AiCostCompare

Claude Haiku 4.5 vs gpt-oss-120b (batch)

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and gpt-oss-120b (batch) (OpenAI). Green cells mark the better value in each row.

Prices updated Nov 17, 2026, 5:09 PM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

gpt-oss-120b (batch)

OpenAI

Pricing
Input $/1M$1.00$0.03
Output $/1M$5.00$0.136
Blended $/1M (3:1)$2.00$0.056
RAG example (30K in / 2K out)$0.04$0.00116
Quality & speed
Intelligence Index7.43.8
Coding Index43.930.4
Agentic Index83.7
Output speed (tok/s)——
Time to first token——
Specs
Context window200K131K
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Haiku 4.5 or gpt-oss-120b (batch)?

gpt-oss-120b (batch) has the lower blended API price at $0.056 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), gpt-oss-120b (batch) costs about $0.00116 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and gpt-oss-120b (batch) offers 131K.

Which scores higher on Artificial Analysis benchmarks?

Claude Haiku 4.5 leads on the Artificial Analysis Intelligence Index (7.4 vs 3.8). Check coding and agentic indices on this page for workload-specific tradeoffs.