen weights
Llama-3.1-Nemotron-Ultra-253B-v1 by Nebius Token Factory costs $0.60 per 1M input tokens and $1.80 per 1M output tokens, with a 128K-token context window.
Pricing
Input (per 1M tokens)
$0.60
Output (per 1M tokens)
$1.80
Cached input (per 1M)
$0.06
Specifications
- Provider
- Nebius Token Factory
- Context window
- 128K tokens
- Parameters
- —
- Released
- Jan 2025
- Open weights
- Yes
- Frontier model
- No
Benchmarks
Compare Llama-3.1-Nemotron-Ultra-253B-v1 with…
Llama-3.1-Nemotron-Ultra-253B-v1 vs GLM 4.5V$1.80/1MLlama-3.1-Nemotron-Ultra-253B-v1 vs Qwen3 VL 235B A22B Instruct$1.90/1MLlama-3.1-Nemotron-Ultra-253B-v1 vs DeepSeek V4 Pro 0423$1.91/1MLlama-3.1-Nemotron-Ultra-253B-v1 vs Qwen3.6 Plus$1.95/1MLlama-3.1-Nemotron-Ultra-253B-v1 vs Qwen3.5 35B-A3B$2.00/1MLlama-3.1-Nemotron-Ultra-253B-v1 vs GPT-5 Mini$2.00/1M
FAQ
How much does Llama-3.1-Nemotron-Ultra-253B-v1 cost?
Llama-3.1-Nemotron-Ultra-253B-v1 is priced at $0.60 per 1M input tokens and $1.80 per 1M output tokens. Output tokens cost more than input.
What is Llama-3.1-Nemotron-Ultra-253B-v1's context window?
Llama-3.1-Nemotron-Ultra-253B-v1 supports a context window of 128K tokens — the maximum prompt plus response length it can handle in a single request.
Is Llama-3.1-Nemotron-Ultra-253B-v1 open weight?
Yes — Llama-3.1-Nemotron-Ultra-253B-v1 has openly available weights.
Data as of 2026-06-28. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.