GLM-4.5V
aihubmix/glm-4.5v · family glm · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.
$0.48
Blended $/1M (3:1)
$0.274
Input $/1M
$1.1
Output $/1M
$1.37
1M in + 1M out
—
Cache read $/1M
#2789 of 7,795
Cheapest rank
- Provider
- AIHubMix (
aihubmix) - Kind
- text (outputs text)
- Context
- 64,000 tokens
- Max output
- 16,384 tokens
- Capabilities
- tools reasoning text image video
Same model, other providers
“GLM-4.5V” is offered by 9 providers — cheapest-effective first. 302.AI is the cheapest at $0.43 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| 302.AI | $0.29 | $0.86 | $0.43 | 64k |
| AIHubMix (this) | $0.274 | $1.1 | $0.48 | 64k |
| Z.AI | $0.6 | $1.8 | $0.90 | 64k |
| Kilo Gateway | $0.6 | $1.8 | $0.90 | 66k |
| OpenRouter | $0.6 | $1.8 | $0.90 | 66k |
| Hugging Face | $0.6 | $1.8 | $0.90 | 66k |
| Tempr | $0.6 | $1.8 | $0.90 | 64k |
| Zhipu AI | $0.6 | $1.8 | $0.90 | 64k |
| DevPass (LLM Gateway) | $0.6 | $1.8 | $0.90 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at AIHubMix and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"glm-4.5v","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):