Klinn is now OpenCheap. Same models, same keys, same prices; api.klinn.dev keeps working. What changed

opencheap.si

GLM 5V Turbo API price

On OpenCheap, GLM 5V Turbo (Zhipu) costs $1.10 per 1M input tokens and $4.00 per 1M output tokens (cached input $0.240), through one OpenAI-compatible API.

Prices updated 2026-11-03 21:11 UTC.

Price per 1M tokens

GLM 5V Turbo on OpenCheap: our price per million tokens, context length, and the public list price
Input, our price$1.10
Output, our price$4.00
Cached input, our price$0.240
Prompts above 32K tokens, input · output$1.50 · $5.50
Context length202K tokens
OpenRouter list, input · output$1.20 · $4.00
vs listsame

“vs list” compares our price with OpenRouter's list price on a 1:3 input:output blend, as on the Models page. Above a tier's prompt length, the whole request is priced at that tier's rates.

Variants

  • GLM 5V Turbo Thinking (opencheap/glm-5v-turbo:thinking): $1.80 input · $6.00 output per 1M tokens

How to call GLM 5V Turbo

Base URL https://api.opencheap.si/v1, model id opencheap/glm-5v-turbo, and an API key from the console. Any OpenAI SDK works.

curl https://api.opencheap.si/v1/chat/completions \
  -H "Authorization: Bearer $OPENCHEAP_API_KEY" -H "Content-Type: application/json" \
  -d '{ "model": "opencheap/glm-5v-turbo", "messages": [{ "role": "user", "content": "Hi" }] }'
import os
from openai import OpenAI
client = OpenAI(base_url="https://api.opencheap.si/v1", api_key=os.environ["OPENCHEAP_API_KEY"])
r = client.chat.completions.create(model="opencheap/glm-5v-turbo",
    messages=[{"role": "user", "content": "Hi"}])
print(r.choices[0].message.content)

FAQ

What is the cheapest GLM 5V Turbo API?

On OpenCheap, GLM 5V Turbo costs $1.10 per 1M input tokens and $4.00 per 1M output tokens, and cached input $0.240 per 1M tokens. Each request is routed to the cheapest healthy source for the model. You pay from one prepaid balance, with no monthly fee.

Is it OpenAI-compatible?

Yes. Point any OpenAI SDK or HTTP client at the base URL https://api.opencheap.si/v1 with an OpenCheap API key, and call /chat/completions with the model id opencheap/glm-5v-turbo. Requests and responses have the same shape as OpenAI's chat completions, streaming included.

Does it work with Cursor, Claude Code or Codex?

Yes. In Cursor, add the custom model opencheap/glm-5v-turbo with the base URL https://api.opencheap.si/v1. In Claude Code, set ANTHROPIC_BASE_URL to https://api.opencheap.si and ANTHROPIC_MODEL to opencheap/glm-5v-turbo. In Codex, add OpenCheap as a model provider with base_url https://api.opencheap.si/v1. The quickstart has each setup step by step.

More Zhipu models

Every major model, one key.

Read the docs