فا

Anthropic: Claude Haiku 5.5

by Anthropic

anthropic/claude-haiku-5.5
UnavailableRank #13No change in 7 daysNew

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

Context

1Mtokens

About 1,429 pages of text at once

Max output

128Ktokens

About 183 pages in one answer

Intelligence

36.2/ 100

Above 68% of the catalogue

Output speed

153tokens/s

A 500-word answer in about 4.6 s

From public market statistics for this model

First token

1.4s

Reasoning models start later

From public market statistics for this model

Health, 30 days

60.61%

0 of 30 days without a fault

IranRouter’s measurements

Price & cost

Every rate in Rial. A request pays only for the tokens it actually uses.

Input273,999IRR / 1M tokens
Output1,369,994IRR / 1M tokens
Reasoning tokensThe output rate1,369,994IRR / 1M tokens
Cache read27,400IRR / 1M tokens
Cache write, 5 minutes342,498IRR / 1M tokens
Cache write, 1 hour547,998IRR / 1M tokens
Image input tokensThe input rate273,999IRR / 1M tokens
Per web search27,400IRR

Under these conditions, these rates replace the ones above:

Prompts over 100K tokens

Input1,369,994IRR / 1M tokens
Output6,849,969IRR / 1M tokens
Cache read136,999IRR / 1M tokens
Cache write, 5 minutes1,712,492IRR / 1M tokens
Cache write, 1 hour2,739,988IRR / 1M tokens

With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.

What would this model cost you a month?

Monthly cost

49.32MIRR

1.64M IRR a day, 822 IRR each request

The same work on peer models

Anthropic: Claude Haiku 5.549.32MIRRThis model
Meta: Muse Spark 1.3518.05MIRR950% dearerSpaceXAI: Grok 4.7789.41MIRR1,501% dearerZ.ai: GLM 5.386.32MIRR75% dearer

30 days at today’s rate.

Rial price over 90 days

It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.

InputOutput

Performance, 30 days

Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.

Daily health60.61%

Time to first token1.54 s

Output speed146 tokens/s

Place in the market

By usage across the global model market.

Daily rank#13

Share of the day’s tokens1.8%

Among its peers

Cost of one message against intelligence; this model is highlighted.

Cost of one message, IRR (log scale)

Capabilities

Image inputYes
Audio inputNo
Tool callingYes
JSON outputYes
ReasoningReasoning levels: max, xhigh, high, medium, low, none
Web searchNo
Prompt cacheYes
Makes imagesNo
Open weightsNo
On the free planNo
Input
TextImageFile
Output
Text

Parameters it accepts

include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity

Other benchmarks

Intelligence index36

Design contests

  • 3DElo: 1,340Win rate: 58%
  • Game devElo: 1,321Win rate: 55%
  • Data vizElo: 1,289Win rate: 53%
  • Code (overall)Elo: 1,280Win rate: 51%
3 moreShow less
  • UI componentsElo: 1,278Win rate: 51%
  • WebsitesElo: 1,261Win rate: 49%
  • SVGElo: 1,205Win rate: 44%

Standard tests

  • GPQA DiamondScore: 87%Tasks: 594
  • τ-bench Verified AirlineScore: 73%Tasks: 150

Start in a minute

The official OpenAI and Anthropic SDKs; only the address and the key change.

Base URLhttps://iranrouter.com/v1
Model IDanthropic/claude-haiku-5.5
API keyCreate one in the dashboard
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://iranrouter.com/v1",
    api_key="ir-...",
)

r = client.chat.completions.create(
    model="anthropic/claude-haiku-5.5",
    messages=[{"role": "user", "content": "Hello, introduce yourself"}],
)
print(r.choices[0].message.content)
The full guide in the docs: keys, streaming and errors

Peer models

Its family and models with a close score; the last column compares one message’s cost with this model.

ModelAgainst this model
Meta: Muse Spark 1.3Meta12,67736.41571M928% dearer
SpaceXAI: Grok 4.7xAI19,1873571500K1,456% dearer
Z.ai: GLM 5.3Z.ai2,30231.7821M87% dearer
Google: Gemini 3.8 FlashGoogle9,25130.5741M650% dearer
Meta: Muse Spark 1.313K IRRMeta928% dearerSpaceXAI: Grok 4.719K IRRxAI1,456% dearerZ.ai: GLM 5.32,302 IRRZ.ai87% dearerGoogle: Gemini 3.8 Flash9,251 IRRGoogle650% dearer

Technical specs

ID
anthropic/claude-haiku-5.5
Maker
Anthropic
Tokenizer
Claude
Released
Oct 7, 2026
Added to IranRouter
Oct 8, 2026
Context
1,000,000 tokens
Max output
128,000 tokens

Scores by Artificial Analysis, Design Arena, as of Oct 31, 2026

Anthropic: Claude Haiku 5.5One message about 1,230 IRRStart with this model