Task Shortlist · High-volume pipelines
Best API models for high-volume pipelines
Cheap and fast, at scale.
Trade-offs & Editorial Note
For classification, extraction, routing and subagents, token price dominates. Haiku 5.5 and Luna cost the same up to 100K prompt tokens, but Haiku scores higher. Above 100K, Haiku’s price rises 5×.
1
Claude Haiku 5.5Anthropic
Classification, extraction, routing, summaries, subagents and browser use at very low cost.
Benchmark $0.41/task · $0.10 in / $0.50 out per 1M
36.5INDEX
Dossier 2
GPT-6 LunaOpenAI
Simple, high-volume text and image tasks where price matters most.
Benchmark $0.15/task · $0.10 in / $0.50 out per 1M
27.9INDEX
Dossier 3
Gemini 4 HydrogenGoogle
Everyday coding, multimodal work and agents.
Benchmark $3.16/task · $1.50 in / $7.50 out per 1M
53.9INDEX
Dossier 4
Targeted edits, explanations, routine fixes and rapid iteration.
No token price