Curated models for your best work

Join the waitlist
Log inGet API key

Claude Haiku 5.5

  • Vision
  • Tool calling
  • Reasoning
  • Streaming
  • 1M context
  • Runs on Anthropic

Model id

anthropic/claude-haiku-5-5
APITry this model
Context window
1M
tokens
Input price
$0.1
per 1M tokens
Output price
$0.5
per 1M tokens
Max output
128K
tokens

Provider list price

Pricing

USD / 1M tokens

Input$0.1 / M tokens
Output$0.5 / M tokens
Cache read$0.01 / M tokens
Cache write (5 min)$0.125 / M tokens
Cache write (1 hour)$0.2 / M tokens
Past 100K prompt tokens$0.5 in / $2.5 out per M$0.05 cache read$0.625 cache write
Context window1M tokens
RoutingFree

Provider list price. BYOK bills your provider; managed credits draw down at these rates. No markup or request fee. Every request is metered per engineer and joined to shipped work.

Registry 2026-10-21.3 · effective 9/17/2026 · Anthropic API pricing

Registry contract

Capabilities

Protocols
3
Chat · Responses · Messages · streaming
Tools
2
Chat · Messages
JSON Schema
None
Not supported
Vision
Yes
Chat · Responses · Messages
Reasoning
1
Messages
Output limit
128,000
tokens

canonical anthropic/claude-haiku-5-5 · revision anthropic/claude-haiku-5-5 · aliases claude-haiku-5-5

First request

Run it

Python · TokenSpend SDK
from tokenspend import TokenSpend

client = TokenSpend()
resp = client.chat.completions.create(
    model="anthropic/claude-haiku-5-5",
    messages=[{"role": "user", "content": "hello"}],
)
TypeScript · TokenSpend SDK
import { TokenSpend } from "@tokenspend/sdk";

const client = new TokenSpend();
const resp = await client.chat.completions.create({
  model: "anthropic/claude-haiku-5-5",
  messages: [{ role: "user", content: "hello" }]
});
curl
curl https://api.tokenspend.dev/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $TOKENSPEND_API_KEY" \
  -d '{"model":"anthropic/claude-haiku-5-5","messages":[{"role":"user","content":"hello"}]}'
Claude Code integration
export ANTHROPIC_BASE_URL=https://api.tokenspend.dev
export ANTHROPIC_API_KEY=$TOKENSPEND_API_KEY
export ANTHROPIC_MODEL=anthropic/claude-haiku-5-5

One request shape reaches every model. Claude Code connects as an integration with two environment variables. TokenSpend never stores prompts or responses.

Questions

Who runs Claude Haiku 5.5?

Anthropic runs it, at the list price above. A request that fails there fails with an error, because there is no second provider to move to.

What does Claude Haiku 5.5 cost?

$0.10 per 1M input tokens and $0.50 per 1M output tokens, rising to $0.50 and $2.50 past 100K prompt tokens. TokenSpend adds no markup and no per-request fee. If you pay with managed credits, buying them carries a 5% fee.

What can I do with Claude Haiku 5.5 through TokenSpend?

Chat and streaming, plus tool calling (Chat, Messages), image input (Chat, Messages) and reasoning controls (Messages). It does not support JSON schema output here. Tool calling and JSON schema are enabled per provider, only after that provider passes our tests, so a provider chosen by hand may lack them.

How long can my prompt be?

1M tokens of context, prompt and reply together, with up to 128,000 tokens in a single reply.

Does prompt caching make Claude Haiku 5.5 cheaper?

Yes, when the provider caches a repeated prompt prefix. Cached input is billed at $0.01 per 1M tokens instead of $0.10, and writing to the cache costs $0.125 per 1M tokens.

How current is this pricing?

It follows rate card 2026-10-21.3, effective 9/17/2026. Source: Anthropic API pricing.