GLM 5.3
chutes/zai-org/GLM-5.3 · family glm · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.
This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See Chutes’s docs for per-unit rates.
- Provider
- Chutes (
chutes) - Kind
- text (outputs text)
- Context
- 0 tokens
- Max output
- 0 tokens
- Capabilities
- text
Same model, other providers
“GLM 5.3” is offered by 16 providers — cheapest-effective first. Umans AI Coding Plan is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Umans AI Coding Plan | free | free | $0.00 | 1M |
| NanoGPT | $0.6 | $1.1 | $0.72 | 1M |
| Prime Inference | $0.4 | $2.46 | $0.92 | 1M |
| CoreWeave | $0.75 | $3 | $1.31 | 1M |
| Inceptron | $1 | $4.9 | $1.98 | 1M |
| Cloudflare Workers AI | $1.4 | $4.4 | $2.15 | 1M |
| Fireworks AI | $1.4 | $4.4 | $2.15 | 1M |
| Vercel AI Gateway | $1.4 | $4.4 | $2.15 | 1M |
| Umans AI | $1.4 | $4.4 | $2.15 | 1M |
| EmpirioLabs AI | $1.4 | $4.4 | $2.15 | 1M |
| ZenMux | $1.4 | $4.4 | $2.15 | 1M |
| AI/ML API | $1.4 | $4.4 | $2.15 | 1M |
| Chutes (this) | — | — | — | 0 |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Chutes and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"zai-org/GLM-5.3","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):