Price Per TokenPrice Per Token
Amazon
Amazon
vs
Meta-llama
Meta-llama

Nova Pro 1.0 vs Llama 3.3 70B Instruct

A detailed comparison of pricing, benchmarks, and capabilities

108 out of our 483 tracked models have had a price change in March.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Nova Pro 1.0 wins:

  • Larger context window
  • Better at coding
  • Supports vision

Llama 3.3 70B Instruct wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
  • Higher intelligence benchmark
  • Better at math
Price Advantage
Llama 3.3 70B Instruct
Benchmark Advantage
Llama 3.3 70B Instruct
Context Window
Nova Pro 1.0
Speed
Llama 3.3 70B Instruct

Pricing Comparison

Price Comparison

MetricNova Pro 1.0Llama 3.3 70B InstructWinner
Input (per 1M tokens)$0.80$0.10 Llama 3.3 70B Instruct
Output (per 1M tokens)$3.20$0.32 Llama 3.3 70B Instruct
Cache Read (per 1M)N/A$0.13 Llama 3.3 70B Instruct
Using a 3:1 input/output ratio, Llama 3.3 70B Instruct is 89% cheaper overall.

Nova Pro 1.0 Providers

No provider data available

Llama 3.3 70B Instruct Providers

No provider data available

Benchmark Comparison

8
Benchmarks Compared
0
Nova Pro 1.0 Wins
6
Llama 3.3 70B Instruct Wins

Benchmark Scores

BenchmarkNova Pro 1.0Llama 3.3 70B InstructWinner
Intelligence Index
Overall intelligence score
13.514.5
Coding Index
Code generation & understanding
11.010.7-
Math Index
Mathematical reasoning
7.07.7
MMLU Pro
Academic knowledge
69.171.3
GPQA
Graduate-level science
49.949.8-
LiveCodeBench
Competitive programming
23.328.8
Aider
Real-world code editing
54.159.4
AIME
Competition math
10.730.0
Llama 3.3 70B Instruct wins 6 out of 8 benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Nova Pro 1.0
Other models

Context & Performance

Context Window

Nova Pro 1.0
300,000
tokens
Llama 3.3 70B Instruct
131,072
tokens
Nova Pro 1.0 has a 56% larger context window.

Speed Performance

MetricNova Pro 1.0Llama 3.3 70B InstructWinner
Tokens/second0.0 tok/s99.5 tok/s
Time to First Token0.00s0.54s
Llama 3.3 70B Instruct responds Infinity% faster on average.

Capabilities

Feature Comparison

FeatureNova Pro 1.0Llama 3.3 70B Instruct
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyNova Pro 1.0Llama 3.3 70B Instruct
LicenseProprietaryOpen Source
AuthorAmazonMeta-llama
ReleasedDec 2024Dec 2024

Nova Pro 1.0 Modalities

Input
textimage
Output
text

Llama 3.3 70B Instruct Modalities

Input
text
Output
text

Related Comparisons

Compare Nova Pro 1.0 with:

Compare Llama 3.3 70B Instruct with:

Frequently Asked Questions

Llama 3.3 70B Instruct has cheaper input pricing at $0.10/M tokens. Llama 3.3 70B Instruct has cheaper output pricing at $0.32/M tokens.
Nova Pro 1.0 scores higher on coding benchmarks with a score of 11.0, compared to Llama 3.3 70B Instruct's score of 10.7.
Nova Pro 1.0 has a 300,000 token context window, while Llama 3.3 70B Instruct has a 131,072 token context window.
Nova Pro 1.0 supports vision. Llama 3.3 70B Instruct does not support vision.