GLM-4.5-Air
huggingface/zai-org/GLM-4.5-Air · family glm-air · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.31
Blended $/1M (3:1)
$0.13
Input $/1M
$0.85
Output $/1M
$0.98
1M in + 1M out
—
Cache read $/1M
#2266 of 7,708
Cheapest rank
- Provider
- Hugging Face (
huggingface) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 98,304 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“GLM-4.5-Air” is offered by 8 providers — cheapest-effective first. This one (Hugging Face) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Hugging Face (this) | $0.13 | $0.85 | $0.31 | 131k |
| Kilo Gateway | $0.13 | $0.85 | $0.31 | 131k |
| OpenRouter | $0.13 | $0.85 | $0.31 | 131k |
| DevPass (LLM Gateway) | $0.13 | $0.85 | $0.31 | 131k |
| Z.AI | $0.2 | $1.1 | $0.43 | 131k |
| Impossibl | $0.2 | $1.1 | $0.43 | 131k |
| OrcaRouter | $0.2 | $1.1 | $0.43 | 131k |
| Zhipu AI | $0.2 | $1.1 | $0.43 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Hugging Face and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"zai-org/GLM-4.5-Air","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):