glm-4.7-flash
poe/novita/glm-4.7-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See Poe’s docs for per-unit rates.
- Provider
- Poe (
poe) - Kind
- text (outputs text)
- Context
- 200,000 tokens
- Max output
- 65,500 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“glm-4.7-flash” is offered by 15 providers — cheapest-effective first. Z.AI is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Z.AI | free | free | $0.00 | 200k |
| Pendra | free | free | $0.00 | 200k |
| Hugging Face | free | free | $0.00 | 200k |
| Zhipu AI | free | free | $0.00 | 200k |
| Deep Infra | $0.06 | $0.4 | $0.15 | 203k |
| DevPass (LLM Gateway) | $0.06 | $0.4 | $0.15 | 200k |
| Cloudflare Workers AI | $0.0605 | $0.4 | $0.15 | 131k |
| Kilo Gateway | $0.0605 | $0.4 | $0.15 | 131k |
| OpenRouter | $0.0605 | $0.4 | $0.15 | 200k |
| NovitaAI | $0.07 | $0.4 | $0.15 | 200k |
| Jiekou.AI | $0.07 | $0.4 | $0.15 | 200k |
| Amazon Bedrock | $0.07 | $0.4 | $0.15 | 203k |
| Poe (this) | — | — | — | 200k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Poe and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"novita/glm-4.7-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):