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

Llama 3.1 405B (base) vs Llama 3.3 70B Instruct

A detailed comparison of pricing, benchmarks, and capabilities

112 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

Llama 3.1 405B (base) wins:

  • No clear advantages in compared metrics

Llama 3.3 70B Instruct wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
Price Advantage
Llama 3.3 70B Instruct
Benchmark Advantage
Llama 3.3 70B Instruct
Context Window
Llama 3.3 70B Instruct
Speed
Llama 3.3 70B Instruct

Pricing Comparison

Price Comparison

MetricLlama 3.1 405B (base)Llama 3.3 70B InstructWinner
Input (per 1M tokens)$4.00$0.10 Llama 3.3 70B Instruct
Output (per 1M tokens)$4.00$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 96% cheaper overall.

Llama 3.1 405B (base) Providers

No provider data available

Llama 3.3 70B Instruct Providers

No provider data available

Benchmark Comparison

8
Benchmarks Compared
0
Llama 3.1 405B (base) Wins
0
Llama 3.3 70B Instruct Wins

Benchmark Scores

BenchmarkLlama 3.1 405B (base)Llama 3.3 70B InstructWinner
Intelligence Index
Overall intelligence score
-14.5-
Coding Index
Code generation & understanding
-10.7-
Math Index
Mathematical reasoning
-7.7-
MMLU Pro
Academic knowledge
-71.3-
GPQA
Graduate-level science
-49.8-
LiveCodeBench
Competitive programming
-28.8-
Aider
Real-world code editing
-59.4-
AIME
Competition math
-30.0-
Llama 3.3 70B Instruct significantly outperforms in coding benchmarks.

Cost vs Quality

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

Context & Performance

Context Window

Llama 3.1 405B (base)
32,768
tokens
Llama 3.3 70B Instruct
131,072
tokens
Llama 3.3 70B Instruct has a 75% larger context window.

Speed Performance

MetricLlama 3.1 405B (base)Llama 3.3 70B InstructWinner
Tokens/secondN/A95.0 tok/s
Time to First TokenN/A0.55s

Capabilities

Feature Comparison

FeatureLlama 3.1 405B (base)Llama 3.3 70B Instruct
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyLlama 3.1 405B (base)Llama 3.3 70B Instruct
LicenseOpen SourceOpen Source
AuthorMeta-llamaMeta-llama
ReleasedAug 2024Dec 2024

Llama 3.1 405B (base) Modalities

Input
text
Output
text

Llama 3.3 70B Instruct Modalities

Input
text
Output
text

Related Comparisons

Compare Llama 3.1 405B (base) 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.
Llama 3.3 70B Instruct scores higher on coding benchmarks with a score of 10.7, compared to Llama 3.1 405B (base)'s score of N/A.
Llama 3.1 405B (base) has a 32,768 token context window, while Llama 3.3 70B Instruct has a 131,072 token context window.
Llama 3.1 405B (base) does not support vision. Llama 3.3 70B Instruct does not support vision.