The board shows this model's cheapest measured offer ($0.877/1M); the smaller figure under it is the mean of the 21 offers listed below ($1.27/1M). Add those up and divide — it matches.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| Alibaba (fp8) | OpenRouter | $0.390 | $2.34 | 871ms | 61 | 98.9% | API-measured |
| DigitalOcean | OpenRouter | $0.385 | $2.45 | 1191ms | 12 | 98.3% | API-measured |
| burncloud | burncloud | $0.430 | $2.58 | — | — | — | API-measured |
| deepinfra | HuggingFace Router | $0.450 | $3.00 | 241ms | 77 | — | API-measured |
| Chutes (fp8) | OpenRouter | $0.450 | $3.00 | 910ms | 58 | 100% | API-measured |
| DeepInfra (fp8) | OpenRouter | $0.450 | $3.00 | 397ms | 63 | 98.4% | API-measured |
| requesty | Requesty | $0.490 | $3.60 | — | — | — | API-measured |
| Parasail (fp8) | OpenRouter | $0.500 | $3.60 | 556ms | 77 | 98.6% | API-measured |
| AtlasCloud (fp8) | OpenRouter | $0.550 | $3.50 | 1127ms | 51 | 98.1% | API-measured |
| Phala | OpenRouter | $0.550 | $3.50 | 991ms | 62 | 100% | API-measured |
| openrouter | Pricebook (LiteLLM) | $0.600 | $3.60 | — | — | — | Official list |
| together_ai | Pricebook (LiteLLM) | $0.600 | $3.60 | — | — | — | Official list |
| scaleway | Pricebook (LiteLLM) | $0.600 | $3.60 | — | — | — | Official list |
| Novita | OpenRouter | $0.600 | $3.60 | 896ms | 58 | 97.2% | API-measured |
| StreamLake | OpenRouter | $0.600 | $3.60 | 1382ms | 48 | 95.2% | API-measured |
| GMICloud (fp8) | OpenRouter | $0.600 | $3.60 | — | — | — | API-measured |
| novita | HuggingFace Router | $0.600 | $3.60 | 960ms | 64 | — | API-measured |
| novita-ai | Novita AI | $0.600 | $3.60 | — | — | — | API-measured |
| scaleway | HuggingFace Router | $0.684 | $4.10 | 554ms | 105 | — | API-measured |
| ovhcloud | HuggingFace Router | $0.710 | $4.25 | 460ms | 122 | — | API-measured |
| Venice | OpenRouter | $0.750 | $4.50 | 960ms | 43 | 95.4% | API-measured |
Price trend
Cheapest blended price, last 31 days (USD/1M): $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.5704 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775 → $0.8775
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/qwen3.5-397b-a17b.json. Free reuse requires attribution to tkx.org.
About
Qwen3.5 397B A17B is a large language 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 Qwen3.5 397B A17B cost?
Cheapest measured offer right now: $0.39/1M input, $2.34/1M output via Alibaba (fp8) — across 17 tracked providers, refreshed hourly.
Who serves Qwen3.5 397B A17B?
17 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of Qwen3.5 397B A17B going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.