Anthropic

Claude Haiku 5.5

claude-haiku-5-5

Fastest Claude model for high-volume, latency-sensitive tasks

Claude Haiku 5.5 is for high-volume, latency-sensitive work such as classification, extraction, and routing. The API id is claude-haiku-5-5. It accepts text and image input, with a 1M context window, up to 128K output tokens, and adaptive thinking at a default effort of medium. The overview lists pricing from $0.10/M input and $0.50/M output. The Cursor price table lists $0.10 input, $0.125 cache write, $0.01 cache read, and $0.50 output (verified 2026-10-09).

1M context1M context
Released2026-10-07
Relays84 sites
reasoningtool usefast

Model information

Model ID
claude-haiku-5-5
Context
1M
Max input
-
Max output
128K
Knowledge cutoff
2026-06
Open weights
Not supported
License
-
Release date
2026-10-07

Input

Text: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported

Output

Text: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported

API capabilities

Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported

Anthropic Official Pricing

CNY
Updated: 2026-10-08T04:13:03.408+08:00

Input

~¥0.6686/ 1M tokens

Output

~¥3.343/ 1M tokens

Cache read

~¥0.0669/ 1M tokens

Cache write

~¥0.8358/ 1M tokens

Relay Comparison

Compare token, per-request, or per-second pricing by relay channel.

Modelflare

https://origin.modelflare.devToken billing

Price range ¥0.166 - ¥0.332 / 1M tokens

claude-award
BillingToken
Input¥0.166
Output¥0.83
Cache hit¥0.0166
Cache write¥0.2075
claude-stable
BillingToken
Input¥0.2092
Output¥1.05
Cache hit¥0.0209
Cache write¥0.2615
claude-premium
BillingToken
Input¥0.332
Output¥1.66
Cache hit¥0.0332
Cache write¥0.415

88API Token聚合平台

https://88api.ai/sign-up?aff=po46Token billing

Price range ¥0.14 - ¥0.28 / 1M tokens

Claude Max池 可外接
BillingToken
Input¥0.14
Output¥0.7
Cache hit¥0.014
Cache write¥0.28
Claude VIP池
BillingToken
Input¥0.21
Output¥1.05
Cache hit¥0.021
Cache write¥0.42
Claude 官转 可蒸馏
BillingToken
Input¥0.28
Output¥1.4
Cache hit¥0.028
Cache write¥0.56

9527code

https://9527.codesToken billing

Price range ¥0.035 - ¥0.15 / 1M tokens

claude-kiro(满缓存)
BillingToken
Input¥0.035
Output¥0.175
Cache hit¥0.0035
Cache write¥0.0437
claude-特惠活动
BillingToken
Input¥0.145
Output¥0.725
Cache hit¥0.0145
Cache write¥0.1812
claude
BillingToken
Input¥0.15
Output¥0.75
Cache hit¥0.015
Cache write¥0.1875

sidrune

https://sidrune.ai/Token billing

Price range ¥0.1 - ¥0.14 / 1M tokens

Claude-Max-cc
BillingToken
Input¥0.1
Output¥0.5
Cache hit¥0.01
Cache write¥0.2
Claude-Max-外接
BillingToken
Input¥0.12
Output¥0.6
Cache hit¥0.012
Cache write¥0.24
Claude-Max超低注入
BillingToken
Input¥0.14
Output¥0.7
Cache hit¥0.014
Cache write¥0.28

8sToken

8stoken.comToken billing

Price range ¥0.038 - ¥0.09 / 1M tokens

Claude-Kiro企业
BillingToken
Input¥0.038
Output¥0.19
Cache hit¥0.0038
Cache write¥0.076
Claude满血
BillingToken
Input¥0.06
Output¥0.3
Cache hit¥0.006
Cache write¥0.12
Claude-AWSB逆向
BillingToken
Input¥0.09
Output¥0.45
Cache hit¥0.009
Cache write¥0.18

How should Claude Haiku 5.5 relay pricing be compared?

This Claude Haiku 5.5 pricing page compares official pricing with public prices from 84 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: 11/08/2026, 08:15.

Data sources
Public price catalogs, official pricing records, and monitoring results.
Metric definitions
Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
Risk note
Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.