GLM 4.7

zenmux/z-ai/glm-4.7 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.49Blended $/1M (3:1)

$0.28Input $/1M

$1.14Output $/1M

$1.421M in + 1M out

$0.06 −79%Cache read $/1M

#2205 of 5,000Cheapest rank

Provider: ZenMux (zenmux)
Context: 200,000 tokens
Max output: 64,000 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“GLM 4.7” is offered by 6 providers — cheapest-effective first. NanoGPT is the cheapest at $0.35 blended.

Provider	Input	Output	Blended	Context
NanoGPT	$0.2	$0.8	$0.35	200k
ZenMux (this)	$0.28	$1.14	$0.49	200k
Baseten	$0.6	$2.2	$1.00	200k
Vercel AI Gateway	$0.6	$2.2	$1.00	200k
Venice AI	$0.55	$2.65	$1.07	198k
Berget.AI	$0.77	$2.75	$1.27	128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at ZenMux 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-4.7","messages":[{"role":"user","content":"hello"}]}'

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