GLM-5V-Turbo

zai/glm-5v-turbo · family glm · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideopdf.

$1.90Blended $/1M (3:1)

$1.2Input $/1M

$4Output $/1M

$5.201M in + 1M out

$0.24 −80%Cache read $/1M

#3883 of 5,000Cheapest rank

Provider: Z.AI (zai)
Context: 200,000 tokens
Max output: 131,072 tokens
Capabilities: toolsreasoningtextimagevideopdf

Same model, other providers

“GLM-5V-Turbo” is offered by 8 providers — cheapest-effective first. Zhipu AI Coding Plan is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Zhipu AI Coding Plan	free	free	$0.00	200k
302.AI	$0.72	$3.2	$1.34	200k
Cortecs	$1.186	$3.955	$1.88	203k
Z.AI (this)	$1.2	$4	$1.90	200k
Ofox	$1.2	$4	$1.90	200k
TensorX	$1.2	$4	$1.90	203k
Kilo Gateway	$1.2	$4	$1.90	203k
OpenRouter	$1.2	$4	$1.90	203k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Z.AI and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"glm-5v-turbo","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):