Llama 3.1 405B (Fireworks) vs InternLM 2.5 20B: Pricing, Benchmarks & Verdict (2026)

Pricing verified Apr 8, 2026

⚡ Quick Answer

Compare Llama 3.1 405B (Fireworks) and InternLM 2.5 20B across pricing, benchmarks, and capabilities.

Updated: April 8, 2026 · ✓ Pricing verified

Side-by-Side Comparison

FeatureLlama 3.1 405B (Fireworks)InternLM 2.5 20B
ProviderFireworks AIShanghai AI Lab
Input Price / 1M tokens$3.00$0.180
Output Price / 1M tokens$3.00$0.180
Context Window
131.072K
32K
Max Output Tokens
4,096
4,096
Arena ELO
1,240
1,155
Coding ELO
1,200
1,150
TTFT (ms)
150
150
Tokens/sec
100
100
MultimodalNoNo
JSON ModeYesYes
Function CallingYesYes
VisionNoNo
When to Use Llama 3.1 405B (Fireworks)

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

Strengths:

  • Largest model
  • High quality
  • Large context

Best for:

general-purposereasoning
When to Use InternLM 2.5 20B

InternLM 2.5 20B excels at cost-effective, general-purpose tasks.

Strengths:

  • Very affordable
  • Good instruction following
  • Fast

Best for:

cost-effectivegeneral-purpose

Related Comparisons