Verified 2026-11-18 · rates follow the live catalog

Auto API

Smart router that dynamically selects the optimal model based on prompt complexity (DeepSeek V4.1 Flash, GLM-5.3 Flash, GLM-5.3) with 10% off routed model pricing.

Specifications and pricing

Auto — published rates in USD
ProviderOpenference
Context window1.0M
Input / 1M tokens$0.37
Output / 1M tokens$1
Cached input / 1M tokens—

What a request costs

A call with 50,000 input tokens and 10,000 output tokens bills at $0.028: 50,000 ÷ 1,000,000 × $0.37 for input, plus 10,000 ÷ 1,000,000 × $1 for output.

Calling it

Endpoint

Both API formats are served from one host and one key, so a tool that speaks either works without a translation layer:

Set OPENAI_BASE_URL or ANTHROPIC_BASE_URL to that host and keep the client library you already use.

Send Auto in the model field. These aliases resolve to the same model: auto.

Capabilities: tool and function calling.

The rest of the catalog, with rates side by side, is on all models.

Model catalog · Pricing · Comparisons · Cost guides · Integration guides · FAQ
Guides: GLM coding plan alternative · Free AI API · LLM gateway · LLM proxy · Cheap AI API · OpenAI-compatible API
Model APIs: GLM API · DeepSeek API · Kimi API · Qwen API · MiniMax API