AIALMI
← Models

NVIDIA · deprecated

Llama 3.1 Nemotron 70B Instruct

Llama 3.1 Nemotron 70B Instruct is attributed to NVIDIA in the catalog. It accepts text input and produces text output. Reported capabilities include tool calling.

Compare model
Report an errorModel and price history

Modalities

Hosted provider token rates

$0.357 / $0.408

USD per 1M input / output tokens · NanoGPT

Context

128K

Released

2025-04-15

Knowledge cutoff

Unknown

No recent lab-operated provider rate is available. Showing the third-party host with the lowest input rate + ¼ output rate. This is one offering, not an average; other providers, modalities, tiers, and fees may differ.

Where to use it

3 observed offerings · token prices in USD per million where available

Estimate your workload cost
Nvidia

nvidia/llama-3.1-nemotron-70b-instruct

deprecated

Input

$0

Output

$0

Cache

—

Context

128K

Max output

8K
Reasoning
No
Tool calling
Yes
Structured output
Unknown
Temperature
Yes

Not a current offering

Eden AI

deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct

current

Input

$0.60

Output

$0.60

Cache

—

Context

131K

Max output

8K
Reasoning
No
Tool calling
Yes
Structured output
No
Temperature
Yes

Recent price

NanoGPT

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

current

Input

$0.357

Output

$0.408

Cache

$0.1785

Context

16K

Max output

8K
Reasoning
No
Tool calling
No
Structured output
No
Temperature
Yes

Recent price

Limits and capabilities reflect each provider’s listed offering. Unknown means support was not reported.

Capabilities and limits

Input
text
Output
text
Max output
8K
Weights
Open (source-reported)
Release
2025-04-15
Knowledge cutoff
Unknown
Family
nemotron

Tool calling

Provider-specific limits and support can differ.

Plan a model evaluation

Evaluate quality and latency on examples from your intended use before choosing a model.

Explore available evidence

Models to compare

Candidates match reported specifications; they are not tested replacements.

nemotron-voicechatNVIDIA · 128K contextCompare →Nemotron-nano 12b v2-vlNVIDIA · 128K contextCompare →Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA · 256K contextCompare →

Model and price history

Latest recorded change: source refresh · 2026-10-22

Model changes (1)
  • source refresh · 2026-10-22
    {
  "before": {
    "status": "current"
  },
  "after": {
    "status": "deprecated"
  }
}
Price history (111 observations)
DateProviderInput / output
2026-11-02Nvidia$0 / $0
2026-11-02Eden AI$0.60 / $0.60
2026-11-02NanoGPT$0.357 / $0.408
2026-11-01Nvidia$0 / $0
2026-11-01Eden AI$0.60 / $0.60
2026-11-01NanoGPT$0.357 / $0.408
2026-10-31Nvidia$0 / $0
2026-10-31Eden AI$0.60 / $0.60
2026-10-31NanoGPT$0.357 / $0.408
2026-10-30Nvidia$0 / $0
2026-10-30Eden AI$0.60 / $0.60
2026-10-30NanoGPT$0.357 / $0.408
2026-10-29Nvidia$0 / $0
2026-10-29Eden AI$0.60 / $0.60
2026-10-29NanoGPT$0.357 / $0.408
2026-10-28Nvidia$0 / $0
2026-10-28Eden AI$0.60 / $0.60
2026-10-28NanoGPT$0.357 / $0.408
2026-10-27Nvidia$0 / $0
2026-10-27Eden AI$0.60 / $0.60
2026-10-27NanoGPT$0.357 / $0.408
2026-10-27Nvidia$0 / $0
2026-10-27Eden AI$0.60 / $0.60
2026-10-27NanoGPT$0.357 / $0.408
2026-10-27Nvidia$0 / $0
2026-10-27Eden AI$0.60 / $0.60
2026-10-27NanoGPT$0.357 / $0.408
2026-10-27Nvidia$0 / $0
2026-10-27Eden AI$0.60 / $0.60
2026-10-27NanoGPT$0.357 / $0.408
2026-10-26Nvidia$0 / $0
2026-10-26Eden AI$0.60 / $0.60
2026-10-26NanoGPT$0.357 / $0.408
2026-10-25Nvidia$0 / $0
2026-10-25Eden AI$0.60 / $0.60
2026-10-25NanoGPT$0.357 / $0.408
2026-10-24Nvidia$0 / $0
2026-10-24Eden AI$0.60 / $0.60
2026-10-24NanoGPT$0.357 / $0.408
2026-10-24Nvidia$0 / $0
2026-10-24Eden AI$0.60 / $0.60
2026-10-24NanoGPT$0.357 / $0.408
2026-10-24Nvidia$0 / $0
2026-10-24Eden AI$0.60 / $0.60
2026-10-24NanoGPT$0.357 / $0.408
2026-10-23Nvidia$0 / $0
2026-10-23Eden AI$0.60 / $0.60
2026-10-23NanoGPT$0.357 / $0.408
2026-10-23Nvidia$0 / $0
2026-10-23Eden AI$0.60 / $0.60
2026-10-23NanoGPT$0.357 / $0.408
2026-10-23Nvidia$0 / $0
2026-10-23Eden AI$0.60 / $0.60
2026-10-23NanoGPT$0.357 / $0.408
2026-10-23Nvidia$0 / $0
2026-10-23Eden AI$0.60 / $0.60
2026-10-23NanoGPT$0.357 / $0.408
2026-10-23Nvidia$0 / $0
2026-10-23Eden AI$0.60 / $0.60
2026-10-23NanoGPT$0.357 / $0.408
2026-10-22Nvidia$0 / $0
2026-10-22Eden AI$0.60 / $0.60
2026-10-22NanoGPT$0.357 / $0.408
2026-10-21Nvidia$0 / $0
2026-10-21Eden AI$0.60 / $0.60
2026-10-21NanoGPT$0.357 / $0.408
2026-10-20Nvidia$0 / $0
2026-10-20Eden AI$0.60 / $0.60
2026-10-20NanoGPT$0.357 / $0.408
2026-10-19Nvidia$0 / $0
2026-10-19Eden AI$0.60 / $0.60
2026-10-19NanoGPT$0.357 / $0.408
2026-10-18Nvidia$0 / $0
2026-10-18Eden AI$0.60 / $0.60
2026-10-18NanoGPT$0.357 / $0.408
2026-10-17Nvidia$0 / $0
2026-10-17Eden AI$0.60 / $0.60
2026-10-17NanoGPT$0.357 / $0.408
2026-10-12Nvidia$0 / $0
2026-10-12Eden AI$0.60 / $0.60
2026-10-12NanoGPT$0.357 / $0.408
2026-10-12Nvidia$0 / $0
2026-10-12Eden AI$0.60 / $0.60
2026-10-12NanoGPT$0.357 / $0.408
2026-10-11Nvidia$0 / $0
2026-10-11Eden AI$0.60 / $0.60
2026-10-11NanoGPT$0.357 / $0.408
2026-10-10Nvidia$0 / $0
2026-10-10Eden AI$0.60 / $0.60
2026-10-10NanoGPT$0.357 / $0.408
2026-10-09Nvidia$0 / $0
2026-10-09Eden AI$0.60 / $0.60
2026-10-09NanoGPT$0.357 / $0.408
2026-10-09Nvidia$0 / $0
2026-10-09NanoGPT$0.357 / $0.408
2026-10-08Nvidia$0 / $0
2026-10-08NanoGPT$0.357 / $0.408
2026-10-07Nvidia$0 / $0
2026-10-07NanoGPT$0.357 / $0.408
2026-09-22Nvidia$0 / $0
2026-09-22NanoGPT$0.357 / $0.408
2026-09-21Nvidia$0 / $0
2026-09-21NanoGPT$0.357 / $0.408
2026-09-20Nvidia$0 / $0
2026-09-20NanoGPT$0.357 / $0.408
2026-09-19Nvidia$0 / $0
2026-09-19NanoGPT$0.357 / $0.408
2026-09-18Nvidia$0 / $0
2026-09-18NanoGPT$0.357 / $0.408
2026-09-17Nvidia$0 / $0
2026-09-17NanoGPT$0.357 / $0.408