{"source":"BenchGecko","url":"https://benchgecko.ai/model/deepseek-v4-1-flash","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/deepseek-v4-1-flash","cite":"DeepSeek V4.1 Flash · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/deepseek-v4-1-flash","slug":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","provider":{"name":"DeepSeek","slug":"deepseek"},"model_type":"multimodal","release_date":"2026-09-10","is_open_source":false,"status":"active","context_window":1048576,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","benchgecko_score":{"value":58.7,"rank":96,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":58.7,"list_price":{"input_usd_per_m":0.15,"output_usd_per_m":0.6,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.15,"output":0.6},"providers":[{"provider":"Relace","endpoint":"relace","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.003,"output_usd_per_m":2.4,"cache_read_usd_per_m":0.003,"uptime_1d_pct":99.93,"as_of":"2026-10-05"},{"provider":"InferenceNet","endpoint":"inference-net","quantization":null,"context_tokens":1040000,"input_usd_per_m":0.05,"output_usd_per_m":0.3,"cache_read_usd_per_m":0.018,"uptime_1d_pct":99.25,"as_of":"2026-10-05"},{"provider":"Morph","endpoint":"morph/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.058,"output_usd_per_m":0.45,"cache_read_usd_per_m":0.008,"uptime_1d_pct":96.13,"as_of":"2026-10-05"},{"provider":"Wafer","endpoint":"wafer","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.065,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.06,"uptime_1d_pct":99.9,"as_of":"2026-10-05"},{"provider":"Sail Research","endpoint":"sail-research/fp4","quantization":"fp4","context_tokens":1048576,"input_usd_per_m":0.08,"output_usd_per_m":0.4,"cache_read_usd_per_m":0.01,"uptime_1d_pct":98.06,"as_of":"2026-10-05"},{"provider":"Decart","endpoint":"decart/fp4","quantization":"fp4","context_tokens":1048576,"input_usd_per_m":0.09,"output_usd_per_m":0.18,"cache_read_usd_per_m":0.018,"uptime_1d_pct":98.47,"as_of":"2026-10-05"},{"provider":"Ionstream","endpoint":"ionstream","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.1188,"output_usd_per_m":1.15,"cache_read_usd_per_m":0.0055,"uptime_1d_pct":98.77,"as_of":"2026-10-05"},{"provider":"DekaLLM","endpoint":"dekallm","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.12,"output_usd_per_m":2.4,"cache_read_usd_per_m":0.005,"uptime_1d_pct":97.02,"as_of":"2026-10-05"},{"provider":"DeepInfra","endpoint":"deepinfra/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.14,"output_usd_per_m":0.42,"cache_read_usd_per_m":0.0042,"uptime_1d_pct":99.95,"as_of":"2026-10-05"},{"provider":"AtlasCloud","endpoint":"atlas-cloud/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.141,"output_usd_per_m":0.564,"cache_read_usd_per_m":0.0141,"uptime_1d_pct":99.81,"as_of":"2026-10-05"},{"provider":"StreamLake","endpoint":"streamlake/fp8","quantization":"fp8","context_tokens":1024000,"input_usd_per_m":0.141,"output_usd_per_m":0.564,"cache_read_usd_per_m":0.00282,"uptime_1d_pct":99.86,"as_of":"2026-10-05"},{"provider":"DigitalOcean","endpoint":"digitalocean","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.18,"output_usd_per_m":0.72,"cache_read_usd_per_m":0.0036,"uptime_1d_pct":99.75,"as_of":"2026-10-05"},{"provider":"GMICloud","endpoint":"gmicloud/fp8","quantization":"fp8","context_tokens":1048575,"input_usd_per_m":0.18,"output_usd_per_m":0.72,"cache_read_usd_per_m":0.0036,"uptime_1d_pct":99.52,"as_of":"2026-10-05"},{"provider":"CoreWeave","endpoint":"coreweave/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.2,"output_usd_per_m":0.65,"cache_read_usd_per_m":0.03,"uptime_1d_pct":98.98,"as_of":"2026-10-05"},{"provider":"NextBit","endpoint":"nextbit/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.21,"output_usd_per_m":0.84,"cache_read_usd_per_m":0.004,"uptime_1d_pct":99.98,"as_of":"2026-10-05"},{"provider":"Phala","endpoint":"phala","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.21,"output_usd_per_m":0.84,"cache_read_usd_per_m":0.0042,"uptime_1d_pct":99.93,"as_of":"2026-10-05"},{"provider":"Novita","endpoint":"novita/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.24,"output_usd_per_m":0.96,"cache_read_usd_per_m":0.0048,"uptime_1d_pct":99.92,"as_of":"2026-10-05"},{"provider":"Makora","endpoint":"makora/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.27,"output_usd_per_m":1.15,"cache_read_usd_per_m":0.009,"uptime_1d_pct":99.93,"as_of":"2026-10-05"},{"provider":"Alibaba","endpoint":"alibaba","quantization":null,"context_tokens":1000000,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.03,"uptime_1d_pct":97.07,"as_of":"2026-10-05"},{"provider":"Baidu","endpoint":"baidu/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.006,"uptime_1d_pct":99.83,"as_of":"2026-10-05"},{"provider":"BaseTen","endpoint":"baseten/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.007,"uptime_1d_pct":99.96,"as_of":"2026-10-05"},{"provider":"DeepSeek","endpoint":"deepseek","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.006,"uptime_1d_pct":99.99,"as_of":"2026-10-05"},{"provider":"Fireworks","endpoint":"fireworks","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.006,"uptime_1d_pct":92.49,"as_of":"2026-10-05"},{"provider":"Modal","endpoint":"modal","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.03,"uptime_1d_pct":99.8,"as_of":"2026-10-05"},{"provider":"Parasail","endpoint":"parasail/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.006,"uptime_1d_pct":99.76,"as_of":"2026-10-05"},{"provider":"SiliconFlow","endpoint":"siliconflow/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.006,"uptime_1d_pct":99.64,"as_of":"2026-10-05"},{"provider":"Together","endpoint":"together","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.006,"uptime_1d_pct":99.93,"as_of":"2026-10-05"},{"provider":"Venice","endpoint":"venice/fp8","quantization":"fp8","context_tokens":1000000,"input_usd_per_m":0.3,"output_usd_per_m":1.2,"cache_read_usd_per_m":0.0075,"uptime_1d_pct":99.17,"as_of":"2026-10-05"},{"provider":"Fireworks","endpoint":"fireworks/us","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.45,"output_usd_per_m":1.8,"cache_read_usd_per_m":0.009,"uptime_1d_pct":97.25,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"Relace","endpoint":"relace","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.003,"output_usd_per_m":2.4,"cache_read_usd_per_m":0.003,"uptime_1d_pct":99.93,"as_of":"2026-10-05"},"providers_source":"OpenRouter endpoints API, one row per provider, refreshed daily","scores":[{"benchmark":"Artificial Analysis · Long Context Reasoning","benchmark_slug":"aa-long-context-reasoning","score":84,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-long-context-reasoning"},{"benchmark":"Dtbench","benchmark_slug":"dtbench","score":83.12,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/dtbench"},{"benchmark":"Artificial Analysis · MMMU Pro","benchmark_slug":"aa-mmmu-pro","score":77,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-mmmu-pro"},{"benchmark":"Lmca","benchmark_slug":"lmca","score":55.26,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/lmca"},{"benchmark":"Artificial Analysis · GDPval","benchmark_slug":"aa-gdpval","score":55,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-gdpval"},{"benchmark":"Proofbench","benchmark_slug":"proofbench","score":54,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/proofbench"},{"benchmark":"Artificial Analysis · SciCode","benchmark_slug":"aa-scicode","score":51.9,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-scicode"},{"benchmark":"Surface Evolver Bench","benchmark_slug":"surface-evolver-bench","score":46.25,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/surface-evolver-bench"},{"benchmark":"Artificial Analysis — Quality Index","benchmark_slug":"aa-quality-index","score":39.46,"unit":"index","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-quality-index"},{"benchmark":"Artificial Analysis · Humanity's Last Exam","benchmark_slug":"aa-humanitys-last-exam","score":39.2,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-humanitys-last-exam"},{"benchmark":"Artificial Analysis · CritPt","benchmark_slug":"aa-critpt","score":14.3,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-critpt"}],"gecko_tests":{"gecko_score":12,"rank":13,"tests_taken":3,"tests":[{"test":"who-are-you","name":"Who Are You","grade":"E","value":60,"verdict":"Sometimes says it is OpenAI","url":"https://benchgecko.ai/gecko-tests/who-are-you"},{"test":"censorship-index","name":"Censorship Index","grade":"E","value":94.4,"verdict":"Refuses or dodges 6%","url":"https://benchgecko.ai/gecko-tests/censorship-index"},{"test":"tokenizer-tax","name":"Tokenizer Tax","grade":"D","value":32,"verdict":"68% 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/deepseek-v4-1-flash","json":"https://benchgecko.ai/api/v1/models/deepseek-v4-1-flash","price_history":"https://benchgecko.ai/api/v1/price-history/deepseek-v4-1-flash","provider_prices":"https://benchgecko.ai/pricing/arbitrage/deepseek-v4-1-flash"}}