google/gemini-3.1-pro-preview, anthropic/claude-sonnet-4.6, google/gemini-3-pro-image-preview are Now Live

Claude Sonnet 4 will be retired by both providers: AWS Bedrock and Anthropic on June 14, 2026. We recommend upgrading to Claude Sonnet 4.6.

Claude Opus 4 will be retired by both providers: AWS Bedrock on May 31, 2026 and Anthropic on June 14, 2026. We recommend upgrading to Claude opus 4.7.

Qwen3 Max Thinking Preview will be deprecated and removed on April 24, 2026. We recommend upgrading to Qwen3-Max-Thinking.

Caution: On Azure, gpt-5-chat will be deprecated and removed on May 15, 2026.

Claude 3.7 Sonnet will be retired by both providers: AWS Bedrock on April 28, 2026, and Google Cloud Vertex AI on May 11, 2026. We recommend upgrading to Claude Sonnet 4.6.

A billing anomaly was identified. Affected users will receive compensation. Read more.

Model Pricing
Transparent pricing, pay per usage

Model Provider Publish Time Input Output Cache Web Search Image Reasoning Video Audio Audio Cache Read Audio Input Audio & Video Operations
Z.AI: GLM 4.6V Flash (Free) BigModel 2025-12-08 0≤Input<32
$0.021
/M tokens
32≤Input<∞
$0.043
/M tokens		 0≤Input<32
$0.21
/M tokens
32≤Input<∞
$0.43
/M tokens		 0≤Input<32
$0.0043
/M tokens
32≤Input<∞
$0.0043
/M tokens		 -
/M tokens		 -
/M tokens		 -
/M tokens		 $0.01
/count		 -
/count		 -
/M tokens		 -
/count		 -
/count		 -
/M tokens
OpenAI: GPT-4.1 Mini OpenAI 2025-04-14 $0.4
/M tokens		 $1.6
/M tokens		 $0.1
/M tokens		 -
/M tokens		 -
/M tokens		 -
/M tokens		 -
/count		 -
/count		 -
/M tokens		 -
/count		 -
/count		 -
/M tokens
Anthropic: Claude Opus 4 Amazon Bedrock 2025-05-22 $15
/M tokens		 $75
/M tokens		 $1.5
/M tokens		 $18.75
/M tokens		 -
/M tokens		 -
/M tokens		 -
/count		 -
/count		 -
/M tokens		 -
/count		 -
/count		 -
/M tokens

Note: Prices in $/M tokens (per million tokens). Input = input token price, Output = output token price. Cache pricing available for supported models.

ZenMux AI Insurance

World's first platform offering insurance for AI output quality

Poor Output Quality

Model output significantly below expectations

Hallucination Issues

Model generates false or incorrect information

High Latency

Response time exceeds normal range

How it works: Daily auto-detection → Identify problematic requests → Auto-credit compensation next day.

Begin with Pay As You Go now

Start with 0% Service Fee on top-up

FAQs
How do I set up auto top-up?
Can I use PAYG credits to purchase a subscription?
How do I view consumption details?
How do I export invoices?
How do I claim AI Insurance compensation?