GLM-4.5

kilo/z-ai/glm-4.5 · family glm · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$1.00Blended $/1M (3:1)

$0.6Input $/1M

$2.2Output $/1M

$2.801M in + 1M out

$0.11 −82%Cache read $/1M

#3168 of 5,000Cheapest rank

Provider: Kilo Gateway (kilo)
Context: 131,072 tokens
Max output: 98,304 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“GLM-4.5” is offered by 9 providers — cheapest-effective first. ModelScope is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
ModelScope	free	free	$0.00	131k
302.AI	$0.286	$1.142	$0.50	131k
Kilo Gateway (this)	$0.6	$2.2	$1.00	131k
Zhipu AI	$0.6	$2.2	$1.00	131k
Impossibl	$0.6	$2.2	$1.00	131k
LLM Gateway	$0.6	$2.2	$1.00	131k
Abacus	$0.6	$2.2	$1.00	131k
OrcaRouter	$0.6	$2.2	$1.00	131k
Merge Gateway	$0.6	$2.2	$1.00	128k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"z-ai/glm-4.5","messages":[{"role":"user","content":"hello"}]}'

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