Z.ai: GLM 5.3 Flash
4 providers live- 4 live providers
- 100% uptime
- 0.69 s first token
- 193 tok/s output
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.
- Context
- 1M
- tokens
- Max output
- 943.7K
- tokens
- Input
- $0.15
- per million tokens
- Output
- $0.50
- per million tokens
Providers
Ranked by price and speed. Requests go to the best healthy provider, then fail over down the list.Benchmarks| Who answers now | Input per 1M | First token |
|---|---|---|
 llm.buzzpicked | $0.15 | 2.48 s |
 Prime Intellect | $0.15 | 0.69 s |
 DeepInfra | $0.15 | 0.83 s |
 Novita | $0.15 | 2.48 s |
llm.buzz answers now: first in the router's order.
First token is the 24-hour median. If the pick fails, the next one answers at its own price.
| # | Provider | Input | Output | Cache read | Latency | Throughput | Uptime (3d) |
|---|---|---|---|---|---|---|---|
| 1 | Data policy not declared | $0.15 | $0.50 | $0.03 | 2.48 s | 193 tok/s | 98.6% |
| 2 | Data policy not declared | $0.15 | $0.50 | $0.03 | 0.69 s | 65 tok/s | 100% |
| 3 | Data policy not declared | $0.15 | $0.50 | $0.03 | 0.83 s | 31 tok/s | 93% |
| 4 | Data policy not declared | $0.15 | $0.50 | $0.03 | 2.48 s | 93 tok/s | 100% |
Price history
No price changes since Oct 20, 2026.
- DeepInfra$0.15 in, $0.50 out
- Prime Intellect$0.15 in, $0.50 out
- Novita$0.15 in, $0.50 out
Performance
Last 24 hours, from llm.buzz's test requestsThroughput (tok/s)
- llm.buzz193 tok/s
- Prime Intellect65 tok/s
- DeepInfra31 tok/s
- Novita93 tok/s
Data table
| Provider | From (UTC) | p50 | p90 | p99 |
|---|---|---|---|---|
| llm.buzz | Oct 26, 05:00 | 334 tok/s | 334 tok/s | 334 tok/s |
| llm.buzz | Oct 26, 09:00 | 193 tok/s | 193 tok/s | 193 tok/s |
| llm.buzz | Oct 26, 14:00 | 65 tok/s | 65 tok/s | 65 tok/s |
| llm.buzz | Oct 26, 19:00 | 93 tok/s | 93 tok/s | 93 tok/s |
| llm.buzz | Oct 26, 23:00 | 65 tok/s | 65 tok/s | 65 tok/s |
| llm.buzz | Oct 27, 04:00 | 193 tok/s | 193 tok/s | 193 tok/s |
| llm.buzz | Last 24 hours | 193 tok/s | 65 tok/s | 65 tok/s |
| Prime Intellect | Oct 26, 06:00 | 37 tok/s | 37 tok/s | 37 tok/s |
| Prime Intellect | Oct 26, 11:00 | 65 tok/s | 65 tok/s | 65 tok/s |
| Prime Intellect | Oct 26, 15:00 | 65 tok/s | 65 tok/s | 65 tok/s |
| Prime Intellect | Oct 26, 20:00 | 54 tok/s | 54 tok/s | 54 tok/s |
| Prime Intellect | Oct 27, 01:00 | 278 tok/s | 278 tok/s | 278 tok/s |
| Prime Intellect | Last 24 hours | 65 tok/s | 37 tok/s | 37 tok/s |
| DeepInfra | Oct 26, 07:00 | 31 tok/s | 31 tok/s | 31 tok/s |
| DeepInfra | Oct 26, 15:00 | 18 tok/s | 18 tok/s | 18 tok/s |
| DeepInfra | Oct 26, 19:00 | 8.7 tok/s | 8.7 tok/s | 8.7 tok/s |
| DeepInfra | Oct 26, 23:00 | 65 tok/s | 65 tok/s | 65 tok/s |
| DeepInfra | Oct 27, 03:00 | 78 tok/s | 78 tok/s | 78 tok/s |
| DeepInfra | Last 24 hours | 31 tok/s | 8.7 tok/s | 8.7 tok/s |
| Novita | Oct 26, 06:00 | 134 tok/s | 134 tok/s | 134 tok/s |
| Novita | Oct 26, 11:00 | 78 tok/s | 78 tok/s | 78 tok/s |
| Novita | Oct 26, 15:00 | 112 tok/s | 112 tok/s | 112 tok/s |
| Novita | Oct 26, 20:00 | 54 tok/s | 54 tok/s | 54 tok/s |
| Novita | Oct 27, 00:00 | 37 tok/s | 37 tok/s | 37 tok/s |
| Novita | Oct 27, 04:00 | 93 tok/s | 93 tok/s | 93 tok/s |
| Novita | Last 24 hours | 93 tok/s | 37 tok/s | 37 tok/s |
Latency (time to first token)
- llm.buzz2.48 s
- Prime Intellect0.69 s
- DeepInfra0.83 s
- Novita2.48 s
Data table
| Provider | From (UTC) | p50 | p90 | p99 |
|---|---|---|---|---|
| llm.buzz | Oct 26, 05:00 | 2.07 s | 2.07 s | 2.07 s |
| llm.buzz | Oct 26, 09:00 | 3.57 s | 3.57 s | 3.57 s |
| llm.buzz | Oct 26, 14:00 | 38.2 s | 38.2 s | 38.2 s |
| llm.buzz | Oct 26, 19:00 | 2.48 s | 2.48 s | 2.48 s |
| llm.buzz | Oct 26, 23:00 | 5.14 s | 5.14 s | 5.14 s |
| llm.buzz | Oct 27, 04:00 | 1.72 s | 1.72 s | 1.72 s |
| llm.buzz | Last 24 hours | 2.48 s | 38.2 s | 38.2 s |
| Prime Intellect | Oct 26, 06:00 | 0.83 s | 0.83 s | 0.83 s |
| Prime Intellect | Oct 26, 11:00 | 0.69 s | 0.69 s | 0.69 s |
| Prime Intellect | Oct 26, 15:00 | 0.58 s | 0.58 s | 0.58 s |
| Prime Intellect | Oct 26, 20:00 | 0.83 s | 0.83 s | 0.83 s |
| Prime Intellect | Oct 27, 01:00 | 0.40 s | 0.40 s | 0.40 s |
| Prime Intellect | Last 24 hours | 0.69 s | 0.83 s | 0.83 s |
| DeepInfra | Oct 26, 07:00 | 0.69 s | 0.69 s | 0.69 s |
| DeepInfra | Oct 26, 15:00 | 1.00 s | 1.00 s | 1.00 s |
| DeepInfra | Oct 26, 19:00 | 1.44 s | 1.44 s | 1.44 s |
| DeepInfra | Oct 26, 23:00 | 0.83 s | 0.83 s | 0.83 s |
| DeepInfra | Oct 27, 03:00 | 0.83 s | 0.83 s | 0.83 s |
| DeepInfra | Last 24 hours | 0.83 s | 1.44 s | 1.44 s |
| Novita | Oct 26, 06:00 | 2.98 s | 2.98 s | 2.98 s |
| Novita | Oct 26, 11:00 | 1.72 s | 1.72 s | 1.72 s |
| Novita | Oct 26, 15:00 | 2.98 s | 2.98 s | 2.98 s |
| Novita | Oct 26, 20:00 | 4.29 s | 4.29 s | 4.29 s |
| Novita | Oct 27, 00:00 | 2.48 s | 2.48 s | 2.48 s |
| Novita | Oct 27, 04:00 | 1.72 s | 1.72 s | 1.72 s |
| Novita | Last 24 hours | 2.48 s | 4.29 s | 4.29 s |
Uptime
Last 72 hours, by hour- Up: 95% or more served
- Degraded: 85% to 95%
- Down: below 85%
- No data
- From llm.buzz's test requests
Questions
How much does Z.ai: GLM 5.3 Flash cost?
Z.ai: GLM 5.3 Flash costs $0.15 per million input tokens and $0.50 per million output tokens at llm.buzz, the provider requests go to first, with cache reads at $0.03 per million tokens.
Do providers train on my prompts?
Each provider declares it, and the table above shows every declaration. You can limit a request to providers that keep nothing, or to providers in the EU.
Can I serve Z.ai: GLM 5.3 Flash myself?
Yes. Apply as a provider, add your endpoint and list this model at your price. It goes live once the automated check passes.
Similar models
Call it
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.llm.buzz/api/v1",
api_key=os.environ["LLM_BUZZ_KEY"],
)
reply = client.chat.completions.create(
model="z-ai/glm-5.3-flash",
messages=[{"role": "user", "content": "Hello"}],
)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.llm.buzz/api/v1",
apiKey: process.env.LLM_BUZZ_KEY,
});
const reply = await client.chat.completions.create({
model: "z-ai/glm-5.3-flash",
messages: [{ role: "user", content: "Hello" }],
});curl https://api.llm.buzz/api/v1/chat/completions \
-H "Authorization: Bearer $LLM_BUZZ_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "z-ai/glm-5.3-flash",
"messages": [{"role": "user", "content": "Hello"}]}'Endpoints
POST /api/v1/chat/completionsPOST /api/v1/responsesPOST /api/v1/messagesAuthentication
Send your llm.buzz key as a Bearer token: Authorization: Bearer $LLM_BUZZ_KEY. Create keys in the console. The same key calls every model; each request pays the price of the provider that answered it.
More in Authentication and the API reference.
README
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.
- Model ID
- z-ai/glm-5.3-flash
- Takes
- Text, image
- Answers
- Text
- Context
- 1M tokens
- Max output
- 943.7K tokens
- Capabilities
- Tools, Caching, Structured outputs
- Parameters
- max_tokens, response_format, structured_outputs, temperature, tool_choice, tools
- Weights
- Open weights
- On llm.buzz since
- Oct 20, 2026