Fast:zhipu GLM 5.3 API
Fireworks's chat model. Call it on 666 AI with the same API key as every other model. Pay as you go; prices follow the upstream in real time and this page updates hourly.
| Vendor | Fireworks |
| Type | chat |
| Price | $2.83 per 1M input tokens · $8.91 per 1M output tokens |
| Context window | 128K tokens |
| Live test | Passed our live test in the last 7 days |
| Model ID (use this in your request) | fireworks/fast:zhipu/glm-5.3 |
How to call Fast:zhipu GLM 5.3
The API is OpenAI-compatible. Replace YOUR-ENDPOINT with the endpoint shown on your API Key page after you sign up, and YOUR-KEY with your key.
curl https://YOUR-ENDPOINT/v1/chat/completions \
-H "Authorization: Bearer YOUR-KEY" \
-H "Content-Type: application/json" \
-d '{"model": "fireworks/fast:zhipu/glm-5.3", "messages": [{"role": "user", "content": "Hello"}]}'from openai import OpenAI
client = OpenAI(base_url="https://YOUR-ENDPOINT/v1", api_key="YOUR-KEY")
r = client.chat.completions.create(
model="fireworks/fast:zhipu/glm-5.3",
messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)Similar models — price comparison
| Model | Price |
|---|---|
| Qwen3.7 Max | $2.7 per 1M input tokens · $8.1 per 1M output tokens |
| Qwen3.8 2.4T A95B | $2.7 per 1M input tokens · $8.1 per 1M output tokens |
| Qwen3.8 Max | $2.7 per 1M input tokens · $8.1 per 1M output tokens |
| Grok 4.5 | $2.7 per 1M input tokens · $8.1 per 1M output tokens |
| Grok 4.7 | $2.97 per 1M input tokens · $8.91 per 1M output tokens |
| Gemini 3.5 Flash | $1.82 per 1M input tokens · $10.94 per 1M output tokens |
More models from Fireworks
| Model | Price |
|---|---|
| Inkling | $1.35 per 1M input tokens · $5.47 per 1M output tokens |
| Kimi K3 Fast | $6.08 per 1M input tokens · $30.38 per 1M output tokens |
FAQ
How much does the Fast:zhipu GLM 5.3 API cost?
On 666 AI, Fast:zhipu GLM 5.3 costs $2.83 per 1M input tokens · $8.91 per 1M output tokens. You pay only for what you use — no monthly fee. Prices follow the upstream in real time; this page updates every hour.
Can I use the official OpenAI SDK?
Yes. The API is OpenAI-compatible: in the OpenAI Python or Node.js SDK just change base_url and api_key, and set model to fireworks/fast:zhipu/glm-5.3.
How do I pay?
Bank card (including Google Pay / Apple Pay), USDT / ETH, or bank wire. Top up once and usage is deducted as you go.