GLM 4.6

vercel/zai/glm-4.6 · 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

#3174 of 5,000Cheapest rank

Provider: Vercel AI Gateway (vercel)
Context: 200,000 tokens
Max output: 96,000 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“GLM 4.6” is offered by 6 providers — cheapest-effective first. NanoGPT is the cheapest at $0.61 blended.

Provider	Input	Output	Blended	Context
NanoGPT	$0.35	$1.4	$0.61	200k
ZenMux	$0.35	$1.54	$0.65	200k
IO.NET	$0.4	$1.75	$0.74	200k
Venice AI	$0.43	$1.75	$0.76	198k
NovitaAI	$0.55	$2.2	$0.96	205k
Vercel AI Gateway (this)	$0.6	$2.2	$1.00	200k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"zai/glm-4.6","messages":[{"role":"user","content":"hello"}]}'

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