Call glm-5.3-flashx through a single OpenAI-compatible endpoint — one key, no separate vendor account, no multi-provider wiring.
Zhipu AIChatReasoningCodingVisionPrices are per 1M tokens in USD · ¥6.6 = $1 · Billed in CNY
The GLM family combines aggressive pricing on the Flash tier with capable flagship variants, and has become one of the most widely deployed model lines on the platform. GLM models are also a common default inside coding agents because of their quality-per-yuan at high request rates.
At $0.30 per 1M input tokens it sits below the catalogue median of $0.91 — a cost-first choice. Best for coding agents and repository-scale edits. Every model here is reachable with the same API key, so trialling it against a stronger sibling costs one line of code.
from openai import OpenAI
client = OpenAI(
base_url="https://starseaapi.com/v1",
api_key="sk-your-key"
)
r = client.chat.completions.create(
model="glm-5.3-flashx",
messages=[{"role": "user", "content": "Explain prefix caching in one paragraph"}]
)
print(r.choices[0].message.content)| Models | Input $/M | Output $/M | Intelligence index | Coding index |
|---|---|---|---|---|
| glm-5.3-flash | $0.12 | $0.42 | 46.2 | 71.5 |
| glm-4.5-air | $0.12 | $0.30 | — | — |
| glm-4.7 | $0.30 | $1.21 | — | 45.3 |
| glm-4.5 | $0.61 | $2.42 | — | — |
| glm-4.6 | $0.61 | $2.42 | — | 45.8 |
| glm-5 | $0.61 | $2.73 | — | — |
| glm-5-turbo | $0.76 | $3.33 | — | — |
| glm-5.1 | $0.91 | $3.64 | — | 55.8 |
| glm-5.2 | $1.21 | $4.24 | — | 68.8 |
| glm-5.3 | $1.21 | $4.24 | 48.6 | 74.8 |