backchannel.lol
Create account
models / glm-5.3
model / glm-5.3

GLM 5.3

Z.ai GLM-5.3 via Crusoe Managed Inference. Multimodal, tool-calling, 1M context.

chat1.05M context1 upstream routelive
Input$0.1400/ 1M
Cached input$0.0260/ 1M
Output$0.4400/ 1M
90% off at signupbase $1.40 / $4.40Create an account to lock your tier
Requests 24h
0
Tokens 24h
0
0 cached
Uptime 24h
—
Avg latency
—
Avg TTFT
—
Tokens / sec
—
Requests / hour
last 24 hours
12:00: 0 req13:00: 0 req14:00: 0 req15:00: 0 req16:00: 0 req17:00: 0 req18:00: 0 req19:00: 0 req20:00: 0 req21:00: 0 req22:00: 0 req23:00: 0 req00:00: 0 req01:00: 0 req02:00: 0 req03:00: 0 req04:00: 0 req05:00: 0 req06:00: 0 req07:00: 0 req08:00: 0 req09:00: 0 req10:00: 0 req11:00: 0 req12:0016:0020:0000:0004:0008:0011:001 req
Average latency
milliseconds · last 24 hours
12:00: 0ms13:00: 0ms14:00: 0ms15:00: 0ms16:00: 0ms17:00: 0ms18:00: 0ms19:00: 0ms20:00: 0ms21:00: 0ms22:00: 0ms23:00: 0ms00:00: 0ms01:00: 0ms02:00: 0ms03:00: 0ms04:00: 0ms05:00: 0ms06:00: 0ms07:00: 0ms08:00: 0ms09:00: 0ms10:00: 0ms11:00: 0ms12:0016:0020:0000:0004:0008:0011:001ms

Call it

Any of the three dialects works. The proxy translates to this model's native upstream API.

API docs
chat completions
curl https://backchannel.lol/v1/chat/completions \
  -H "Authorization: Bearer $BACKCHANNEL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3",
    "messages": [{"role": "user", "content": "hello"}]
  }'