Claude Haiku Latest
Claude Haiku Latest is a large language model made by Anthropic, added to the catalog on 27 Apr 2026. It has a context window of 1,000,000 tokens and costs $0.10 per 1M input tokens and $0.50 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: summarising lengthy documents, answering questions about supplied images and drafting structured text from reference material.
Price checked · source: OpenRouter
What Claude Haiku Latest is
Anthropic: Claude Haiku Latest is a model entry that redirects to the latest model in the Claude Haiku family. Its target may therefore follow the family’s latest model rather than identify a fixed version. The listed interface accepts text, images, and files, and produces text. The catalog specifies a context length of 1,000,000 tokens and a maximum output of 128,000 tokens, giving it room to work with long inputs or produce lengthy responses within those limits.
The model supports reasoning, tool use, structured outputs, and response-format controls. These features suit tasks where a text response needs to follow a defined format, draw on supplied material, or use tools as part of an interaction. Inputs can include documents and images as well as text, while the output remains text; audio is not listed as a supported input or output. The large context can accommodate extensive reference material in one request, such as a long document or conversation, though context length alone does not guarantee a particular answer quality. Potential uses include summarising supplied documents, answering questions about images, and drafting structured text from lengthy context. The catalog does not specify particular tools, file formats, or domain-specific capabilities, so those should not be assumed from the listed support alone.
Key features
- Accepts text, images, and files; produces text
- Has a context length of 1,000,000 tokens
- Supports a maximum output of 128,000 tokens
- Supports tools, reasoning, structured outputs, and response formats
- Redirects to the latest model in the Claude Haiku family
Typical uses
- Summarising lengthy documents
- Answering questions about supplied images
- Drafting structured text from reference material
- Working with long text inputs
- Tool-assisted text tasks
Claude Haiku Latest pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.10 |
| Output, per 1M tokens | $0.50 |
| Cached input read, per 1M tokens | $0.01 |
| Cache write, per 1M tokens | $0.125 |
| Web search, per search | $0.01 |
| Input above 100,000 prompt tokens, per 1M | $0.50 |
| Output above 100,000 prompt tokens, per 1M | $2.50 |
No price change since it was added on 27 Apr 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0029 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0040 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.079 |
Claude Haiku Latest specifications
| Model id | ~anthropic/claude-haiku-latest |
|---|---|
| Version | claude-haiku-latest |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 27 Apr 2026 |
| Input types | text, image, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Claude Haiku Latest yet.
Compare Claude Haiku Latest
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.