Claude Haiku 5.5 vs North Small Translate

Side by side: price, limits, capabilities and real cost examples. Catalog data · checked Nov 16, 2026

Short answer

  • Claude Haiku 5.5 reads 31× more text per request (1M vs 32.8K tokens).
  • Only Claude Haiku 5.5 offers: tool calling, structured output, reasoning mode, image input, file input, prompt caching.
  • A quality verdict needs a hands-on test. Neither model has completed our Hero suite yet, so this page compares facts, not output quality.
Claude Haiku 5.5AnthropicNorth Small TranslateCohere
Input price / 1M tokens$0.1$0
Output price / 1M tokens$0.5$0
Context window1M32.8K
Max output per answer128K16K
ReleasedOct 2026Sep 2026
Tool callingYesNo
Structured outputYesNo
Reasoning modeYesNo
Image inputYesNo
File inputYesNo
Prompt cachingYesNo
What it costs in practice
1,000 support replies1,000 chats with 800 input and 250 output tokens each$0.205$0
Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out$0.016$0
10,000 product descriptions300 input and 200 output tokens per text$1.3$0
One day of agentic codingabout 3M input and 150K output tokens across many calls$0.375$0

Green marks the better value in that row. Prices are first-party list prices in USD. Method.

Calculate with my numbersCompare with another model