# Anthropic models: APIs and prices

Claude models for reasoning, coding and multimodal work. XiaoZhan AIhub offers 14 Anthropic models (Text generation). Call them with one API key through the OpenAI, Anthropic or Gemini SDK; prices are in credits (60 credits = ¥1) and every model page lists the full price.

- Page: https://qd.zsopc.com/en/vendors/anthropic
- Models: 14
- Last updated: 2026-11-17

## Text generation

### Claude Fable 5

Anthropic Fable 5, a Claude 5 variant for long-form writing and storytelling. 200K context. Supports the OpenAI Chat and Anthropic Messages protocols.

- Model ID: `claude-fable-5`
- Page: https://qd.zsopc.com/en/models/claude-fable-5 (Markdown: https://qd.zsopc.com/en/models/claude-fable-5.md)
- Context window: 200,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 2,426 credits (≈ ¥40.44 / ≈ $6) per 1M tokens
    - Output: 12,132 credits (≈ ¥202.2 / ≈ $30) per 1M tokens
    - Cached input: 242.64 credits (≈ ¥4.04 / ≈ $0.6) per 1M tokens
    - Cache write: 3,033 credits (≈ ¥50.55 / ≈ $7.5) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 4,044 credits (≈ ¥67.4 / ≈ $10) per 1M tokens
    - Output: 20,220 credits (≈ ¥337 / ≈ $50) per 1M tokens
    - Cached input: 404.4 credits (≈ ¥6.74 / ≈ $1) per 1M tokens
    - Cache write: 5,055 credits (≈ ¥84.25 / ≈ $12.5) per 1M tokens

### Claude Fable 5.1

Anthropic Fable 5.1, Anthropic's most capable general model, built for the hardest reasoning and long-horizon agent tasks. 1M context. Supports the OpenAI Chat and Anthropic Messages protocols.

- Model ID: `claude-fable-5-1`
- Page: https://qd.zsopc.com/en/models/claude-fable-5-1 (Markdown: https://qd.zsopc.com/en/models/claude-fable-5-1.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 2,426 credits (≈ ¥40.44 / ≈ $6) per 1M tokens
    - Output: 12,132 credits (≈ ¥202.2 / ≈ $30) per 1M tokens
    - Cached input: 60.66 credits (≈ ¥1.01 / ≈ $0.15) per 1M tokens
    - Cache write: 3,033 credits (≈ ¥50.55 / ≈ $7.5) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 4,044 credits (≈ ¥67.4 / ≈ $10) per 1M tokens
    - Output: 20,220 credits (≈ ¥337 / ≈ $50) per 1M tokens
    - Cached input: 101.1 credits (≈ ¥1.68 / ≈ $0.25) per 1M tokens
    - Cache write: 5,055 credits (≈ ¥84.25 / ≈ $12.5) per 1M tokens

### Claude Haiku 4.5

Anthropic Haiku 4.5. 200K context, the fastest and most economical Claude, for high-concurrency and low-latency workloads. Supports all three protocols.

- Model ID: `claude-haiku-4-5-20251001`
- Page: https://qd.zsopc.com/en/models/claude-haiku-4-5-20251001 (Markdown: https://qd.zsopc.com/en/models/claude-haiku-4-5-20251001.md)
- Context window: 200,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 242.64 credits (≈ ¥4.04 / ≈ $0.6) per 1M tokens
    - Output: 1,213 credits (≈ ¥20.22 / ≈ $3) per 1M tokens
    - Cached input: 24.26 credits (≈ ¥0.404 / ≈ $0.06) per 1M tokens
    - Cache write: 303.3 credits (≈ ¥5.06 / ≈ $0.75) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 404.4 credits (≈ ¥6.74 / ≈ $1) per 1M tokens
    - Output: 2,022 credits (≈ ¥33.7 / ≈ $5) per 1M tokens
    - Cached input: 40.44 credits (≈ ¥0.674 / ≈ $0.1) per 1M tokens
    - Cache write: 505.5 credits (≈ ¥8.43 / ≈ $1.25) per 1M tokens

### Claude Haiku 5.5

Anthropic Haiku 5.5, the new lightweight Claude. 1M context, fast and economical; good for high concurrency, classification, extraction and sub-tasks. Supports the OpenAI Chat and Anthropic Messages protocols.

- Model ID: `claude-haiku-5-5`
- Page: https://qd.zsopc.com/en/models/claude-haiku-5-5 (Markdown: https://qd.zsopc.com/en/models/claude-haiku-5-5.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 40.44 credits (≈ ¥0.674 / ≈ $0.1) per 1M tokens
  - Output: 202.2 credits (≈ ¥3.37 / ≈ $0.5) per 1M tokens
  - Cached input: 4.04 credits (≈ ¥0.067 / ≈ $0.01) per 1M tokens
  - Cache write: 50.55 credits (≈ ¥0.842 / ≈ $0.125) per 1M tokens
  - Long-context tier (prompt ≥ 100,001 tokens): input 202.2 credits (≈ ¥3.37 / ≈ $0.5), output 1,011 credits (≈ ¥16.85 / ≈ $2.5)

### Claude Opus 4.5

Anthropic Opus 4.5. 200K context, for reasoning, coding and agent tasks. Supports the OpenAI Chat and Anthropic Messages protocols.

- Model ID: `claude-opus-4-5-20251101`
- Page: https://qd.zsopc.com/en/models/claude-opus-4-5-20251101 (Markdown: https://qd.zsopc.com/en/models/claude-opus-4-5-20251101.md)
- Context window: 200,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 1,213 credits (≈ ¥20.22 / ≈ $3) per 1M tokens
    - Output: 6,066 credits (≈ ¥101.1 / ≈ $15) per 1M tokens
    - Cached input: 121.32 credits (≈ ¥2.02 / ≈ $0.3) per 1M tokens
    - Cache write: 1,517 credits (≈ ¥25.28 / ≈ $3.75) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 2,022 credits (≈ ¥33.7 / ≈ $5) per 1M tokens
    - Output: 10,110 credits (≈ ¥168.5 / ≈ $25) per 1M tokens
    - Cached input: 202.2 credits (≈ ¥3.37 / ≈ $0.5) per 1M tokens
    - Cache write: 2,528 credits (≈ ¥42.13 / ≈ $6.25) per 1M tokens

### Claude Opus 4.6

Anthropic Opus 4.6. 1M context, an all-rounder for reasoning, coding and multimodal work, suited to the hardest tasks. Supports the OpenAI Chat, Anthropic Messages and OpenAI Responses protocols.

- Model ID: `claude-opus-4-6`
- Page: https://qd.zsopc.com/en/models/claude-opus-4-6 (Markdown: https://qd.zsopc.com/en/models/claude-opus-4-6.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 1,213 credits (≈ ¥20.22 / ≈ $3) per 1M tokens
    - Output: 6,066 credits (≈ ¥101.1 / ≈ $15) per 1M tokens
    - Cached input: 121.32 credits (≈ ¥2.02 / ≈ $0.3) per 1M tokens
    - Cache write: 1,517 credits (≈ ¥25.28 / ≈ $3.75) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 2,022 credits (≈ ¥33.7 / ≈ $5) per 1M tokens
    - Output: 10,110 credits (≈ ¥168.5 / ≈ $25) per 1M tokens
    - Cached input: 202.2 credits (≈ ¥3.37 / ≈ $0.5) per 1M tokens
    - Cache write: 2,528 credits (≈ ¥42.13 / ≈ $6.25) per 1M tokens

### Claude Opus 4.7

Anthropic Opus 4.7. 1M context, an all-rounder for reasoning, coding and multimodal work. Supports the OpenAI Chat, Anthropic Messages and OpenAI Responses protocols.

- Model ID: `claude-opus-4-7`
- Page: https://qd.zsopc.com/en/models/claude-opus-4-7 (Markdown: https://qd.zsopc.com/en/models/claude-opus-4-7.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 1,213 credits (≈ ¥20.22 / ≈ $3) per 1M tokens
    - Output: 6,066 credits (≈ ¥101.1 / ≈ $15) per 1M tokens
    - Cached input: 121.32 credits (≈ ¥2.02 / ≈ $0.3) per 1M tokens
    - Cache write: 1,517 credits (≈ ¥25.28 / ≈ $3.75) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 2,022 credits (≈ ¥33.7 / ≈ $5) per 1M tokens
    - Output: 10,110 credits (≈ ¥168.5 / ≈ $25) per 1M tokens
    - Cached input: 202.2 credits (≈ ¥3.37 / ≈ $0.5) per 1M tokens
    - Cache write: 2,528 credits (≈ ¥42.13 / ≈ $6.25) per 1M tokens

### Claude Opus 4.8

Anthropic Opus 4.8. 1M context, the strongest Opus to date, an all-rounder for reasoning, coding and multimodal work, suited to the hardest tasks. Supports all three protocols.

- Model ID: `claude-opus-4-8`
- Page: https://qd.zsopc.com/en/models/claude-opus-4-8 (Markdown: https://qd.zsopc.com/en/models/claude-opus-4-8.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 1,213 credits (≈ ¥20.22 / ≈ $3) per 1M tokens
    - Output: 6,066 credits (≈ ¥101.1 / ≈ $15) per 1M tokens
    - Cached input: 121.32 credits (≈ ¥2.02 / ≈ $0.3) per 1M tokens
    - Cache write: 1,517 credits (≈ ¥25.28 / ≈ $3.75) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 2,022 credits (≈ ¥33.7 / ≈ $5) per 1M tokens
    - Output: 10,110 credits (≈ ¥168.5 / ≈ $25) per 1M tokens
    - Cached input: 202.2 credits (≈ ¥3.37 / ≈ $0.5) per 1M tokens
    - Cache write: 2,528 credits (≈ ¥42.13 / ≈ $6.25) per 1M tokens

### Claude Opus 5

Anthropic Opus 5, the new strongest Opus. 1M context, an all-rounder for reasoning, coding and multimodal work, suited to the hardest tasks. Supports the OpenAI Chat and Anthropic Messages protocols.

- Model ID: `claude-opus-5`
- Page: https://qd.zsopc.com/en/models/claude-opus-5 (Markdown: https://qd.zsopc.com/en/models/claude-opus-5.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 1,213 credits (≈ ¥20.22 / ≈ $3) per 1M tokens
    - Output: 6,066 credits (≈ ¥101.1 / ≈ $15) per 1M tokens
    - Cached input: 121.32 credits (≈ ¥2.02 / ≈ $0.3) per 1M tokens
    - Cache write: 1,517 credits (≈ ¥25.28 / ≈ $3.75) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 2,022 credits (≈ ¥33.7 / ≈ $5) per 1M tokens
    - Output: 10,110 credits (≈ ¥168.5 / ≈ $25) per 1M tokens
    - Cached input: 202.2 credits (≈ ¥3.37 / ≈ $0.5) per 1M tokens
    - Cache write: 2,528 credits (≈ ¥42.13 / ≈ $6.25) per 1M tokens

### Claude Opus 5.5

Anthropic Opus 5.5, the successor to Opus 5. 1M context, stronger at long-horizon agentic coding and knowledge work. Supports the OpenAI Chat and Anthropic Messages protocols.

- Model ID: `claude-opus-5-5`
- Page: https://qd.zsopc.com/en/models/claude-opus-5-5 (Markdown: https://qd.zsopc.com/en/models/claude-opus-5-5.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 970.56 credits (≈ ¥16.18 / ≈ $2.4) per 1M tokens
    - Output: 4,853 credits (≈ ¥80.88 / ≈ $12) per 1M tokens
    - Cached input: 48.53 credits (≈ ¥0.809 / ≈ $0.12) per 1M tokens
    - Cache write: 1,213 credits (≈ ¥20.22 / ≈ $3) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 1,618 credits (≈ ¥26.96 / ≈ $4) per 1M tokens
    - Output: 8,088 credits (≈ ¥134.8 / ≈ $20) per 1M tokens
    - Cached input: 80.88 credits (≈ ¥1.35 / ≈ $0.2) per 1M tokens
    - Cache write: 2,022 credits (≈ ¥33.7 / ≈ $5) per 1M tokens

### Claude Sonnet 4.5

Anthropic Claude Sonnet 4.5: 200K context, reasoning, vision and tool calling.

- Model ID: `claude-sonnet-4-5-20250929`
- Page: https://qd.zsopc.com/en/models/claude-sonnet-4-5-20250929 (Markdown: https://qd.zsopc.com/en/models/claude-sonnet-4-5-20250929.md)
- Context window: 200,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 727.92 credits (≈ ¥12.13 / ≈ $1.8) per 1M tokens
    - Output: 3,640 credits (≈ ¥60.66 / ≈ $9) per 1M tokens
    - Cached input: 72.79 credits (≈ ¥1.21 / ≈ $0.18) per 1M tokens
    - Cache write: 909.9 credits (≈ ¥15.17 / ≈ $2.25) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 1,213 credits (≈ ¥20.22 / ≈ $3) per 1M tokens
    - Output: 6,066 credits (≈ ¥101.1 / ≈ $15) per 1M tokens
    - Cached input: 121.32 credits (≈ ¥2.02 / ≈ $0.3) per 1M tokens
    - Cache write: 1,517 credits (≈ ¥25.28 / ≈ $3.75) per 1M tokens

### Claude Sonnet 4.6

Anthropic Sonnet 4.6. 1M context, the best value, balanced between reasoning and coding. Cached input costs 1/10 of the input price. Supports all three protocols.

- Model ID: `claude-sonnet-4-6`
- Page: https://qd.zsopc.com/en/models/claude-sonnet-4-6 (Markdown: https://qd.zsopc.com/en/models/claude-sonnet-4-6.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 727.92 credits (≈ ¥12.13 / ≈ $1.8) per 1M tokens
    - Output: 3,640 credits (≈ ¥60.66 / ≈ $9) per 1M tokens
    - Cached input: 72.79 credits (≈ ¥1.21 / ≈ $0.18) per 1M tokens
    - Cache write: 909.9 credits (≈ ¥15.17 / ≈ $2.25) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 1,213 credits (≈ ¥20.22 / ≈ $3) per 1M tokens
    - Output: 6,066 credits (≈ ¥101.1 / ≈ $15) per 1M tokens
    - Cached input: 121.32 credits (≈ ¥2.02 / ≈ $0.3) per 1M tokens
    - Cache write: 1,517 credits (≈ ¥25.28 / ≈ $3.75) per 1M tokens

### Claude Sonnet 5

Anthropic Sonnet 5, the new best-value flagship. 1M context, balanced between reasoning and coding. Supports the OpenAI Chat, Anthropic Messages and OpenAI Responses protocols.

- Model ID: `claude-sonnet-5`
- Page: https://qd.zsopc.com/en/models/claude-sonnet-5 (Markdown: https://qd.zsopc.com/en/models/claude-sonnet-5.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - 40% OFF right now; these are the prices charged:
    - Input: 485.28 credits (≈ ¥8.09 / ≈ $1.2) per 1M tokens
    - Output: 2,426 credits (≈ ¥40.44 / ≈ $6) per 1M tokens
    - Cached input: 48.53 credits (≈ ¥0.809 / ≈ $0.12) per 1M tokens
    - Cache write: 606.6 credits (≈ ¥10.11 / ≈ $1.5) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 808.8 credits (≈ ¥13.48 / ≈ $2) per 1M tokens
    - Output: 4,044 credits (≈ ¥67.4 / ≈ $10) per 1M tokens
    - Cached input: 80.88 credits (≈ ¥1.35 / ≈ $0.2) per 1M tokens
    - Cache write: 1,011 credits (≈ ¥16.85 / ≈ $2.5) per 1M tokens

### Claude Sonnet 5.5

Anthropic Sonnet 5.5, the successor to Sonnet 5. 1M context, balancing speed, cost and capability; strong at documents, code and agent tasks. Supports the OpenAI Chat and Anthropic Messages protocols.

- Model ID: `claude-sonnet-5-5`
- Page: https://qd.zsopc.com/en/models/claude-sonnet-5-5 (Markdown: https://qd.zsopc.com/en/models/claude-sonnet-5-5.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 111.32 credits (≈ ¥1.86 / ≈ $0.275) per 1M tokens
  - Output: 556.62 credits (≈ ¥9.28 / ≈ $1.38) per 1M tokens
  - Cached input: 5.58 credits (≈ ¥0.093 / ≈ $0.014) per 1M tokens
  - Cache write: 139.15 credits (≈ ¥2.32 / ≈ $0.344) per 1M tokens

Prices are in credits, 60 credits = ¥1. The prices above are what is charged today (limited-time discounts included); ≈¥ / ≈$ use the platform's published rates.

## FAQ

### How do I call Anthropic models?

Create an API key on XiaoZhan AIhub, point your SDK's base_url at https://qd.zsopc.com/v1 and put the model ID from the list above in the model field. The OpenAI, Anthropic and Gemini SDKs all work.

### How are Anthropic models billed?

Each model is billed its own way: text models per input and output token, image models per image, video models per second or per token. Prices are in credits (60 credits = ¥1); each model page lists the full price.
