glm-5.3-flash
openrouter · 1311K ctx · 30 providers · updated 2026-09-12 06:15 UTC
The board shows this model's cheapest measured offer ($0.119/1M); the smaller figure under it is the mean of the 38 offers listed below ($0.230/1M). Add those up and divide — it matches. 24h token volume (1.7T) 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: 3.68% of gateway token volume, —% of spend (2026-09-12; share-of-traffic, daily, data CC BY 4.0).
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| openrouter | Pricebook (LiteLLM) ↗ | $0.075 | $0.250 | — | — | — | Official list |
| requesty | Requesty ↗ | $0.075 | $0.250 | — | — | — | API-measured |
| DeepInfra (fp4) | OpenRouter ↗ | $0.075 | $0.250 | 1729ms | 16 | 97.4% | API-measured |
| Relace | OpenRouter ↗ | $0.090 | $0.300 | 1128ms | 47 | 99.9% | API-measured |
| Morph (fp8) | OpenRouter ↗ | $0.100 | $0.350 | 1998ms | 15 | 98.6% | API-measured |
| Wafer | OpenRouter ↗ | $0.100 | $0.350 | 1061ms | 21 | 99.9% | API-measured |
| StreamLake (fp8) | OpenRouter ↗ | $0.112 | $0.374 | 5521ms | 46 | 99.9% | API-measured |
| GMICloud (fp8) | OpenRouter ↗ | $0.113 | $0.375 | 3735ms | 37 | 98.9% | API-measured |
| Novita (fp8) | OpenRouter ↗ | $0.132 | $0.440 | 2660ms | 30 | 99.4% | API-measured |
| Makora | OpenRouter ↗ | $0.140 | $0.470 | 505ms | 46 | 100% | API-measured |
| friendliai | Pricebook (LiteLLM) ↗ | $0.150 | $0.500 | — | — | — | Official list |
| nebius | Pricebook (LiteLLM) ↗ | $0.150 | $0.500 | — | — | — | Official list |
| together_ai | Pricebook (LiteLLM) ↗ | $0.150 | $0.500 | — | — | — | Official list |
| zai | Pricebook (LiteLLM) ↗ | $0.150 | $0.500 | — | — | — | Official list |
| novita | HuggingFace Router ↗ | $0.150 | $0.500 | 1208ms | 73 | — | API-measured |
| together | HuggingFace Router ↗ | $0.150 | $0.500 | 213ms | 82 | — | API-measured |
| baseten | HuggingFace Router ↗ | $0.150 | $0.500 | 390ms | 114 | — | API-measured |
| deepinfra | HuggingFace Router ↗ | $0.150 | $0.500 | 3072ms | 8 | — | API-measured |
| novita-ai | Novita AI ↗ | $0.150 | $0.500 | — | — | — | API-measured |
| Crusoe (fp4) | OpenRouter ↗ | $0.150 | $0.500 | 773ms | 109 | 95.9% | API-measured |
| CoreWeave (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 1402ms | 63 | 100% | API-measured |
| Sail Research (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 1831ms | 22 | 99.5% | API-measured |
| NextBit (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 2614ms | 33 | 99.9% | API-measured |
| Fireworks | OpenRouter ↗ | $0.150 | $0.500 | 784ms | 88 | 99.9% | API-measured |
| Phala (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 3821ms | 39 | 99.4% | API-measured |
| Friendli | OpenRouter ↗ | $0.150 | $0.500 | 736ms | 95 | 99.6% | API-measured |
| SiliconFlow (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 2236ms | 37 | 100% | API-measured |
| DigitalOcean | OpenRouter ↗ | $0.150 | $0.500 | 1188ms | 45 | 100% | API-measured |
| Together | OpenRouter ↗ | $0.150 | $0.500 | 631ms | 80 | 99.4% | API-measured |
| Reka (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 933ms | 75 | 100.0% | API-measured |
| Parasail (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 1406ms | 55 | 97.8% | API-measured |
| BaseTen (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 676ms | 123 | 100.0% | API-measured |
| Venice | OpenRouter ↗ | $0.150 | $0.500 | 1758ms | 16 | 100.0% | API-measured |
| Io Net (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 1384ms | 27 | 99.9% | API-measured |
| Cloudflare | OpenRouter ↗ | $0.150 | $0.500 | 982ms | 50 | 100% | API-measured |
| Z.AI (fp8) | OpenRouter ↗ | $0.150 | $0.500 | 2721ms | 35 | 99.8% | API-measured |
| 0g-teetls | 0G Router ↗ | $0.158 | $0.525 | — | — | — | API-measured |
| Modal (fp8) | OpenRouter ↗ | $0.450 | $1.50 | 1266ms | 58 | 99.9% | API-measured |
Volume trend
Last 17 days: 361B → 1.7T (+381%); range 361B–2.0T 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-5.3-flash.json. Free reuse requires attribution to tkx.org.
FAQ
How much does glm-5.3-flash cost?
Cheapest measured offer right now: $0.075/1M input, $0.25/1M output via openrouter — across 30 tracked providers, refreshed hourly.
Who serves glm-5.3-flash?
30 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
How heavily is glm-5.3-flash used?
glm-5.3-flash routed 1.7T 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.