Back
Anthropic: Claude 3 Haiku
Claude
Input: text
Input: image
Output: text
Released: Mar 13, 2024•Updated: Mar 28, 2025
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance.
See the launch announcement and benchmark results here
#multimodal
200,000 Token Context
Process and analyze large documents and conversations.
Advanced Coding
Improved capabilities in front-end development and full-stack updates.
Agentic Workflows
Autonomously navigate multi-step processes with improved reliability.
Vision Capabilities
Process and understand images alongside text inputs.
Available On
| Provider | Model ID | Context | Max Output | Input Cost | Output Cost | Throughput | Latency |
|---|---|---|---|---|---|---|---|
| Anthropic | anthropic | 200K | 4K | $0.25/M | $1.25/M | 149.1 t/s | 606 ms |
| Google Vertex | vertex | 200K | 4K | $0.25/M | $1.25/M | 153.5 t/s | 1288 ms |
Standard Pricing
Input Tokens
$0.00000025
per 1K tokens
Output Tokens
$0.00000125
per 1K tokens
Image Processing
$0.0004
per image
Input Cache Read
$0.00000003
per 1K tokens
Input Cache Write
$0.0000003
per 1K tokens