All models · Pricing · API docs
glm-5.3-flashx API
GLM-5.3-FlashX (Z.AI) - high-speed variant of glm-5.3-flash (18 Sep 2026), up to 200 tokens/s per the vendor · primary route is the direct Z.AI API · premium wallet model · pay per token from balance · 1M context · reads images and calls tools (measured 19 Sep 2026) · reasoning consumes output tokens, set max_tokens with headroom · ⚠ third-party provider: requests are processed by an external upstream
- Type: LLM · chat · reasoning · зрение · 1M ctx · pay-as-you-go
- Context: 1M
- Access: Wallet · pay per token
- Endpoint: /v1/chat/completions, /v1/responses
Requests to this model are processed outside Russia.
How to connect: change one line — base_url. Get an sk- key in the dashboard.
curl https://api.neuraldeep.ru/v1/chat/completions \
-H "Authorization: Bearer $NEURALDEEP_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"glm-5.3-flashx","messages":[{"role":"user","content":"Hello"}]}'