Developers
GLM 5.3 API pricing
GLM 5.3 (Zhipu) is priced at $1.4 / $4.4 per 1M input / output tokens. It ranks #6 of 17 models on Somnus by blended price. With Somnus credit (2× to 2.5× on every top-up) the effective price is $0.7 / $2.2 or lower.
GLM 5.3 cost by workload
| Workload | Tokens per request (in / out) | Requests | List cost | With Somnus |
|---|---|---|---|---|
| Support chatbot | 1,500 / 500 | 10,000 | $43.00 | $21.50 |
| Coding agent step | 12,000 / 1,500 | 2,000 | $46.80 | $23.40 |
| Document summary | 8,000 / 400 | 1,000 | $12.96 | $6.48 |
| Classification / tagging | 400 / 20 | 100,000 | $64.80 | $32.40 |
Effective cost uses the minimum 2× credit.
How GLM 5.3 pricing works
You are charged per token: 1.4 USD per million tokens you send and 4.4 USD per million tokens GLM writes back. Output is 3.1× the input rate for GLM 5.3, so answer length drives most of the bill.
Somnus bills usage at the list price and credits every top-up at 2× or more, which is how the effective $0.7 / $2.2 rate comes about.
At list price
$80.00 /mo
You pay with Somnus (2× credit)
$40.00 /mo
Cheapest models for this workload
- DeepSeek V4 Flash$6.60 /mo
- MiMo V2.5 Pro$10.95 /mo
- DeepSeek V4 Pro$19.80 /mo
- Gemini 3.8 Flash$30.00 /mo
- Claude Haiku 4.5$40.00 /mo
Estimate GLM 5.3 cost from the usage field
from openai import OpenAI
import os
client = OpenAI(
api_key=os.environ["SOMNUS_API_KEY"],
base_url="https://gateway-production-c837.up.railway.app/v1",
)
resp = client.chat.completions.create(
model="claude-sonnet-5",
messages=[
{"role": "user", "content": "Count my tokens"}
],
)
print(resp.choices[0].message.content)Multiply usage.prompt_tokens by 1.4/1e6 and usage.completion_tokens by 4.4/1e6.
Questions
How much does GLM 5.3 cost per 1M tokens?
$1.4 / $4.4 list; $0.7 / $2.2 effective with Somnus credit.
Is there a free GLM 5.3 tier?
New Somnus accounts get $5 free credit usable on GLM 5.3.
Related
Browse more: Alternatives · Compare · Use cases · Developers · Solutions · Tools