Claude Haiku 5.5
anthropic/claude-haiku-5-5Fast adaptive reasoning for high-volume coding and assistant workloads.
Official price: $0.1Sale price: $0.07Official price: $0.5Sale price: $0.3530% off- Text, Image
- 1M
- Oct 7, 2026
Overview
Fast adaptive reasoning for high-volume coding and assistant workloads. It is billed from the same balance as every other model and tool here, and the price of each call comes back in the response.
Run Claude Haiku 5.5 with an agent
Each guide pairs this model with a currently compatible agent, explains their separate roles, and opens the shared Composer with both selections ready.
- Open guide
Hermes + Claude Haiku 5.5
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
Claude Code + Claude Haiku 5.5
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
OpenCode + Claude Haiku 5.5
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
goose + Claude Haiku 5.5
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
Kilo + Claude Haiku 5.5
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
- Open guide
MiniMax Code + Claude Haiku 5.5
Compatibility, setup, current model facts, pricing boundaries, and a preselected Composer.
Pricing
30% offPrices in USD per million tokens, using your plan when signed in.
Each request uses the tier matching its full input context, including cached input. Output tokens do not choose the tier. Choose the row for your cache and thinking modes.
| Input context (tokens) | Cache mode | Thinking | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|---|
| Up to 100,000 | Automatic | Standard | ||||
| 100,001–1,000,000 | Automatic | Standard |
Your balance and per-call records come from /v1/credits and /v1/generation.
Use it
Point your client at the gateway and pass this model id. Nothing else changes.
import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({
baseURL: "https://gateway.agentsky.dev",
apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});
const message = await client.messages.create({
model: "anthropic/claude-haiku-5-5",
max_tokens: 256,
messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(message.usage.cost); // USD, in the response