Llama 3.1 405B (Together) vs Yi-Lightning: Pricing, Benchmarks & Verdict (2026)

Pricing verified Apr 8, 2026

⚡ Quick Answer

Compare Llama 3.1 405B (Together) and Yi-Lightning across pricing, benchmarks, and capabilities.

Updated: April 8, 2026 · ✓ Pricing verified

Side-by-Side Comparison

FeatureLlama 3.1 405B (Together)Yi-Lightning
ProviderTogether AI01.AI
Input Price / 1M tokens$3.50$0.140
Output Price / 1M tokens$3.50$0.140
Context Window
4K
16K
Max Output Tokens
4,096
4,096
Arena ELO
1,240
1,165
Coding ELO
1,200
1,170
TTFT (ms)
150
150
Tokens/sec
100
100
MultimodalNoNo
JSON ModeYesYes
Function CallingYesYes
VisionNoNo
When to Use Llama 3.1 405B (Together)

Llama 3.1 405B (Together) excels at general-purpose, reasoning tasks.

Strengths:

  • Largest model
  • High quality
  • Good pricing

Best for:

general-purposereasoning
When to Use Yi-Lightning

Yi-Lightning excels at cost-effective, fast-inference tasks.

Strengths:

  • Very cheap
  • Very fast
  • Good quality

Best for:

cost-effectivefast-inference

Related Comparisons