--- title: "Qwen: Qwen3.6 35B A3B — unrated, priced in this catalogue · Undominated.ai" canonical: https://undominated.ai/models/qwen__qwen3.6-35b-a3b/ description: "Qwen: Qwen3.6 35B A3B: $0.100/M in, $0.900/M out. No independent quality score in this catalogue — unrated, not ranked, not scored zero." --- # Qwen: Qwen3.6 35B A3B — unrated, priced in this catalogue · Undominated.ai > Qwen: Qwen3.6 35B A3B: $0.100/M in, $0.900/M out. No independent quality score in this catalogue — unrated, not ranked, not scored zero. [Check base rates for this workload](/check/qwen__qwen3.6-35b-a3b/) [Cheaper alternatives](/alternatives/) [Family](/families/qwen/) [Compare models](https://undominated.ai/compare/?models=qwen%2Fqwen3.6-35b-a3b) Comparison context Choose up to three standard models in Compare. Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls. MODEL PROOF # Qwen3.6 35B A3B Qwen · 27 Apr 2026 Balanced Summarise Chat Code gen Agentic NOT INDEPENDENTLY RATED ## No independent LMArena score is published for this model. **$0.300** / 1M tokens Balanced · 3 tokens in per 1 out Serving precision differs between offers. Evidence as of 06 Oct 2026 [openrouter/models](https://openrouter.ai/api/v1/models) Independent LMArena score Not independently rated Context window 262.14K Maximum output 235.93K Input modalities text, image, video Output modalities text Published input price $0.100 / 1M tokens Published output price $0.900 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from AkashML: the cheapest offer that is serving, at standard delivery and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known. Cheaper right now: $0.213/M at Darkbloom — 4-bit It does not pass the like-for-like test, so it never sets a rank. Every price dimension · USD per million tokens | Input | $0.100 /M | | --- | --- | | Output | $0.900 /M | | Cached input | $0.050 /M | | Cache write | Unknown /M | | Cache write 1h | Unknown /M | | Reasoning | Unknown /M | ### Who sells it The same weights, different shops. Cheapest is not like-for-like when serving precision differs. Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.100/M from AkashML. 10 provider offers · rates, limits and conditions Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test. | Seller | Input | Output | Precision | Uptime (1d) | | --- | --- | --- | --- | --- | | Seller Darkbloom darkbloom/fp4 Endpoint terms Cached input /M $0.025 Context limit 262,144 tokens Output limit 32,768 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.98% | Input $0.050 | Output $0.700 | Precision fp4 | Uptime (1d) 99.83% | | Seller AkashML akashml/fp8 Endpoint terms Cached input /M $0.050 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.98% | Input $0.100 | Output $0.900 | Precision fp8 | Uptime (1d) 99.98% | | Seller DeepInfra deepinfra/fp8 Endpoint terms Cached input /M $0.100 Context limit 262,144 tokens Output limit 65,536 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.93% | Input $0.100 | Output $0.950 | Precision fp8 | Uptime (1d) 99.83% | | Seller Venice venice/fp8 Endpoint terms Cached input /M Unknown Context limit 256,000 tokens Output limit 65,536 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.100 | Output $1.00 | Precision fp8 | Uptime (1d) 99.90% | | Seller DekaLLM dekallm Endpoint terms Cached input /M $0.050 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.54% | Input $0.100 | Output $1.00 | Precision undeclared | Uptime (1d) 99.70% | | Seller Parasail parasail/fp8 Endpoint terms Cached input /M $0.050 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.99% | Input $0.150 | Output $1.00 | Precision fp8 | Uptime (1d) 99.98% | | Seller AtlasCloud atlas-cloud/fp8 Endpoint terms Cached input /M $0.186 Context limit 262,144 tokens Output limit 65,536 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.186 | Output $1.11 | Precision fp8 | Uptime (1d) 98.43% | | Seller Phala phala Endpoint terms Cached input /M $0.056 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.81% | Input $0.200 | Output $1.27 | Precision undeclared | Uptime (1d) 99.54% | | Seller SiliconFlow siliconflow/fp8 Endpoint terms Cached input /M $0.150 Context limit 262,144 tokens Output limit 235,929 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 98.56% | Input $0.240 | Output $1.80 | Precision fp8 | Uptime (1d) 98.79% | | Seller CoreWeave coreweave/fp8 Endpoint terms Cached input /M $0.250 Context limit 262,144 tokens Output limit 235,929 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.250 | Output $1.25 | Precision fp8 | Uptime (1d) 99.91% | ### Independent scores No independent benchmark has measured this model. Unrated is not a score of zero. ### Capability | Context window | 262K | | --- | --- | | Max output | 235K | | Input modes | text, image, video | | Tool use | yes | | Reasoning | optional | | Open weights | Unknown | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | unrated | Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated... ## Questions this page answers What does Qwen3.6 35B A3B cost? $0.100/M in, $0.900/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does Qwen3.6 35B A3B have an independent quality score? Qwen3.6 35B A3B has no independent quality score in this catalogue. Unrated is not a score of zero. What beats Qwen3.6 35B A3B? Qwen3.6 35B A3B has no independent quality score. Unrated is not a score of zero. Does this page use Artificial Analysis scores for Qwen3.6 35B A3B? No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated. Does a missing score mean Qwen3.6 35B A3B scored zero? Unrated is not a score of zero. Is the cheapest Qwen3.6 35B A3B endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.100/M from AkashML. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options Qwen: Qwen3.6 35B A3B. Balanced workload. Not independently rated. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related No independent quality score, so there is no dominator to name. Unrated is not a clean bill of health. - Same vendor [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) - Qwen models [Qwen](/providers/qwen/) - Where this model appears [wire](/wire/) - Same vendor [Qwen3.6 Max Preview](/models/qwen__qwen3.6-max-preview/) - Where this model appears [spreads](/spreads/) - Same vendor [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) - Where this model appears [traps](/traps/) ## Badge The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not. Markdown Copy [![Qwen3.6 35B A3B — Undominated.ai dominance verdict](https://undominated.ai/badge/qwen__qwen3.6-35b-a3b.svg)](https://undominated.ai/models/qwen__qwen3.6-35b-a3b/) HTML Copy Qwen3.6 35B A3B — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/qwen__qwen3.6-35b-a3b.svg](https://undominated.ai/badge/qwen__qwen3.6-35b-a3b.svg) — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy. ## Continue your investigation - [Explore model families](/families/) - [Compare a shortlist](/compare/) - [Check a model](/check/) - [Understand the evidence](/methodology/)