Nvidia

Llama 3.1 Nemotron 70B Instruct API Pricing 2026

Compare pricing, benchmarks, and providers for Llama 3.1 Nemotron 70B Instruct. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Llama 3.1 Nemotron 70B Instruct was released on October 15, 2024. Pricing starts at $0.880 per million input tokens and $0.880 per million output tokens. The model supports a context window of up to 131K tokens. API access is available through Nvidia.

Context Window
131K
tokens
Pricing
Input$0.880
Output$0.880
Cached$0.450
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Tools

Llama 3.1 Nemotron 70B Instruct is priced at $0.880 per million input tokens and $0.880 per million output tokens. It has a context window of 131,072 tokens. It is available from 2 providers, with Together the cheapest at $0.880 per million input tokens (input prices range from $0.880 to $0.900). On benchmarks, Llama 3.1 Nemotron 70B Instruct scores Aider 54.9 (37th percentile).

Pricing Comparison

Compare Llama 3.1 Nemotron 70B Instruct with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.880
$0.880
—
—
—
131,072
Try
$0.800
$0.800
—
—
—
4,096
Try
$0.800
$1.600
—
—
—
131,072
Try
$0.800
$0.800
—
—
—
4,096
Try
$0.800
$0.800
—
—
—
4,096
Try
$0.834
$2.501
—
—
—
1,048,576
Try
$0.850
$1.250
—
—
—
256,000
Try
$0.850
$3.400
—
—
—
131,072
Try
$0.850
$0.850
—
—
—
32,768
Try
$0.875
$7.000
—
—
—
128,000
Try
$0.880
$0.880
—
—
—
131,072
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Llama 3.1 Nemotron 70B Instruct is available from multiple providers with different pricing and availability.

2
Providers
$0.880
Cheapest Input/M
$0.880
Cheapest Output/M
Together
Best Price

Provider Pricing

2 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
Together
Together
Best Price
$0.880
$0.880
-
-
-
$0.900
$0.900
$0.450
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Llama 3.1 Nemotron 70B Instruct perform? Vote based on your experience.

Cost vs. Quality

Compare Llama 3.1 Nemotron 70B Instruct's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try Llama 3.1 Nemotron 70B Instruct

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Llama 3.1 Nemotron 70B Instruct directly in your browser.

Open Playground

Frequently Asked Questions

Llama 3.1 Nemotron 70B Instruct costs $0.000880 per 1,000 input tokens and $0.000880 per 1,000 output tokens.
Llama 3.1 Nemotron 70B Instruct is available from 2 providers. Together offers the best price.
Together offers Llama 3.1 Nemotron 70B Instruct at $0.880 per million input tokens, the lowest of 2 providers (input prices range from $0.880 to $0.900 per million tokens).
Llama 3.1 Nemotron 70B Instruct scores Aider 54.9 (37th percentile). Only benchmarks with published data for this model are shown.
We compare Llama 3.1 Nemotron 70B Instruct with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Nvidia Models

See pricing for all Nvidia models.

View all Nvidia models →