GLM 5.3 Flash
modal/zai-org/GLM-5.3-Flash · family glm · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.
$0.71
Blended $/1M (3:1)
$0.45
Input $/1M
$1.5
Output $/1M
$1.95
1M in + 1M out
$0.09 −80%
Cache read $/1M
#3160 of 6,950
Cheapest rank
- Provider
- Modal (
modal) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text image video
Same model, other providers
“GLM 5.3 Flash” is offered by 8 providers — cheapest-effective first. NanoGPT is the cheapest at $0.12 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.075 | $0.25 | $0.12 | 1M |
| EmpirioLabs AI | $0.075 | $0.25 | $0.12 | 1M |
| Cloudflare Workers AI | $0.15 | $0.5 | $0.24 | 1.3M |
| Baseten | $0.15 | $0.5 | $0.24 | 1M |
| Vercel AI Gateway | $0.15 | $0.5 | $0.24 | 1M |
| Venice AI | $0.15 | $0.5 | $0.24 | 1M |
| Weights & Biases | $0.15 | $0.5 | $0.24 | 1M |
| Modal (this) | $0.45 | $1.5 | $0.71 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Modal 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-Flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):