jishie

GLM-5.3

nan/glm5.3 · family glm · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
Cache read $/1M
#186 of 7,264
Cheapest rank
Provider
NaN (nan)
Kind
text (outputs text)
Context
1,000,000 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text

Same model, other providers

“GLM-5.3” is offered by 37 providers — cheapest-effective first. This one (NaN) is the cheapest.

ProviderInputOutputBlendedContext
NaN (this)freefree$0.001M
Z.AI Coding Planfreefree$0.001M
Kenarifreefree$0.001M
Zhipu AI Coding Planfreefree$0.001M
SCNet Token Planfreefree$0.001M
Volcengine Ark Coding Planfreefree$0.001M
CrofAI$0.4$1.4$0.651M
Merge Gateway$0.7$2.2$1.071M
Vancine$1.12$3.52$1.721M
ai&$1$4$1.751M
Cortecs$1.11$3.9$1.811M
AIHubMix$1.13$3.94$1.831M
DevPass (LLM Gateway)$1.2$4$1.901M

Call it

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

Most providers are OpenAI-compatible — point base_url at NaN and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"glm5.3","messages":[{"role":"user","content":"hello"}]}'

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

← all NaN models · model index · JSON