Models / GLM

GLM 5.3 Flash Unfiltered

The sprinter. Fast MoE, no leash.

chattoolsjsonweb
Try it in chat API docs

What it is.What it costs.

GLM 5.3 Flash, uncensored. A mixture-of-experts model that only wakes a small slice of itself per token, so it streams fast and costs little. Built for roleplay, agents, bulk jobs and anything that needs speed.

venym/glm-flash
spec
Model idvenym/glm-flash
FamilyGLM
Parameters320B MoE, 18B active
ArchitectureMixture of experts
QuantizationFP8
Context window131,072 tokens
Max output16,384 tokens
Input price$0.10 / 1M tokens
Output price$0.40 / 1M tokens
With live webvenym/glm-flash:online
Context in practiceabout 98K words
0131.1K tokens
Pricing
per 1M tokens
Input
$0.10
Output
$0.40

Billed per token on the API, always. Add :online and a search call is billed too. Plans make the chat app free; they do not change these rates.

One token wakes only this slice
Active per token 18B of 320B (5.6%)
Read per token
18 GB
18B active × FP8
Of the model
5.6%
18B of 320B
vs Qwen
0.67x
weights read per token
Tokens you ran here
0
press Run a token

What it can do.Then call it.

Click a capability to see the request parameter behind it. The call on the right works with any OpenAI SDK: point it at our base URL and swap the model id.

Capabilities
4 listed

OpenAI-compatible chat completions, with streaming.

"stream": true

Function calling in the OpenAI format: send tools, get tool_calls back.

"tools": [{ "type": "function", "function": { "name": "get_weather", ... } }]

JSON mode: ask for a JSON object and get one.

"response_format": { "type": "json_object" }

Append :online and the answer is grounded in live web results, with sources.

"model": "venym/glm-flash:online"
terminal
:online
curl https://venym.io/v1/chat/completions \
  -H "Authorization: Bearer $VENYM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "venym/glm-flash",
    "messages": [{"role": "user", "content": "Hello."}]
  }'
OpenAI-compatibleQuickstart
Response
illustration
200 · stream: true·venym/glm-flash
Prompt
9 tok
× $0.10 / 1M
Completion
11 tok
× $0.40 / 1M
This call
$0.000006
tokens only
venym · cost calculator
toy

What GLM costsat your volume.

Drag the sliders. The price comes from the same table that bills you.

Model
GLM 5.3 Flash Unfiltered
Input / day$0.10
$0.10 / 1M
Output / day$0.12
$0.40 / 1M
Per month · 30 days
$6.60$0.22 / day
30-day spend$6.60
Left on day 30$13.40
Busiest day$0.30
Input · tokens / day1.00M
10K× $0.10 / 1M100M
Output · tokens / day300.0K
10K× $0.40 / 1M100M
Your balanceor drag the line

A plan ($12.00/mo for Pro) makes the chat app free. The API stays per token: this bill does not change.

Spend over 30 days · against your balancecovers the month
$0.00$11.20$22.40balance $20.00dailyday 051015202530
GLM spendweekday-heavy load, illustrative
$20.00 lasts 91 days at this rate$13.40 left on day 30
GLM 5.3 Flash Unfiltered

Ask it something.It will answer.

Try it in chat API docs
Also on Venym
Qwen 27B Unfiltered
The thinker. Dense 27B, refusals removed.
$0.30 in · $1.20 out
GLM 5.3 Flash Unfiltered · Venym