Rapid code completion, customer service, fast structured parsing
Stored values, not live provider measurements.
| Provider | Anthropic |
| Category | Cost-Efficient |
| Input cost / 1M tokens | $0.800 |
| Output cost / 1M tokens | $4.00 |
| Cache read / 1M tokens | $0.080 |
| Context window | 200k tokens |
| Max output | 8k tokens |
| Batch API | Supported |
| Vision | Supported |
| Vision price / 1k images | $0.400 |
| Speed rating | Unrated |
| Intelligence score | Unrated |
| Throughput | Unrated |
| Time to first token | Unrated |
| Hardware | AWS Trainium2 / NVIDIA H100 |
Enter your own input, output, caching, and batch assumptions in the calculator.
Open calculatorPricing review: date not recorded
Performance review: source/date not recorded
Claude 3.5 Haiku costs $0.800 per 1M input tokens and $4.000 per 1M output tokens in the stored catalog. Blended cost depends on your input/output mix.
Claude 3.5 Haiku has a context window of 200k tokens (200,000 tokens). This is the maximum combined input and output for a single request.
Claude 3.5 Haiku is retired by its provider; the recommended successor is claude-haiku-5-5.