GLM 5.3 Flash is an open-weight 321B-parameter (18B active) reasoning model with a 1M context window, hosted by Reka. It is served as an OpenAI-compatible passthrough with native tool calling, structured outputs, logprobs, and streaming.
function_callinghttps://api.reka.ai/v1/chat/completions| Provider | Input | Output | Since launch |
|---|---|---|---|
| OpenCode Zencheapest | $0.15 | $0.5 | — |
| Reka AIcheapest | $0.15 | $0.5 | — |
| Z.AI (Zhipu)cheapest | $0.15 | $0.5 | — |
| Model | Context | Max out | Pricing |
|---|---|---|---|
| GLM 5.3 Flash | 1.0M | 1.0M | $0.15$0.5 |
| GLM 5.3 | 1.0M | 262K | $1.17$3.96 |
/v1/models/reka/glm5.3-flash