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

Command A 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

Command A wins:

  • Larger context window
  • Better at math

Llama 3.3 70B Instruct wins:

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

Pricing Comparison

Price Comparison

MetricCommand ALlama 3.3 70B InstructWinner
Input (per 1M tokens)$2.50$0.10 Llama 3.3 70B Instruct
Output (per 1M tokens)$10.00$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.

Command A Providers

No provider data available

Llama 3.3 70B Instruct Providers

No provider data available

Benchmark Comparison

8
Benchmarks Compared
2
Command A Wins
4
Llama 3.3 70B Instruct Wins

Benchmark Scores

BenchmarkCommand ALlama 3.3 70B InstructWinner
Intelligence Index
Overall intelligence score
13.514.5
Coding Index
Code generation & understanding
9.910.7
Math Index
Mathematical reasoning
13.07.7
MMLU Pro
Academic knowledge
71.271.3-
GPQA
Graduate-level science
52.749.8
LiveCodeBench
Competitive programming
28.728.8-
Aider
Real-world code editing
12.059.4
AIME
Competition math
9.730.0
Command A shows stronger mathematical reasoning abilities.

Cost vs Quality

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

Context & Performance

Context Window

Command A
256,000
tokens
Llama 3.3 70B Instruct
131,072
tokens
Command A has a 49% larger context window.

Speed Performance

MetricCommand ALlama 3.3 70B InstructWinner
Tokens/second35.0 tok/s99.5 tok/s
Time to First Token0.48s0.54s
Llama 3.3 70B Instruct responds 184% faster on average.

Capabilities

Feature Comparison

FeatureCommand ALlama 3.3 70B Instruct
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyCommand ALlama 3.3 70B Instruct
LicenseOpen SourceOpen Source
AuthorCohereMeta-llama
ReleasedMar 2025Dec 2024

Command A Modalities

Input
text
Output
text

Llama 3.3 70B Instruct Modalities

Input
text
Output
text

Related Comparisons

Compare Command A 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 Command A's score of 9.9.
Command A has a 256,000 token context window, while Llama 3.3 70B Instruct has a 131,072 token context window.
Command A does not support vision. Llama 3.3 70B Instruct does not support vision.