GLM 5.2
baseten/zai-org/GLM-5.2 · family glm · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$2.15
Blended $/1M (3:1)
$1.4
Input $/1M
$4.4
Output $/1M
$5.80
1M in + 1M out
$0.3 −79%
Cache read $/1M
#5331 of 7,708
Cheapest rank
- Provider
- Baseten (
baseten) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“GLM 5.2” is offered by 13 providers — cheapest-effective first. NanoGPT is the cheapest at $0.65 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.42 | $1.32 | $0.65 | 1M |
| Inceptron | $0.71 | $2.35 | $1.12 | 1M |
| CoreWeave | $0.76 | $2.42 | $1.18 | 1M |
| Vercel AI Gateway | $0.8 | $2.55 | $1.24 | 1M |
| Lilac | $0.9 | $3 | $1.43 | 524k |
| ZenMux | $0.98 | $3.08 | $1.50 | 1M |
| Baseten (this) | $1.4 | $4.4 | $2.15 | 1M |
| Cloudflare Workers AI | $1.4 | $4.4 | $2.15 | 262k |
| EmpirioLabs AI | $1.4 | $4.4 | $2.15 | 1M |
| Venice AI | $1.4 | $4.4 | $2.15 | 1M |
| Fireworks AI | $1.4 | $4.4 | $2.15 | 1M |
| Neuralwatt | $1.45 | $4.5 | $2.21 | 1M |
| above.dev | $1.54 | $4.84 | $2.37 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Baseten 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-5.2","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):