Anthropic: Claude Haiku 4.5
Analysis Summary
Claude Haiku 4.5 is Anthropic's latest lightweight flagship, and it punches well above its price class. With a coding index of 43.9 and agentic index of 41, it sits in the excellent tier for both dimensions, supported by a livecodebench score of 0.615 and a terminalbench hard score of 0.272. The long-context reliability score of 0.703 is among the strongest in this batch, and the ifbench score of 0.543 confirms reliable instruction following. Vision, file input, tool use, and function calling make it a broad-capability model.
For businesses, it is well suited to coding assistance, agentic task automation, long-document analysis, and client-facing content generation. The 200K context window handles large codebases and contracts comfortably. The intelligence index of 29.6 places it below frontier reasoning models, so it is not the first choice for the most complex analytical tasks, but for the vast majority of business workloads it delivers reliable, high-quality output.
At $1/1M input and $5/1M output, it offers strong value relative to its capability breadth. Teams looking for a dependable, multi-purpose model from a trusted provider will find Haiku 4.5 a compelling default choice for production workflows.
Assessed June 30, 2026
Editorial notes
Claude Haiku 4.5 from Anthropic delivers strong coding, agentic, and long-context performance with vision and file support at $1/1M input, making it a highly capable and cost-efficient model for business workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Anthropic: Claude Haiku 4.5 compares
Anthropic: Claude Haiku 4.5 ranks #82 of 385 AI models we track for overall intelligence, #39 of 129 for coding, #117 of 293 for agentic tasks. Its 200K-token context window is larger than 65% of the models we list. At $1.00 per million input tokens it is cheaper than 25% of comparable models.
About Anthropic: Claude Haiku 4.5
Claude Haiku 4.5 is Anthropicās fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4ās performance..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Anthropic: Claude Haiku 4.5 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
anthropic/claude-haiku-4.5
|
| Provider | anthropic |
| Release Date | October 15, 2025 |
| Context Length | 200,000 tokens |
| Max Completion | 64,000 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.00 | $0.001000 |
| Output | $5.00 | $0.005000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Anthropic: Claude Haiku 4.5
How much does Anthropic: Claude Haiku 4.5 cost?
Anthropic: Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens.
What is the context window of Anthropic: Claude Haiku 4.5?
Anthropic: Claude Haiku 4.5 has a context window of 200,000 tokens (200K).
Is Anthropic: Claude Haiku 4.5 good for coding?
On our coding benchmark index, Anthropic: Claude Haiku 4.5 ranks #39 of 129 models, placing it in the broader range of the field for code generation and debugging.
What can Anthropic: Claude Haiku 4.5 do?
Anthropic: Claude Haiku 4.5 supports image/vision input, tool use, and function calling.
Who created Anthropic: Claude Haiku 4.5?
Anthropic: Claude Haiku 4.5 is developed by Anthropic and was released on October 15, 2025.
