The board shows this model's cheapest measured offer ($0.030/1M); the smaller figure under it is the mean of the 24 offers listed below ($0.430/1M). Add those up and divide — it matches.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| PrimeIntellect (fp8) | OpenRouter ↗ | $0.010 | $0.092 | 605ms | 68 | 100% | API-measured |
| sail | Pricebook (LiteLLM) ↗ | $0.050 | $0.400 | — | — | — | Official list |
| Darkbloom (fp4) | OpenRouter ↗ | $0.050 | $0.700 | 3884ms | 44 | 99.9% | API-measured |
| pinstripes | Pricebook (LiteLLM) ↗ | $0.140 | $0.450 | — | — | — | Official list |
| libertai | Pricebook (LiteLLM) ↗ | $0.150 | $0.500 | — | — | — | Official list |
| AkashML (fp8) | OpenRouter ↗ | $0.100 | $0.900 | 619ms | 114 | 100% | API-measured |
| Parasail (fp8) | OpenRouter ↗ | $0.100 | $0.900 | 562ms | 107 | 100% | API-measured |
| deepinfra | Pricebook (LiteLLM) ↗ | $0.100 | $0.950 | — | — | — | Official list |
| deepinfra | HuggingFace Router ↗ | $0.100 | $0.950 | 429ms | 128 | — | API-measured |
| DeepInfra (fp8) | OpenRouter ↗ | $0.100 | $0.950 | 301ms | 112 | 100% | API-measured |
| CoreWeave (fp8) | OpenRouter ↗ | $0.100 | $0.950 | 526ms | 124 | 100% | API-measured |
| DekaLLM | OpenRouter ↗ | $0.100 | $1.00 | 474ms | 128 | 100% | API-measured |
| Venice (fp8) | OpenRouter ↗ | $0.100 | $1.00 | 802ms | 66 | 100% | API-measured |
| Phala | OpenRouter ↗ | $0.200 | $1.27 | 1152ms | 96 | 100% | API-measured |
| wandb | Pricebook (LiteLLM) ↗ | $0.250 | $1.25 | — | — | — | Official list |
| AtlasCloud (fp8) | OpenRouter ↗ | $0.250 | $1.25 | 609ms | 77 | 100% | API-measured |
| zerogpu | Pricebook (LiteLLM) ↗ | $0.200 | $1.50 | — | — | — | Official list |
| novita | Pricebook (LiteLLM) ↗ | $0.248 | $1.49 | — | — | — | Official list |
| novita-ai | Novita AI ↗ | $0.248 | $1.49 | — | — | — | API-measured |
| scaleway | Pricebook (LiteLLM) ↗ | $0.250 | $1.50 | — | — | — | Official list |
| aihubmix | Pricebook (LiteLLM) ↗ | $0.254 | $1.52 | — | — | — | Official list |
| SiliconFlow (fp8) | OpenRouter ↗ | $0.240 | $1.80 | 1693ms | 21 | 98.5% | API-measured |
| streamlake | Pricebook (LiteLLM) ↗ | $0.375 | $2.25 | — | — | — | Official list |
| 0g-teetls | 0G Router ↗ | $0.563 | $3.38 | — | — | — | API-measured |
Price trend
Cheapest blended price, last 31 days (USD/1M): $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.1375 → $0.0305 → $0.0305 → $0.0305
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/qwen3.6-35b-a3b.json. Free reuse requires attribution to tkx.org.
About
"qwen3.6-35b-a3b" is a large language model served by multiple inference providers on AI model marketplaces, listed under the "pinstripes" serving-platform tag. It is designed for natural language processing tasks, such as text generation and understanding.
AI-generated summary from public information — is this yours?
FAQ
How much does Qwen3.6 35B A3B cost?
Cheapest measured offer right now: $0.01/1M input, $0.092/1M output via PrimeIntellect (fp8) — across 21 tracked providers, refreshed hourly.
Who serves Qwen3.6 35B A3B?
21 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of Qwen3.6 35B A3B going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.