Claude 3.5 HaikuPricing
- Input Tokens: $1 /M tokens
- Output Tokens: $5 /M tokens
Input Modalities
- Text
- Vision
Output Modalities
- Text
Capabilities
- Tools
- Tool calling
- Structured outputs
Providers
Performance for claude-3-5-haiku
Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).
Try this model
Frequently asked questions
Compare Claude 3.5 Haiku
More models from Anthropic
See all Anthropic models →- Input: $ 5 /M
- Output: $ 25 /M
- Web Search: $0.01/request
Claude Opus 4.5 is Anthropic’s latest frontier reasoning model, optimized for complex engineering, agentic workflows, and long-horizon computer use. It features strong multimodal capabilities, improved resistance to prompt injection, and a new Verbosity parameter to control token efficiency. With advanced tool use, extended context, and multi-agent support, Opus 4.5 excels in autonomous research, debugging, planning, and spreadsheet/browser operations.
- Input: $ 5 /M
- Output: $ 25 /M
- Web Search: $0.01/request
Claude Opus 4.5 is Anthropic’s latest frontier reasoning model, optimized for complex engineering, agentic workflows, and long-horizon computer use. It features strong multimodal capabilities, improved resistance to prompt injection, and a new Verbosity parameter to control token efficiency. With advanced tool use, extended context, and multi-agent support, Opus 4.5 excels in autonomous research, debugging, planning, and spreadsheet/browser operations.
- Input: $ 5 /M
- Output: $ 25 /M
- Web Search: $0.01/request
Claude Opus 4.5 is Anthropic’s latest frontier reasoning model, optimized for complex engineering, agentic workflows, and long-horizon computer use. It features strong multimodal capabilities, improved resistance to prompt injection, and a new Verbosity parameter to control token efficiency. With advanced tool use, extended context, and multi-agent support, Opus 4.5 excels in autonomous research, debugging, planning, and spreadsheet/browser operations.
- Input: $ 5 /M
- Output: $ 25 /M
- Web Search: $0.01/request
Claude Opus 4.5 is Anthropic’s latest frontier reasoning model, optimized for complex engineering, agentic workflows, and long-horizon computer use. It features strong multimodal capabilities, improved resistance to prompt injection, and a new Verbosity parameter to control token efficiency. With advanced tool use, extended context, and multi-agent support, Opus 4.5 excels in autonomous research, debugging, planning, and spreadsheet/browser operations.
- Input: $ 5 /M
- Output: $ 25 /M
- Web Search: $0.01/request
Claude Opus 4.5 is Anthropic’s latest frontier reasoning model, optimized for complex engineering, agentic workflows, and long-horizon computer use. It features strong multimodal capabilities, improved resistance to prompt injection, and a new Verbosity parameter to control token efficiency. With advanced tool use, extended context, and multi-agent support, Opus 4.5 excels in autonomous research, debugging, planning, and spreadsheet/browser operations.
- Input: $ 5 /M
- Output: $ 25 /M
- Web Search: $0.01/request
Claude Opus 4.5 is Anthropic’s latest frontier reasoning model, optimized for complex engineering, agentic workflows, and long-horizon computer use. It features strong multimodal capabilities, improved resistance to prompt injection, and a new Verbosity parameter to control token efficiency. With advanced tool use, extended context, and multi-agent support, Opus 4.5 excels in autonomous research, debugging, planning, and spreadsheet/browser operations.
