Anthropic model prices

Claude Haiku 4.5 API pricing

Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens on this gateway, with a 200K token context window. You reach it with the same key and the same OpenAI-compatible base URL as every other model in the catalogue.

Last updated: October 2026
Input / 1M tokens
$1.00
Output / 1M tokens
$5.00
Context window
200K
Vendor
Anthropic

What does Claude Haiku 4.5 cost per request?

A typical request of 5,000 input tokens and 1,500 output tokens costs about $0.013 at list price. A thousand of those requests costs about $12.50.

WorkloadTokensCost at list price
Single chat turn5K in / 1.5K out$0.013
1,000 chat turns5M in / 1.5M out$12.50
Small production month10M in / 2M out$20.00
Busy production month100M in / 20M out$200

Model usage is drawn from your balance at the upstream list price of each model. Figures above are indicative and exclude any plan fee; the console is the source of truth for live pricing.

Where Claude Haiku 4.5 fits

Claude Haiku 4.5 is the cheapest Anthropic model on the gateway at $1.00 per 1M input tokens, and it is the natural choice for the many small calls an agent makes.

Pick it when

  • You are running sub-agents, file summaries or search steps that do not need deep reasoning.
  • You want Anthropic model behaviour at a price that makes retries affordable.
  • You are moderating, tagging or routing traffic before it reaches an expensive model.

What to watch

  • Long chains of dependent reasoning still work better on Sonnet, so keep the escalate path available.
  • Output at $5.00 per 1M tokens is five times the input rate, which punishes prompts that ask for long answers.

Best for: High-frequency small calls, classification and the cheap role in a two-model Claude setup.

How to call Claude Haiku 4.5 through the gateway

Point your client at https://api.quickrouter.homes/v1 with a QuickRouter key and pass claude-haiku-4-5 as the model name. Nothing else in an OpenAI-style client changes.

curl https://api.quickrouter.homes/v1/chat/completions \
  -H "Authorization: Bearer sk-qr-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-4-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

The console lists the model ids your key can reach - use the id exactly as it appears there.

Frequently asked questions

How much does Claude Haiku 4.5 cost?+

List price on this gateway is $1.00 per 1M input tokens and $5.00 per 1M output tokens, with a 200K token context window.

Can Haiku replace Sonnet?+

For short, well-scoped tasks often yes; for multi-step agent loops it is better used as the cheap step with Sonnet as the fallback.

Is Haiku available in Claude Code?+

Yes. Set ANTHROPIC_MODEL to claude-haiku-4-5 for a session, or switch models from inside the CLI.

One key covers every model in this guide

Create an account, pick a plan and copy an API key. Gateway plans start at $19 per month and model usage is billed at upstream list prices.

Claude Haiku 4.5 API price: $1.00 / 1M input tokens on QuickRouter