GLM-4.7-Flash API

Name: GLM-4.7-Flash
Brand: Zhipu AI
Availability: InStock

A 30B-class model balancing performance and efficiency, further optimized for agentic coding: stronger coding capability and long-horizon task planning. Free forever on NovAI - no per-token cost, no platform fee.

FREE

Input / 1M tokens

FREE

Output / 1M tokens

202K

Context window

16K

Max output

Why use GLM-4.7-Flash on NovAI?

Free forever - $0 per 1M input and output tokens. OpenRouter charges $0.06 / $0.40 for the same model
30B-class SOTA efficiency - a new option balancing performance and cost for high-volume workloads
Optimized for agentic coding - strengthened coding capabilities and long-horizon task planning
202K context window - repo-level reasoning and long conversations
Tool calling - plugs straight into agent frameworks (OpenAI-compatible function calling)
Hong Kong low-latency access through NovAI's zero-fee gateway

Price comparison

	NovAI	OpenRouter	You save
Input / 1M tokens	$0.00	$0.06	100%
Output / 1M tokens	$0.00	$0.40	100%

Best use cases

High-volume chatbots and assistants at zero marginal cost
Coding agents and CLI tools on a budget
Classification, routing, and extraction pipelines
Free-tier products that need a reliable workhorse model
Long-context document Q&A

Quick start

cURL

curl https://aiapi-pro.com/v1/chat/completions \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.7-flash",
    "messages": [{"role":"user","content":"Refactor this Python function to be async"}]
  }'

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI(
    base_url="https://aiapi-pro.com/v1",
    api_key="YOUR_NOVAI_API_KEY",
)
resp = client.chat.completions.create(
    model="glm-4.7-flash",
    messages=[{"role":"user","content":"Refactor this Python function to be async"}],
)
print(resp.choices[0].message.content)

Works with any OpenAI-compatible SDK - just set base_url to https://aiapi-pro.com/v1 and use your NovAI API key. Full reference in the API docs.