Zhipu AI models and API pricing
Published Zhipu AI models available through Meldport. Check capabilities before selecting a model for your integration.
Latest catalog evidence: Verified on 2026-11-06.
| Model / publisher | Input | Output | List input / output | Published discount | Capabilities / context | Evidence |
|---|---|---|---|---|---|---|
| GLM 5.3 Flash Zhipu AI | $0.045 | $0.15 | $0.15 / $0.5 | Input: 70% Output: 70% | text, vision, video, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| GLM 5.3 FlashX Zhipu AI | $0.20276 | $0.685 | $0.37 / $1.25 | Input: 45.2% Output: 45.2% | text, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| glm-5.2 Zhipu AI | $0.42 | $1.32 | $1.4 / $4.4 | Input: 70% Output: 70% | text, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| GLM-5.1 (flagship) Zhipu AI | $0.42 | $1.32 | $1.4 / $4.4 | Input: 70% Output: 70% | text, vision, cache, tools, stream 200K tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| GLM-4.6V (vision) Zhipu AI | $0.09 | $0.27 | $0.3 / $0.9 | Input: 70% Output: 70% | text, vision, video, cache, tools, stream 200K tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| GLM 5.3 Zhipu AI | $0.42 | $1.32 | $1.4 / $4.4 | Input: 70% Output: 70% | text, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
Select the exact model and variant
Compare the published context, capabilities and complete model ID before choosing a route. Prices and availability can change; inspect the evidence date on each entry.
One currently active example is GLM 5.3 Flash, API ID meldport/glm-5.3-flash. Its published context is 1,000,000 tokens; published capabilities: text, vision, video, cache, tools, stream. Evidence checked 2026-11-06. Review the model detail for its current evidence and limits.
Try a bounded Chat Completions request
Send this JSON to POST https://api.meldport.com/v1/chat/completions, with Content-Type: application/json and your dedicated key in the Authorization: Bearer header.
{
"model": "meldport/glm-5.3-flash",
"messages": [
{
"role": "user",
"content": "Reply with one short sentence."
}
],
"max_tokens": 64,
"stream": false
}Store a dedicated key in your environment and follow the authentication quickstart. Use the exact ID above; a paid model ID and a :free alias have separate funding rules. See the eligible free aliases and shared monthly pool before assuming a free version is available.
Calculate ordinary input, cache and output costs, compare gateway tradeoffs, or read why your token ratio matters. Client-specific streaming and tool behavior must be tested separately; see agent compatibility.