Models & pricing

Zero data retention pricing for all models

XiuAI does not store request content or model responses. Data privacy details

Prices are in USD per 1M tokens. Per-request prices are labeled separately.

Create an API key Read the quickstart

Average savings64.5%Managed

Average savings

64.5%

Managed

Managed · Up to 93% lower than provider API prices

Available models

Pay for what you use

Most used in the last 24 hours

claude-opus-5-5

By token usage

37 models · 43 model IDs

Input prices

USD per 1M tokens · Each dot is a model; prices increase to the right.

$0.06$0.37148$2.30

glm-5.3

Uncensored

Input: $0.63
Output: $1.98

USD / 1M tokens

55% off

claude-opus-5-5

Input: $0.92
Output: $4.60

USD / 1M tokens

77% off

gpt-6.1-sol

Input: $0.14
Output: $0.70

USD / 1M tokens

93% off

gemini-4-argon

Input: $0.40
Output: $2.00

USD / 1M tokens

80% off

kimi-k3.1-pro

Input: $1.16
Output: $5.80

USD / 1M tokens

42% off

deepseek-v4.1-flash

Input: $0.075
Output: $0.30

USD / 1M tokens

50% off

qwen3.8-flash

Input: $0.06695
Output: $0.20977

USD / 1M tokens

55.4% off

glm-5.2

Input: $0.59369
Output: $1.87

USD / 1M tokens

57.6% off

claude-opus-5

Input: $1.15
Output: $5.75

USD / 1M tokens

77% off

gpt-6.1-terra

Input: $0.07
Output: $0.35

USD / 1M tokens · Input up to 272K

93% off

Model	Reference price per 1M tokens	Tier price	Capabilities / Success rate
glm-5.3Uncensored Zhipu AI55% off	Reference price InputUSD $1.40 OutputUSD $4.40 Cache readUSD $0.26 Cache writeUSD —	Tier priceManaged InputUSD $0.63 OutputUSD $1.98 Cache readUSD $0.117 Cache writeUSD —
claude-opus-5-5 Anthropic77% off	Reference price InputUSD $4.00 OutputUSD $20.00 Cache readUSD $0.20 Cache write (5 min)USD $5.00	Tier priceManaged InputUSD $0.92 OutputUSD $4.60 Cache readUSD $0.046 Cache writeUSD $1.15
gpt-6.1-solDynamic tiers OpenAI93% off	Reference price Input up to 272K InputUSD $2.00 OutputUSD $10.00 Cache readUSD $0.10 Cache writeUSD $2.50 Input above 272K InputUSD $4.00 OutputUSD $15.00 Cache readUSD $0.20 Cache writeUSD $5.00	Tier priceManaged InputUSD $0.14 OutputUSD $0.70 Cache readUSD $0.0070 Cache writeUSD — Fast ×2.5 · Ultrafast ×8
gemini-4-argon GoogleNative thinking levels: low / medium / high80% off	Reference price InputUSD $2.00 OutputUSD $10.00 Cache readUSD $0.10 Cache writeUSD —	Tier priceManaged InputUSD $0.40 OutputUSD $2.00 Cache readUSD $0.02 Cache writeUSD —
kimi-k3.1-pro Moonshot42% off	Reference price InputUSD $2.00 OutputUSD $10.00 Cache readUSD $0.20 Cache writeUSD $2.00	Tier priceManaged InputUSD $1.16 OutputUSD $5.80 Cache readUSD $0.116 Cache writeUSD $1.16	Provider specifications
deepseek-v4.1-flash DeepSeek50% off	Reference price InputUSD $0.15 OutputUSD $0.60 Cache readUSD $0.0030 Cache writeUSD —	Tier priceManaged InputUSD $0.075 OutputUSD $0.30 Cache readUSD $0.0015 Cache writeUSD —
qwen3.8-flash Alibaba55.4% off	Reference price Alibaba Cloud · Singapore InputUSD $0.15 OutputUSD $0.47 Implicit cache readUSD $0.016 Explicit cache creationUSD $0.20	Tier priceManaged InputUSD $0.06695 OutputUSD $0.20977 Cache readUSD $0.0071 Cache writeUSD $0.08926	Provider specifications
glm-5.2 Zhipu AI57.6% off	Reference price InputUSD $1.40 OutputUSD $4.40 Cache readUSD $0.26 Cache writeUSD —	Tier priceManaged InputUSD $0.59369 OutputUSD $1.87 Cache readUSD $0.11026 Cache writeUSD —	Provider specifications
claude-opus-5 Anthropic77% off	Reference price InputUSD $5.00 OutputUSD $25.00 Cache readUSD $0.50 Cache write (5 min)USD $6.25	Tier priceManaged InputUSD $1.15 OutputUSD $5.75 Cache readUSD $0.115 Cache writeUSD $1.44
gpt-6.1-terraDynamic tiers OpenAI93% off	Reference price Input up to 272K InputUSD $1.00 OutputUSD $5.00 Cache readUSD $0.05 Cache writeUSD $1.25 Input above 272K InputUSD $2.00 OutputUSD $7.50 Cache readUSD $0.10 Cache writeUSD $2.50	Tier priceManaged Input up to 272K InputUSD $0.07 OutputUSD $0.35 Cache readUSD $0.0035 Cache writeUSD $0.0875 Input above 272K InputUSD $0.14 OutputUSD $0.525 Cache readUSD $0.0070 Cache writeUSD $0.175 Fast ×2.5

Showing 1–10 of 37

Pricing notes

See each model for current prices and availability.

Usage-based pricing

Charges are based on the model, service tier, and actual input, output, and cache usage.

Four supported API protocols

Use the model’s native API: OpenAI Chat Completions or Responses, Anthropic Messages, or Gemini GenerateContent.

Current availability

Availability shown here is not an SLA.

Faster processing

Fast and Ultrafast multipliers are listed with each model’s prices. Ultrafast requires Pro $500 or an eligible organization and is subject to upstream rate limits and capacity.

Gemini thinking levels

Thinking levels are grouped under each Gemini model and share one reference price. See the model row for available levels and Agent integrations for setup instructions.

View integrations Pricing and usage FAQ