AiCostCompare

Claude Haiku 4.5 vs Inkling 2 Small

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Inkling 2 Small (Thinkingmachines). Green cells mark the better value in each row.

Prices updated Nov 17, 2026, 12:20 PM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

Inkling 2 Small

Thinkingmachines

Pricing
Input $/1M$1.00$0.30
Output $/1M$5.00$1.00
Blended $/1M (3:1)$2.00$0.475
RAG example (30K in / 2K out)$0.04$0.011
Quality & speed
Intelligence Index7.430.6
Coding Index43.9—
Agentic Index8—
Output speed (tok/s)——
Time to first token——
Specs
Context window200K1.05M
Input modalitiestext, image, filetext, image

FAQ

Which is cheaper, Claude Haiku 4.5 or Inkling 2 Small?

Inkling 2 Small has the lower blended API price at $0.475 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), Inkling 2 Small costs about $0.011 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Inkling 2 Small offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

Inkling 2 Small leads on the Artificial Analysis Intelligence Index (30.6 vs 7.4). Check coding and agentic indices on this page for workload-specific tradeoffs.