qihang-ai/gpt-5.2 · family gpt · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.
qihang-ai)“GPT-5.2” is offered by 9 providers — cheapest-effective first. This one (QiHang) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| QiHang (this) | $0.25 | $2 | $0.69 | 400k |
| UnoRouter | $1.05 | $8.4 | $2.89 | 400k |
| SAP AI Core | $1.25 | $9.44 | $3.30 | 400k |
| Jiekou.AI | $1.575 | $12.6 | $4.33 | 400k |
| Poe | $1.6 | $13 | $4.45 | 400k |
| Impossibl | $1.75 | $14 | $4.81 | 400k |
| LLM Gateway | $1.75 | $14 | $4.81 | 400k |
| OpenCode Zen | $1.75 | $14 | $4.81 | 400k |
| GitHub Copilot | $1.75 | $14 | $4.81 | 400k |
jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at QiHang and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"gpt-5.2","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):