AiCostCompare

Claude Haiku 4.5 vs Llama 3 8B Lunaris

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Llama 3 8B Lunaris (Sao10k). Green cells mark the better value in each row.

Prices updated Nov 17, 2026, 7:38 AM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

Llama 3 8B Lunaris

Sao10k

Pricing
Input $/1M$1.00$0.04
Output $/1M$5.00$0.05
Blended $/1M (3:1)$2.00$0.042
RAG example (30K in / 2K out)$0.04$0.0013
Quality & speed
Intelligence Index7.4—
Coding Index43.9—
Agentic Index8—
Output speed (tok/s)——
Time to first token——
Specs
Context window200K8K
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Haiku 4.5 or Llama 3 8B Lunaris?

Llama 3 8B Lunaris has the lower blended API price at $0.042 per 1M tokens (3:1 input:output mix), versus $2.00 for the other model. Prices are live from OpenRouter and refresh nightly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), Llama 3 8B Lunaris costs about $0.0013 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Llama 3 8B Lunaris offers 8K.

Which scores higher on Artificial Analysis benchmarks?

Claude Haiku 4.5 leads on the Artificial Analysis Intelligence Index (7.4 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.