読み込み中…
Observed 2026-06-03 11:12. Prices are USD per 1M tokens (from OpenRouter public pricing). Input: Claude Haiku 4.5 $1 / GPT-4o $2.5, output: $5 / $10.
✓ = the mechanically better side per row (cheaper price / longer context). Magnitude only, not a rating.
| Field | Claude Haiku 4.5 anthropic/claude-haiku-4.5 | GPT-4o openai/gpt-4o |
|---|---|---|
| Input priceUSD/1M | $1✓ | $2.5 |
| Output priceUSD/1M | $5✓ | $10 |
| Cache readUSD/1M | $0.1 | Accumulating… |
| Context windowtokens | 200k✓ | 128k |
Source: OpenRouter /api/v1/models → collect_prices.py → Source(price)。 · Claude Haiku 4.5: anthropic/claude-haiku-4.5 · GPT-4o: openai/gpt-4o
Aggregated observations, not predictions. Prices change (observation time noted). © TraceBottle for AI
As observed on 2026-06-03 11:12, input is Claude Haiku 4.5 $1 / GPT-4o $2.5 per 1M tokens — Claude Haiku 4.5 is cheaper. Output is $5 / $10 — Claude Haiku 4.5 is cheaper.
Claude Haiku 4.5: 200,000 tokens, GPT-4o: 128,000 tokens (observed 2026-06-03 11:12).
Observed 2026-06-03 11:12 (UTC). Source: OpenRouter public pricing (/api/v1/models). Prices change — check each provider's official pricing for the latest. This site publishes only observed values, never predictions.