Claude Haiku 4.5

anthropic/claude-haiku-4.5Anthropic~anthropic/claude-haiku-latestoperational

The fastest Claude model with near-frontier intelligence. 200K context, extended thinking.

Official pricing

USD per million tokens, exactly what Anthropic publishes. ElevenRouter adds no markup on tokens.

Input
$1.00
Output
$5.00
Cache read
$0.100
Cache write
$1.25

Example: 1,000 input + 500 output tokens ≈ $0.00350. Zero-completion responses are never charged.

Specs

Context
200K
Max output
64K
Modalities
text+image+file->text
Tokenizer
Claude
Released
2026-09-20
Family
claude-haiku
Tool calling Structured outputs JSON mode Reasoning Vision Audio input Prompt caching Streaming

Availability on ElevenRouter

Measured by the routing engine; up when at least one credential can serve the model.

Last 3 days
100.00%
Last 30 days
100.00%
30 days agotoday
Full status page

Observed performance

Real requests over the last 7 days.

Time to first token p50
p95
Output tokens/s p50
p95

Percentiles appear after five successful requests.

Usage on ElevenRouter

Tokens per day across all customers (anonymous, aggregate).

0 tokens · 30d
0 requests in the last 7 days

Use it

Any OpenAI or Anthropic SDK works by changing the base URL. Supported parameters: max_tokens, temperature, top_p, top_k, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs.

curl https://elevenrouter.com/api/v1/chat/completions \
  -H "Authorization: Bearer $ELEVENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "anthropic/claude-haiku-4.5", "messages": [{ "role": "user", "content": "Hello" }] }'

Related models

Frequently asked questions

How much does Claude Haiku 4.5 cost on ElevenRouter?

Claude Haiku 4.5 is billed at Anthropic's official list price: $1.00 per million input tokens and $5.00 per million output tokens, with cached input at $0.100. A request with 1,000 input and 500 output tokens costs about $0.00350.

What is the context length of Claude Haiku 4.5?

Claude Haiku 4.5 accepts up to 200K tokens of context and can produce up to 64K output tokens.

Does Claude Haiku 4.5 support tool calling and structured outputs?

Yes, tool calling is supported and JSON-schema structured outputs are native. Supported parameters: max_tokens, temperature, top_p, top_k, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs.

How do I call Claude Haiku 4.5?

Send an OpenAI-compatible chat completion to https://elevenrouter.com/api/v1/chat/completions with "model": "anthropic/claude-haiku-4.5" and your ElevenRouter key, or use the Anthropic Messages endpoint. Any OpenAI or Anthropic SDK works by changing the base URL.

Is Claude Haiku 4.5 available right now?

Availability is measured continuously by the routing engine. Current status: operational, 100.00% uptime over the last 30 days. When one credential fails, requests fail over to another automatically.

Claude Haiku 4.5 by Anthropic — pricing, context, availability · ElevenRouter