The board shows this model's cheapest measured offer ($0.825/1M); the smaller figure under it is the mean of the 44 offers listed below ($1.99/1M). Add those up and divide — it matches. 24h token volume (408B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here. Cross-check — Vercel AI Gateway: 6.29% of gateway token volume, 3.9% of spend (2026-08-04; share-of-traffic, daily, data CC BY 4.0).
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| Decart (fp4) | OpenRouter | $0.600 | $1.50 | 831ms | 72 | 100.0% | API-measured |
| StreamLake (fp8) | OpenRouter | $0.693 | $2.18 | 2132ms | 32 | 99.5% | API-measured |
| Novita (fp8) | OpenRouter | $0.700 | $2.20 | 2962ms | 23 | 97.0% | API-measured |
| deepinfra | HuggingFace Router | $0.750 | $2.40 | 652ms | 38 | — | API-measured |
| DeepInfra (fp4) | OpenRouter | $0.750 | $2.40 | 1444ms | 39 | 99.8% | API-measured |
| CoreWeave (fp4) | OpenRouter | $0.760 | $2.42 | 677ms | 96 | 99.9% | API-measured |
| AkashML (fp8) | OpenRouter | $0.770 | $2.42 | 1332ms | 57 | 92.9% | API-measured |
| GMICloud (fp8) | OpenRouter | $0.924 | $2.90 | 3465ms | 32 | 99.7% | API-measured |
| 0g-teeml | 0G Router | $0.900 | $3.00 | — | — | — | API-measured |
| Inceptron (fp4) | OpenRouter | $0.940 | $2.90 | 763ms | 29 | 100.0% | API-measured |
| Alibaba (fp8) | OpenRouter | $0.966 | $3.04 | 1801ms | 41 | 99.9% | API-measured |
| requesty | Requesty | $1.05 | $3.30 | — | — | — | API-measured |
| Sail Research (fp8) | OpenRouter | $1.00 | $3.50 | 1439ms | 22 | 98.9% | API-measured |
| Baidu (fp8) | OpenRouter | $1.18 | $3.70 | 1076ms | 61 | 100.0% | API-measured |
| SiliconFlow (fp8) | OpenRouter | $1.19 | $3.74 | 2001ms | 37 | 100.0% | API-measured |
| Morph | OpenRouter | $1.10 | $4.10 | 1894ms | 42 | 96.1% | API-measured |
| DigitalOcean | OpenRouter | $1.05 | $4.40 | 1333ms | 48 | 99.4% | API-measured |
| Ambient (fp8) | OpenRouter | $1.05 | $4.40 | 947ms | 94 | 99.5% | API-measured |
| burncloud | burncloud | $1.18 | $4.14 | — | — | — | API-measured |
| Chutes (fp4) | OpenRouter | $1.25 | $3.95 | 1673ms | 28 | 94.8% | API-measured |
| Wafer | OpenRouter | $1.26 | $3.96 | 2762ms | 92 | 100% | API-measured |
| AtlasCloud (fp8) | OpenRouter | $1.26 | $3.96 | 4363ms | 44 | 98.3% | API-measured |
| Phala | OpenRouter | $1.26 | $3.96 | 2148ms | 32 | 96.7% | API-measured |
| cloudflare | Pricebook (LiteLLM) | $1.40 | $4.40 | — | — | — | Official list |
| novita | HuggingFace Router | $1.40 | $4.40 | 1878ms | 38 | — | API-measured |
| together | HuggingFace Router | $1.40 | $4.40 | 447ms | 144 | — | API-measured |
| fireworks-ai | HuggingFace Router | $1.40 | $4.40 | 1178ms | 39 | — | API-measured |
| baseten | HuggingFace Router | $1.40 | $4.40 | 1796ms | 45 | — | API-measured |
| novita-ai | Novita AI | $1.40 | $4.40 | — | — | — | API-measured |
| Z.AI (fp8) | OpenRouter | $1.40 | $4.40 | 3309ms | 41 | 99.9% | API-measured |
| Fireworks | OpenRouter | $1.40 | $4.40 | 1058ms | 54 | 99.6% | API-measured |
| Cloudflare | OpenRouter | $1.40 | $4.40 | 1564ms | 90 | 100% | API-measured |
| Friendli | OpenRouter | $1.40 | $4.40 | 1592ms | 44 | 99.5% | API-measured |
| Parasail (fp4) | OpenRouter | $1.40 | $4.40 | 1174ms | 84 | 99.6% | API-measured |
| Venice (fp8) | OpenRouter | $1.40 | $4.40 | 1149ms | 49 | 99.0% | API-measured |
| Together | OpenRouter | $1.40 | $4.40 | 1260ms | 58 | 92.1% | API-measured |
| Crusoe (fp8) | OpenRouter | $1.40 | $4.40 | 925ms | 82 | 97.7% | API-measured |
| BaseTen (fp8) | OpenRouter | $1.40 | $4.40 | 2068ms | 43 | 99.8% | API-measured |
| scaleway | HuggingFace Router | $2.05 | $6.27 | 599ms | 65 | — | API-measured |
| Wafer (fast) | OpenRouter | $2.10 | $6.60 | 3998ms | 81 | 98.7% | API-measured |
Volume trend
Last 30 days: 364B → 408B (+12%); range 230B–659B tokens/day. Source: OpenRouter public rankings; refreshed hourly.
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-5.2.json. Free reuse requires attribution to tkx.org.
About
GLM 5.2 is a large language model AI system designed for natural language processing tasks. It is served by multiple inference providers on AI model marketplaces and is listed under the organization tag "z-ai".
AI-generated summary from public information — is this yours?
FAQ
How much does GLM 5.2 cost?
Cheapest measured offer right now: $0.6/1M input, $1.5/1M output via Decart (fp4) — across 32 tracked providers, refreshed hourly.
Who serves GLM 5.2?
32 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
How heavily is GLM 5.2 used?
GLM 5.2 routed 408B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.