The board shows this model's cheapest measured offer ($0.930/1M); the smaller figure under it is the mean of the 21 offers listed below ($1.48/1M). Add those up and divide — it matches.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| StreamLake (fp8) | OpenRouter ↗ | $0.600 | $1.92 | 1909ms | 69 | 100% | API-measured |
| GMICloud (fp8) | OpenRouter ↗ | $0.600 | $1.92 | 2209ms | 87 | 100% | API-measured |
| deepinfra | Pricebook (LiteLLM) ↗ | $0.600 | $2.08 | — | — | — | Official list |
| deepinfra | HuggingFace Router ↗ | $0.600 | $2.08 | 730ms | 42 | — | API-measured |
| Baidu (fp8) | OpenRouter ↗ | $0.700 | $2.24 | 1048ms | 51 | 100% | API-measured |
| 0g-teetls | 0G Router ↗ | $0.667 | $3.00 | — | — | — | API-measured |
| SiliconFlow (fp8) | OpenRouter ↗ | $0.950 | $2.55 | 2651ms | 58 | 100% | API-measured |
| baseten | Pricebook (LiteLLM) ↗ | $0.950 | $3.15 | — | — | — | Official list |
| zai | Pricebook (LiteLLM) ↗ | $1.00 | $3.20 | — | — | — | Official list |
| streamlake | Pricebook (LiteLLM) ↗ | $1.00 | $3.20 | — | — | — | Official list |
| together_ai | Pricebook (LiteLLM) ↗ | $1.00 | $3.20 | — | — | — | Official list |
| Amazon Bedrock | OpenRouter ↗ | $1.00 | $3.20 | 589ms | 120 | 100% | API-measured |
| Venice (fp8) | OpenRouter ↗ | $1.00 | $3.20 | 1232ms | 47 | 97.8% | API-measured |
| Novita (fp8) | OpenRouter ↗ | $1.00 | $3.20 | 1734ms | 37 | 100% | API-measured |
| Z.AI (fp8) | OpenRouter ↗ | $1.00 | $3.20 | 2116ms | 40 | 100% | API-measured |
| novita | Pricebook (LiteLLM) ↗ | $1.00 | $3.20 | — | — | — | Official list |
| novita | HuggingFace Router ↗ | $1.00 | $3.20 | 1818ms | 31 | — | API-measured |
| novita-ai | Novita AI ↗ | $1.00 | $3.20 | — | — | — | API-measured |
| requesty | Requesty ↗ | $1.00 | $3.20 | — | — | — | API-measured |
| Venice (turbo) | OpenRouter ↗ | $1.20 | $4.00 | 4492ms | 26 | 100% | API-measured |
| burncloud | burncloud ↗ | $2.00 | $6.40 | — | — | — | API-measured |
Price trend
Cheapest blended price, last 31 days (USD/1M): $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93
Data & method
Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/glm-5.json. Free reuse requires attribution to tkx.org.
About
GLM 5 is an AI model served by multiple inference providers on AI model marketplaces, known for its capabilities in natural language processing tasks.
AI-generated summary from public information — is this yours?
FAQ
How much does GLM 5 cost?
Cheapest measured offer right now: $0.6/1M input, $1.92/1M output via StreamLake (fp8) — across 14 tracked providers, refreshed hourly.
Who serves GLM 5?
14 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of GLM 5 going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.