ChatModelsComparePricingDocs
CouncilClaude CodeCursorCheapest modelsBest for codingFor agentsFree models
LiveAdded 7 Oct 2026Anthropic

Claude Haiku 5.5 API

Anthropic's cheapest and fastest Claude: a big step up from Haiku 4.5 in coding, computer use and knowledge work, at $0.10 / $0.50 per 1M tokens for prompts up to 100K.

Open playgroundView API docs

Model spec

Input
$0.10per 1M tokens
Output
$0.50per 1M tokens
Cached input
$0.01per 1M tokens
Context
1M
Max output
128K

Prompts over 100K tokens bill at $0.50 / $2.50.

Model ID

OpenAI-compatible · api.companyfabric.com/v1

Overview

About Claude Haiku 5.5

Claude Haiku 5.5 is Anthropic's cheapest and fastest Claude, released on 7 October 2026. Anthropic says it costs around 75% less to run than Claude Haiku 4.5 while being a large step up in coding, computer use and knowledge work, and pitches it for high-volume work (summaries, classification, extraction, live customer support) and as a sub-agent under Claude Opus 5.5 or Sonnet 5.5. It has a 1M-token context window and 128K output, reads images, and thinks adaptively by default. Pricing depends on prompt length: up to 100K tokens it is $0.10 input and $0.50 output per million tokens; above that the whole request bills at $0.50 / $2.50. On CompanyFabric it is one key and one balance with every other model. Every model on CompanyFabric shares the same API key, billing balance, and rate-limit envelope, one integration covers the entire library.

Facts

At a glance

Availability

Live

Added 7 Oct 2026

Pricing

$0.10 in · $0.50 out

Per 1M tokens, metered exactly per call

Context window

1M tokens

Up to 128K tokens out

Commercial use

See license

Commercial use of outputs permitted per Anthropic's usage policies.

Variants

All endpoints

Claude Sonnet 4.5

Retiring$3/Mtok in

Frontier-quality text and reasoning through one OpenAI-compatible endpoint.

Chat Completions

Claude Haiku 4.5

$1/Mtok in

Fast, cheap frontier-family model for high-volume tasks.

Chat Completions

Claude Opus 4.6

$5/Mtok in

The frontier tier for the hardest reasoning and agentic work.

Chat Completions

Claude Fable 5

$10/Mtok in

Anthropic's first Mythos-class model, the new flagship tier above Opus, tuned for the hardest reasoning and agentic work.

Chat Completions

Claude Opus 5

$5/Mtok in

The Claude 5 generation's deep-work model, maximum-capability reasoning for research, architecture, and hard agentic tasks.

Chat Completions

Claude Opus 5.5

$4/Mtok in

First of the Claude 5.5 generation: Fable-class agentic coding and computer use at 20% below Opus 5.

Chat Completions

Claude Sonnet 5.5

$2/Mtok in

The fast Claude 5.5: near-Opus coding and knowledge work, 30%+ faster than Sonnet 5, at half Opus 5.5's price.

Chat Completions

Claude Fable 5.1

$10/Mtok in

Anthropic's top generally available model, tied for first on the Artificial Analysis Intelligence Index.

Chat Completions

Claude Haiku 5.5

$0.1/Mtok in

Anthropic's cheapest and fastest Claude: a big step up from Haiku 4.5 in coding, computer use and knowledge work, at $0.10 / $0.50 per 1M tokens for prompts up to 100K.

Chat Completions

Quickstart

How to use the Claude Haiku 5.5 API

  1. 1

    Create a free CompanyFabric account, starter credits are included, no card required.

  2. 2

    Copy your API key from the dashboard. One key covers every model in the library.

  3. 3

    Point any OpenAI SDK at api.companyfabric.com/v1 and set model to "anthropic/claude-haiku-5-5".

  4. 4

    Read the exact metered cost of the call from the response, the same number shown in the playground.

Use cases

What teams build with it

Agents & copilots

Drive agent loops, tool calls, and user-facing assistants over the OpenAI-compatible endpoint.

agentstool useassistants

Content pipelines

Summarization, rewriting, and structured generation at metered per-token cost.

contentsummarization

Extraction & classification

Turn unstructured input into typed JSON with schema-constrained output.

extractionjson mode

Get better output

Prompting tips

  • State the output format before the task, models follow contracts declared early.
  • Few-shot beats description: two worked examples outperform a paragraph of rules.
  • Cap output length explicitly when cost matters; output tokens dominate most bills.

Exact, metered, prepaid

Claude Haiku 5.5 pricing

Claude Haiku 5.5 pricing is per token: $0.1 / M input · $0.5 / M output · $0.01 / M cached input. Output tokens cost 5× input tokens, so long generations, not long prompts, are what actually drive most bills. A typical call with a 2k-token prompt and a 1k-token answer costs about $0.0007.

Every call is metered exactly and attributed to your key, the dashboard, the API usage response, and your invoice all read from the same ledger row. Cap any key's monthly spend with a budget cap, and bring your own provider key (BYOK) at 0% platform fee if you already have a direct contract.

EndpointTypePrice
Claude Sonnet 4.5Chat$3 / M input · $15 / M output
Claude Haiku 4.5Chat$1 / M input · $5 / M output
Claude Opus 4.6Chat$5 / M input · $25 / M output
Claude Fable 5Chat$10 / M input · $50 / M output
Claude Opus 5Chat$5 / M input · $25 / M output
Claude Opus 5.5Chat$4 / M input · $20 / M output
Claude Sonnet 5.5Chat$2 / M input · $10 / M output
Claude Fable 5.1Chat$10 / M input · $50 / M output
Claude Haiku 5.5Chat$0.1 / M input · $0.5 / M output · $0.01 / M cached input

Starter credits

Use Claude Haiku 5.5 free

Your CompanyFabric starter credits cover your first Claude Haiku 5.5 calls at no cost, create a free account, no card required, and the credits apply to Claude Haiku 5.5 and every other model on the key. When they run out, prepaid credits or BYOK (0% fee) take over with no plan to pick.

All ways to use AI models free →

Production-grade

Code samples

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.companyfabric.com/v1",
  apiKey: process.env.COMPANYFABRIC_API_KEY,
})

const res = await client.chat.completions.create({
  model: "anthropic/claude-haiku-5-5",
  max_tokens: 1024,
  temperature: 0.7,
  messages: [{ role: "user", content: "Say hello from the fabric." }],
})

console.log(res.choices[0].message.content)

Playground

Try it in the browser

PlaygroundClaude$0.1 in / $0.5 out per 1M tokens

Comparisons

Claude Haiku 5.5 vs the alternatives

Claude Haiku 5.5 vs GPT-6 Luna

Claude Haiku 5.5 and GPT-6 Luna compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.

Full comparison: Claude Haiku 5.5 vs GPT-6 Luna →

Claude Haiku 5.5 vs Gemini 3.7 Flash

Claude Haiku 5.5 and Gemini 3.7 Flash compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.

Full comparison: Claude Haiku 5.5 vs Gemini 3.7 Flash →

Claude Haiku 5.5 vs DeepSeek V4.1 Flash

Claude Haiku 5.5 and DeepSeek V4.1 Flash compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.

Full comparison: Claude Haiku 5.5 vs DeepSeek V4.1 Flash →

Compare

Claude Haiku 5.5 head to head

Claude Haiku 5.5vsGPT-6 LunaClaude Haiku 5.5vsGemini 3.7 FlashClaude Haiku 5.5vsDeepSeek V4.1 FlashClaude Haiku 5.5vsGLM-5.3-FlashClaude Haiku 5.5vsGemini 3.1 Flash-LiteClaude Haiku 5.5vsMiMo-V2.6-Pro

FAQ

Frequently asked questions

How do I get a Claude Haiku 5.5 API key?

Create a CompanyFabric account, and one key unlocks Claude Haiku 5.5 and every other model in the library. Free starter credits are included, no subscription, no card required to try it.

Why use Claude Haiku 5.5 on CompanyFabric instead of going direct?

One key, one prepaid balance, and one rate-limit envelope across the whole library, at pricing at parity with or below the direct API. Model switching is a one-line change, and BYOK routing is 0% fee.

Is the API OpenAI-compatible?

Yes, point any OpenAI SDK at api.companyfabric.com/v1 and set model to "anthropic/claude-haiku-5-5".

Can I use the output commercially?

Commercial use of outputs permitted per Anthropic's usage policies.

How does billing work?

Prepaid credits via card, or BYOK with your own provider keys at 0% platform fee. No subscription required; balances never expire.

How much does the Claude Haiku 5.5 API cost?

For prompts up to 100,000 tokens: $0.10 per million input tokens, $0.50 per million output tokens and $0.01 per million cached input tokens. For longer prompts the whole request bills at $0.50 / $2.50 / $0.05. Anthropic says about 90% of requests to its previous Haiku were under 100K tokens. Haiku 4.5 is $1 / $5 at any length.

How does Claude Haiku 5.5 compare with Haiku 4.5 and GPT-6 Luna?

On Anthropic's published table Haiku 5.5 scores 72.4% on OSWorld 2.1 computer use (Haiku 4.5: 15.7%, GPT-6 Luna: 48.9%), 39.2% on Terminal-Bench 4.0 (Luna: 16.4%) and 46.4% on FrontierCode 1.1 (Luna: 42.4%). These are Anthropic's numbers, not independent results. GPT-6 Luna has the same headline price, $0.10 / $0.50.

Does Claude Haiku 5.5 accept temperature?

No. Anthropic rejects non-default temperature and top_p on this model. CompanyFabric drops them for you, as it does for the other current Claude models, so an OpenAI SDK that sends temperature by default still works.

Why did my Haiku 5.5 request return no text?

Haiku 5.5 thinks before answering by default, and that thinking counts toward max_tokens. A very small max_tokens (say 50) can be used up before any answer is written. Leave room: 1,000 or more for short answers.

Provider

About Anthropic

Anthropic publishes the claude family. Also in this family: Claude Sonnet 4.5, Claude Haiku 4.5, Claude Opus 4.6, Claude Fable 5, Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1. License: Commercial use of outputs permitted per Anthropic's usage policies.

One key. Every model. Exact prices.

Run Claude Haiku 5.5 with free starter credits. Free starter credits included, no subscription required.

Get your API keyBrowse all models