claude-haiku-4-5
- Input / 1M
- $1.00
- Output / 1M
- $5.00
- Cached input
- $0.10
- Context
- 200K
A 1,000-token prompt costs $0.00100 to send. Token counts for Anthropic models are estimated — approximated, because this family has no public tokenizer.
- Vision
- Tool calling
- Reasoning
- Max output 64K
Writing to the cache costs $1.25 per million at the 5-minute TTL, $2.00 at one hour. Reads are $0.10.
Pinned versions at the same rate: claude-haiku-4-5-20251001
Priced closest to this
| Model | Provider | Input | Output | |
|---|---|---|---|---|
| gemini-robotics-er-1.6-preview | $1.00 | $5.00 | ||
| gpt-3.5-turbo-1106 | OpenAI | $1.00 | $2.00 | |
| codestral-2405 | Mistral | $1.00 | $3.00 | |
| codestral-latest | Mistral | $1.00 | $3.00 | |
| kimi-latest-32k | Moonshot | $1.00 | $3.00 | |
| moonshot-v1-32k | Moonshot | $1.00 | $3.00 |