Claude Haiku 4.5 (batch)
Anthropic · Multimodal · Released Oct 2025
Claude Haiku 4.5 in batch mode is Anthropic's fastest and most cost-efficient model, designed for asynchronous processing with a 200k-token context window.
- Strengths
- Delivers near-frontier reasoning performance at the lowest latency and cost among Claude models, matching Sonnet-tier intelligence in many tasks.
- Best for
- High-volume, time-insensitive workloads where speed and efficiency matter more than extended reasoning, such as classification, summarization, and straightforward question-answering at scale.
- Limitations
- The 200k-token context window is smaller than Opus or Sonnet, and batch processing introduces latency unsuitable for real-time applications; newer Sonnet and Opus releases have expanded capabilities that Haiku does not match on complex reasoning tasks.
Input / 1M
$0.5
Output / 1M
$2.50
Cached input / 1M
$0.05
Context window
200K
Also billed
- Cache write
- $0.625 / 1M
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 28 Jul 2026 | $0.5 | $2.50 | $0.05 | Imported from OpenRouter | openrouter.ai |