GLM 5.1
hpc-ai/zai-org/glm-5.1 · family glm · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$1.08
Blended $/1M (3:1)
$0.615
Input $/1M
$2.46
Output $/1M
$3.08
1M in + 1M out
$0.133 −78%
Cache read $/1M
#4212 of 7,712
Cheapest rank
- Provider
- HPC-AI (
hpc-ai) - Kind
- text (outputs text)
- Context
- 202,000 tokens
- Max output
- 202,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“GLM 5.1” is offered by 8 providers — cheapest-effective first. This one (HPC-AI) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| HPC-AI (this) | $0.615 | $2.46 | $1.08 | 202k |
| NanoGPT | $0.75 | $2.6 | $1.21 | 200k |
| EmpirioLabs AI | $0.825 | $3.3 | $1.44 | 202k |
| ZenMux | $0.8781 | $3.51 | $1.54 | 200k |
| Baseten | $1.3 | $4.3 | $2.05 | 203k |
| Ambient | $1.4 | $4.4 | $2.15 | 203k |
| Vercel AI Gateway | $1.4 | $4.4 | $2.15 | 203k |
| Venice AI | $1.54 | $4.84 | $2.37 | 200k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at HPC-AI 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-5.1","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):