GLM 4.6V
nano-gpt/z-ai/glm-4.6v · family glm · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: text image.
$0.45
Blended $/1M (3:1)
$0.3
Input $/1M
$0.9
Output $/1M
$1.20
1M in + 1M out
$0.15 −50%
Cache read $/1M
#2375 of 7,012
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 24,000 tokens
- Capabilities
- text image
Same model, other providers
“GLM 4.6V” is offered by 3 providers — cheapest-effective first. ZenMux is the cheapest at $0.21 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| ZenMux | $0.14 | $0.42 | $0.21 | 200k |
| NanoGPT (this) | $0.3 | $0.9 | $0.45 | 128k |
| NovitaAI | $0.3 | $0.9 | $0.45 | 131k |
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-4.6v","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):