{"source":"BenchGecko","url":"https://benchgecko.ai/model/deepseek-v4-flash-0731","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-flash-0731","cite":"DeepSeek V4 Flash 0731 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/deepseek-v4-flash-0731","slug":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","provider":{"name":"DeepSeek","slug":"deepseek"},"model_type":"text","release_date":"2026-07-31","is_open_source":false,"status":"active","context_window":1048576,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","benchgecko_score":{"value":60.1,"rank":86,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":60.1,"list_price":{"input_usd_per_m":0.0152,"output_usd_per_m":1.28,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.0152,"output":1.28},"providers":[{"provider":"Relace","endpoint":"relace/fp4","quantization":"fp4","context_tokens":1048576,"input_usd_per_m":0.0152,"output_usd_per_m":1.28,"cache_read_usd_per_m":0.0152,"uptime_1d_pct":99.82,"as_of":"2026-10-05"},{"provider":"Sail Research","endpoint":"sail-research/fp4","quantization":"fp4","context_tokens":1048576,"input_usd_per_m":0.019,"output_usd_per_m":0.3,"cache_read_usd_per_m":0.014,"uptime_1d_pct":99.44,"as_of":"2026-10-05"},{"provider":"Sail Research","endpoint":"sail-research/us","quantization":"fp4","context_tokens":1048576,"input_usd_per_m":0.019,"output_usd_per_m":0.42,"cache_read_usd_per_m":0.012,"uptime_1d_pct":99.02,"as_of":"2026-10-05"},{"provider":"OpenInference","endpoint":"open-inference/fp4","quantization":"fp4","context_tokens":1048576,"input_usd_per_m":0.01976,"output_usd_per_m":1.664,"cache_read_usd_per_m":0.01976,"uptime_1d_pct":99.74,"as_of":"2026-10-05"},{"provider":"Reka","endpoint":"reka","quantization":null,"context_tokens":262144,"input_usd_per_m":0.021,"output_usd_per_m":0.528,"cache_read_usd_per_m":0.0056,"uptime_1d_pct":99.95,"as_of":"2026-10-05"},{"provider":"StreamLake","endpoint":"streamlake/fp8","quantization":"fp8","context_tokens":1024000,"input_usd_per_m":0.044,"output_usd_per_m":0.132,"cache_read_usd_per_m":0.0014,"uptime_1d_pct":99.79,"as_of":"2026-10-05"},{"provider":"Inceptron","endpoint":"inceptron/fp4","quantization":"fp4","context_tokens":1048576,"input_usd_per_m":0.05,"output_usd_per_m":0.65,"cache_read_usd_per_m":0.027,"uptime_1d_pct":99.96,"as_of":"2026-10-05"},{"provider":"DeepInfra","endpoint":"deepinfra/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.06,"output_usd_per_m":0.18,"cache_read_usd_per_m":0.015,"uptime_1d_pct":99.92,"as_of":"2026-10-05"},{"provider":"DigitalOcean","endpoint":"digitalocean","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.119,"output_usd_per_m":0.238,"cache_read_usd_per_m":0.0238,"uptime_1d_pct":99.94,"as_of":"2026-10-05"},{"provider":"BaseTen","endpoint":"baseten/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.13,"output_usd_per_m":0.26,"cache_read_usd_per_m":0.028,"uptime_1d_pct":99.98,"as_of":"2026-10-05"},{"provider":"CoreWeave","endpoint":"coreweave/fp8","quantization":"fp8","context_tokens":262144,"input_usd_per_m":0.13,"output_usd_per_m":0.28,"cache_read_usd_per_m":0.07,"uptime_1d_pct":100,"as_of":"2026-10-05"},{"provider":"Cohere","endpoint":"cohere","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.14,"output_usd_per_m":0.28,"cache_read_usd_per_m":0.07,"uptime_1d_pct":99.87,"as_of":"2026-10-05"},{"provider":"Parasail","endpoint":"parasail/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.14,"output_usd_per_m":0.28,"cache_read_usd_per_m":0.05,"uptime_1d_pct":99.66,"as_of":"2026-10-05"},{"provider":"Together","endpoint":"together","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.14,"output_usd_per_m":0.28,"cache_read_usd_per_m":0.03,"uptime_1d_pct":99.73,"as_of":"2026-10-05"},{"provider":"Wafer","endpoint":"wafer/fast","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.14,"output_usd_per_m":0.84,"cache_read_usd_per_m":0.08,"uptime_1d_pct":99.99,"as_of":"2026-10-05"},{"provider":"Morph","endpoint":"morph/bf16","quantization":"bf16","context_tokens":1048576,"input_usd_per_m":0.142,"output_usd_per_m":0.4,"cache_read_usd_per_m":0.036,"uptime_1d_pct":93.83,"as_of":"2026-10-05"},{"provider":"Venice","endpoint":"venice","quantization":null,"context_tokens":1000000,"input_usd_per_m":0.175,"output_usd_per_m":0.35,"cache_read_usd_per_m":0.035,"uptime_1d_pct":99.61,"as_of":"2026-10-05"},{"provider":"Mancer 2","endpoint":"mancer/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.2,"output_usd_per_m":0.6,"cache_read_usd_per_m":null,"uptime_1d_pct":99.47,"as_of":"2026-10-05"},{"provider":"SiliconFlow","endpoint":"siliconflow/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.22,"output_usd_per_m":0.66,"cache_read_usd_per_m":0.028,"uptime_1d_pct":99.48,"as_of":"2026-10-05"},{"provider":"GMICloud","endpoint":"gmicloud/fp8","quantization":"fp8","context_tokens":1048575,"input_usd_per_m":0.286,"output_usd_per_m":0.858,"cache_read_usd_per_m":0.0091,"uptime_1d_pct":99.99,"as_of":"2026-10-05"},{"provider":"Alibaba","endpoint":"alibaba","quantization":null,"context_tokens":1000000,"input_usd_per_m":0.352,"output_usd_per_m":1.056,"cache_read_usd_per_m":0.0352,"uptime_1d_pct":98.97,"as_of":"2026-10-05"},{"provider":"NextBit","endpoint":"nextbit/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.352,"output_usd_per_m":1.056,"cache_read_usd_per_m":0.012,"uptime_1d_pct":99.99,"as_of":"2026-10-05"},{"provider":"Novita","endpoint":"novita/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.4092,"output_usd_per_m":1.2276,"cache_read_usd_per_m":0.02604,"uptime_1d_pct":100,"as_of":"2026-10-05"},{"provider":"AtlasCloud","endpoint":"atlas-cloud/fp4","quantization":"fp4","context_tokens":1048576,"input_usd_per_m":0.44,"output_usd_per_m":1.32,"cache_read_usd_per_m":0.028,"uptime_1d_pct":99.87,"as_of":"2026-10-05"},{"provider":"Baidu","endpoint":"baidu/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.44,"output_usd_per_m":1.32,"cache_read_usd_per_m":0.014,"uptime_1d_pct":99.97,"as_of":"2026-10-05"},{"provider":"Cloudflare","endpoint":"cloudflare","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.44,"output_usd_per_m":1.32,"cache_read_usd_per_m":0.014,"uptime_1d_pct":99.99,"as_of":"2026-10-05"},{"provider":"Phala","endpoint":"phala","quantization":null,"context_tokens":1048576,"input_usd_per_m":0.44,"output_usd_per_m":1.32,"cache_read_usd_per_m":0.028,"uptime_1d_pct":99.87,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"Relace","endpoint":"relace/fp4","quantization":"fp4","context_tokens":1048576,"input_usd_per_m":0.0152,"output_usd_per_m":1.28,"cache_read_usd_per_m":0.0152,"uptime_1d_pct":99.82,"as_of":"2026-10-05"},"providers_source":"OpenRouter endpoints API, one row per provider, refreshed daily","scores":[{"benchmark":"OTIS Mock AIME 2024-2025","benchmark_slug":"otis-mock-aime-2024-2025","score":94.44,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/otis-mock-aime-2024-2025"},{"benchmark":"ARC-AGI","benchmark_slug":"arc-agi","score":89,"unit":"%","category":"reasoning","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/arc-agi"},{"benchmark":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":88.05,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/gpqa-diamond"},{"benchmark":"Dtbench","benchmark_slug":"dtbench","score":84.88,"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":"WeirdML","benchmark_slug":"weirdml","score":62.96,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/weirdml"},{"benchmark":"ARC-AGI-2","benchmark_slug":"arc-agi-2","score":61.39,"unit":"%","category":"reasoning","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/arc-agi-2"},{"benchmark":"FrontierMath-Tiers-1-3-v2-Private","benchmark_slug":"frontiermath-tiers-1-3-v2-private","score":57.54,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/frontiermath-tiers-1-3-v2-private"},{"benchmark":"Proofbench","benchmark_slug":"proofbench","score":56,"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":"SimpleBench","benchmark_slug":"simplebench","score":53.32,"unit":"%","category":"reasoning","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/simplebench"},{"benchmark":"Lmca","benchmark_slug":"lmca","score":49.09,"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":"SimpleQA Verified","benchmark_slug":"simpleqa-verified","score":33.63,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/simpleqa-verified"},{"benchmark":"Chess Puzzles","benchmark_slug":"chess-puzzles","score":29.5,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/chess-puzzles"},{"benchmark":"Mystery Game Puzzles","benchmark_slug":"mystery-game-puzzles","score":27.3,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/mystery-game-puzzles"},{"benchmark":"FrontierMath-Tier-4-v2-Private","benchmark_slug":"frontiermath-tier-4-v2-private","score":24.39,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/frontiermath-tier-4-v2-private"},{"benchmark":"Frontiercode","benchmark_slug":"frontiercode","score":18.8,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/frontiercode"}],"gecko_tests":{"gecko_score":null,"rank":null,"tests_taken":2,"tests":[{"test":"who-are-you","name":"Who Are You","grade":"E","value":66.7,"verdict":"Sometimes says it is Google or Anthropic","url":"https://benchgecko.ai/gecko-tests/who-are-you"},{"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-flash-0731","json":"https://benchgecko.ai/api/v1/models/deepseek-v4-flash-0731","price_history":"https://benchgecko.ai/api/v1/price-history/deepseek-v4-flash-0731","provider_prices":"https://benchgecko.ai/pricing/arbitrage/deepseek-v4-flash-0731"}}