claude-3-haiku pricing
claude-3-haiku is priced at $0.25 per 1M input tokens and $1.25 per 1M output tokens, with roughly 160 ms to first token and about 55 tokens/sec output throughput.
Price per 1M tokens
Input $0.25 · Output $1.25 · Output/input ratio 5.0x.
- 1M input + 1M output tokens: $1.50
- 10M input + 2M output tokens/month: $5.00
- 100M input + 20M output tokens/month: $50.00
Cheaper alternatives to claude-3-haiku
Same workload, lower output price. Validate quality before switching.
- gpt-5-nano — $1.20/1M output (4% cheaper)
- claude-haiku-4 — $1.00/1M output (20% cheaper)
- llama-4-behemoth — $1.00/1M output (20% cheaper)
- amazon-nova-lite — $0.80/1M output (36% cheaper)
How much are you wasting on claude-3-haiku?
Price lists are the easy part. Run the free waste scanner on your usage export to see which calls should have run on a cheaper tier, which prompts are oversized, and which retries you paid for twice — with dollars recoverable per finding.