claude-3-haiku-20240307
- Input / 1M
- $0.25
- Output / 1M
- $1.25
- Cached input
- $0.03
- Context
- 200K
A 1,000-token prompt costs $0.00025 to send. Token counts for Anthropic models are estimated — approximated, because this family has no public tokenizer.
- Vision
- Tool calling
- Max output 4K
Writing to the cache costs $0.30 per million at the 5-minute TTL, $6.00 at one hour. Reads are $0.03.
Priced closest to this
| Model | Provider | Input | Output | |
|---|---|---|---|---|
| gemini-3.1-flash-lite | $0.25 | $1.50 | ||
| gemini-3.1-flash-lite-preview | $0.25 | $1.50 | ||
| gpt-5-mini | OpenAI | $0.25 | $2.00 | |
| codestral-mamba-latest | Mistral | $0.25 | $0.25 | |
| mistral-tiny | Mistral | $0.25 | $0.25 | |
| open-codestral-mamba | Mistral | $0.25 | $0.25 |