← All modelsZ.ai (Zhipu) — served by Reka

GLM 5.3 Flash

321B MoE (18B active) — reasoning, tool calling, 262K context — self-hosted.

Z.ai (Zhipu) — served by Reka$0.07 in · $0.25 out / 1M tokens (≤256K ctx)llmglmreasoningopen-weights
Capabilities
llmglmreasoningopen-weights
Pricing
Context bandMax tokensInput / M tokOutput / M tok
≤256K262,144$0.075$0.25
API

Wire it up.

EndpointPOST https://api.tryinfer.com/v1/chat/completions
request
curl https://api.tryinfer.com/v1/chat/completions \
-H "Authorization: Bearer $INFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm5.3-flash",
"messages": [{ "role": "user", "content": "Hello!" }]
}'

OpenAI-compatible — point your SDK at Infer with a bearer token. Get an API key →