NVIDIA

Llama 3.3 70b Instruct — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCENVIDIA
Input Cost
$0.10/1M
Output Cost
$0.32/1M
Context Window
131K
Max Output
4K
Accepts
text

Llama 3.3 70b Instruct by NVIDIA demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

Coding Benchmarks

AA Coding Index
11.987th of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)

Reasoning Benchmarks

GPQA Diamond
49.2%115th of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
38.7%87th of 93

Multi-turn service agent making tool calls under strict policy constraints

OpenRouter (measured)

Cost Benchmarks

Input Cost
$0.10114th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$0.32137th of 413

Cost per 1M output tokens

OpenRouter API

Context Benchmarks

Context Length
131K212th of 451

Maximum context window size

OpenRouter API

Available from 33 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 6 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Llama$0$0128K
Nvidia$0$0128K
Pendra$0$0128K
Vercel AI Gateway$0$0128KSupported
NanoGPT$0.05$0.23$0.025131K
Kilo Gateway$0.1$0.32131K
Meganova$0.1$0.3131K
OpenRouter$0.1$0.32131KSupported
Cortecs$0.129$0.399131K
IO.NET$0.13$0.38$0.065128K
DevPass (LLM Gateway)$0.135$0.4131K
NovitaAI$0.135$0.4131K
Merge Gateway$0.22$0.5$0.11131K
Crusoe$0.25$0.75$0.13128K
Neon$0.5$1.5128K
Abacus$0.59$0.79131K
Hugging Face$0.59$0.79131KSupported
Regolo AI$0.6$2.7128K
Charm Hyper$0.6066$1.0386$0.3033128K
Azure$0.71$0.71128KSupported
Azure Cognitive Services$0.71$0.71128K
Amazon Bedrock$0.72$0.72128KSupported
Vertex$0.72$0.72128KSupported
watsonx.ai$0.7526$0.7526131K
Eden AI$0.75348$0.75348128K
LLM Gateway$0.85$1.2128K
Pioneer$0.9$0.9$0.916K
Scaleway$0.9$0.9100K
evroc$1.15$1.15128K
GreenPT$1.254$1.254100K
Tinfoil$1.75$2.75131K
CloudFerro Sherlock$2.92$2.9270K
Snowflake Cortex128K

Llama 3.3 70b Instruct — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Llama 3.3 70b Instruct — Frequently Asked Questions

How much does Llama 3.3 70b Instruct cost?

Llama 3.3 70b Instruct costs $0.10 per 1M input tokens and $0.32 per 1M output tokens. This makes it one of the more affordable models.

What is the context window of Llama 3.3 70b Instruct?

Llama 3.3 70b Instruct has a context window of 131K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Llama 3.3 70b Instruct?

Llama 3.3 70b Instruct was created by NVIDIA. It is classified as a open source model in our catalogue.

Is Llama 3.3 70b Instruct open source?

Yes, Llama 3.3 70b Instruct is an open-source model. The model weights are publicly available for download and self-hosting.