GLM-5.2
nan/glm5.2 · 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
#170 of 7,045
Cheapest rank
- Provider
- NaN (
nan) - Kind
- text (outputs text)
- Context
- 500,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“GLM-5.2” is offered by 70 providers — cheapest-effective first. This one (NaN) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NaN (this) | free | free | $0.00 | 500k |
| Nvidia | free | free | $0.00 | 1M |
| Alibaba Token Plan | free | free | $0.00 | 1M |
| Kenari | free | free | $0.00 | 1M |
| SenseNova (China) | free | free | $0.00 | 1M |
| UnoRouter | free | free | $0.00 | 1M |
| Zhipu AI Coding Plan | free | free | $0.00 | 1M |
| Z.AI Coding Plan | free | free | $0.00 | 1M |
| SCNet Token Plan | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| CrofAI | $0.3 | $1.05 | $0.49 | 1M |
| SCX.ai | $0.55 | $1.78 | $0.86 | 1M |
| DevPass (LLM Gateway) | $0.55 | $1.78 | $0.86 | 1M |
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":"glm5.2","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):