{"source":"BenchGecko","url":"https://benchgecko.ai/model/qwen3-8-2-4t-a95b","as_of":"2026-10-05","license":"BenchGecko collected data (prices, provider offers, Gecko Tests) is CC BY 4.0 · https://creativecommons.org/licenses/by/4.0/. Benchmark scores belong to their original publishers (see sources) and are aggregated with attribution. Attribution required: \"Source: BenchGecko\" with a link.","attribution":"Source: BenchGecko · https://benchgecko.ai/model/qwen3-8-2-4t-a95b","cite":"Qwen3.8 2.4T A95B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/qwen3-8-2-4t-a95b","slug":"qwen3-8-2-4t-a95b","name":"Qwen3.8 2.4T A95B","provider":{"name":"Alibaba Qwen","slug":"alibaba"},"model_type":"text","release_date":"2026-08-12","is_open_source":false,"status":"active","context_window":1048576,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is...","benchgecko_score":null,"avg_score":0,"list_price":{"input_usd_per_m":2,"output_usd_per_m":6,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":2,"output":6},"providers":[{"provider":"Alibaba","endpoint":"alibaba","quantization":null,"context_tokens":1000000,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.25,"uptime_1d_pct":99.84,"as_of":"2026-10-05"},{"provider":"DeepInfra","endpoint":"deepinfra/fp4","quantization":"fp4","context_tokens":262144,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.2,"uptime_1d_pct":99.96,"as_of":"2026-10-05"},{"provider":"Modal","endpoint":"modal","quantization":null,"context_tokens":1000000,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.25,"uptime_1d_pct":99.8,"as_of":"2026-10-05"},{"provider":"Novita","endpoint":"novita","quantization":null,"context_tokens":1000000,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.25,"uptime_1d_pct":99.96,"as_of":"2026-10-05"},{"provider":"SiliconFlow","endpoint":"siliconflow/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.25,"uptime_1d_pct":99.92,"as_of":"2026-10-05"},{"provider":"Together","endpoint":"together","quantization":null,"context_tokens":1010000,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.25,"uptime_1d_pct":99.92,"as_of":"2026-10-05"},{"provider":"Venice","endpoint":"venice","quantization":null,"context_tokens":262144,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.25,"uptime_1d_pct":97.35,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"Alibaba","endpoint":"alibaba","quantization":null,"context_tokens":1000000,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.25,"uptime_1d_pct":99.84,"as_of":"2026-10-05"},"providers_source":"OpenRouter endpoints API, one row per provider, refreshed daily","scores":[{"benchmark":"Artificial Analysis · GPQA Diamond","benchmark_slug":"aa-gpqa-diamond","score":93.5,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-gpqa-diamond"},{"benchmark":"Artificial Analysis · Long Context Reasoning","benchmark_slug":"aa-long-context-reasoning","score":80.3,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-long-context-reasoning"},{"benchmark":"Artificial Analysis · GDPval","benchmark_slug":"aa-gdpval","score":54.9,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-gdpval"},{"benchmark":"Artificial Analysis · SciCode","benchmark_slug":"aa-scicode","score":54.1,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-scicode"},{"benchmark":"Artificial Analysis · Humanity's Last Exam","benchmark_slug":"aa-humanitys-last-exam","score":42.4,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-humanitys-last-exam"},{"benchmark":"Artificial Analysis — Quality Index","benchmark_slug":"aa-quality-index","score":39.89,"unit":"index","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-quality-index"},{"benchmark":"Artificial Analysis · CritPt","benchmark_slug":"aa-critpt","score":20,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-critpt"}],"gecko_tests":{"gecko_score":null,"rank":null,"tests_taken":2,"tests":[{"test":"who-are-you","name":"Who Are You","grade":"B","value":100,"verdict":"Knows who made it","url":"https://benchgecko.ai/gecko-tests/who-are-you"},{"test":"tokenizer-tax","name":"Tokenizer Tax","grade":"A","value":61.1,"verdict":"39% more tokens outside English","url":"https://benchgecko.ai/gecko-tests/tokenizer-tax"}],"scorecard_url":"https://benchgecko.ai/gecko-tests/scorecard"},"links":{"page":"https://benchgecko.ai/model/qwen3-8-2-4t-a95b","json":"https://benchgecko.ai/api/v1/models/qwen3-8-2-4t-a95b","price_history":"https://benchgecko.ai/api/v1/price-history/qwen3-8-2-4t-a95b","provider_prices":"https://benchgecko.ai/pricing/arbitrage/qwen3-8-2-4t-a95b"}}