Home/Models/Claude Sonnet 4.5
MODEL DOSSIER / ENGLISH

Claude Sonnet 4.5

claude-sonnet-4-5

Anthropictext2025-09-29

Claude Sonnet 4.5 is a text model from Anthropic. The snapshot records a release date of 2025-09-29. Context window: 200K tokens. Maximum output: 64K tokens. Input: text, images, PDF. Output: text. Capabilities recorded: reasoning, tool calls.

Directory snapshot 2026-10-26 · Chinese dossier: 完整中文页

Context200K
Max output64K
Inputtext, images, PDF
Outputtext
Official input¥20.05 / 1M
Official output¥100.27 / 1M
Capabilitiesreasoning, tool calls
Release2025-09-29

Official list price

CNY / 1M TOKENS

Official list price in the directory snapshot: ¥20.05 input and ¥100.27 output per 1M tokens, in CNY. Relay prices below are what individual sites listed; they can be lower or higher, and they are not official prices.

Relay coverage

24 SITES

24 sites in our public directory listed this model ID in the 2026-10-26 snapshot. Listed relay price range: ¥0.1075–¥94.125 per 1M input tokens. A listing means the model appeared on the site's public model list; it is not proof that the site serves the genuine model.

SiteDomainRelay price / 1MVerification
找模型api.zhaomoxing.com¥0.1075–¥0.688enterprise
Token 88t8api.com¥0.18–¥0.45enterprise
API快连apikl.ai¥0.18–¥0.45enterprise
MuskAIapi.muskapi.cc¥0.18–¥0.57enterprise
DragonAPInewapi.dragon3api.com¥0.3–¥0.66enterprise
尚猫中心shanmaoapi.com¥0.33–¥0.51—
迈威AImxwell.ai¥0.36–¥2.85—
Toknextoknex.me¥0.39–¥0.75enterprise
JBB金贝贝jbbt.cc¥0.4–¥1enterprise
Monikeraimoniker.top¥0.45–¥1.2enterprise
Super APIsuperapi.buzz¥0.45–¥4.5—
Keda8AIkeda8.ai¥0.51—
LinoRoutelinoroute.com¥0.52944–¥1.76472personal
luchikeysub2api.luchikey.com¥0.6–¥3.6enterprise
sidrunesidrune.ai¥0.75–¥1.8personal
8sToken8stoken.com¥0.75enterprise
幻灵AIapi.huanling.icu¥0.75–¥2.1—
合聚APIhejuapi.com¥0.9enterprise
9527code9527.codes¥1.05–¥3enterprise
ITKKitkk.lol¥1.05—
智流 FluxLanefluxlane.cn¥1.2–¥3.6enterprise
VovoKey|启界vovokey.com¥1.2–¥14.4enterprise
模方api.modelscube.com¥1.35personal
xem中转站ai.xem8k5.top¥1.365–¥94.125—

How to verify this model on a relay

THREE STEPS
  1. Send a short request to the relay and read the model field in the response. It must match the ID you sent; a different ID is a mapping, not necessarily a substitution.
  2. Run the same prompt against a known-good endpoint and compare prompt-token counts. A large, repeatable gap points at a different tokenizer or a different backend.
  3. Run the seven checks. Billing, context retention, error shape, parameter compliance, tools, and streaming each produce evidence you can quote.

Same publisher

Anthropic

Questions

FAQ

What is the context window of Claude Sonnet 4.5?

The snapshot records 200,000 tokens.

How much does Claude Sonnet 4.5 cost?

Official list price: ¥20.05 input / ¥100.27 output per 1M tokens in CNY, per the directory snapshot. 24 relay sites listed it at ¥0.1075–¥94.125 per 1M input tokens.

Is a relay really serving Claude Sonnet 4.5?

A model ID in a response is not proof. The seven-check detection compares tokenizer ratios, billing, error shape, parameter compliance, tools, and streaming against the advertised family. Run it on a key you can afford to spend, and treat one run as a spot check, not 24/7 monitoring.

Specifications and prices come from the 2026-10-26 public directory snapshot. We do not publish IQ scores or structured-output claims for models where we have no reliable data.