jishie

GLM 5.2

nano-gpt/z-ai/glm-5.2 · family glm · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.65
Blended $/1M (3:1)
$0.42
Input $/1M
$1.32
Output $/1M
$1.74
1M in + 1M out
$0.078 −81%
Cache read $/1M
#3016 of 7,012
Cheapest rank
Provider
NanoGPT (nano-gpt)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text

Same model, other providers

“GLM 5.2” is offered by 15 providers — cheapest-effective first. Umans AI Coding Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Umans AI Coding Planfreefree$0.00406k
NanoGPT (this)$0.42$1.32$0.651M
Inceptron$0.71$2.35$1.121M
Weights & Biases$0.76$2.42$1.181M
Vercel AI Gateway$0.8$2.55$1.241M
Lilac$0.9$3$1.43524k
Cloudflare Workers AI$1.4$4.4$2.15262k
Umans AI$1.4$4.4$2.15406k
Baseten$1.4$4.4$2.151M
EmpirioLabs AI$1.4$4.4$2.151M
Venice AI$1.4$4.4$2.151M
Fireworks AI$1.4$4.4$2.151M
ZenMux$1.4$4.5$2.171M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at NanoGPT 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-5.2","messages":[{"role":"user","content":"hello"}]}'

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

← all NanoGPT models · model index · JSON