{"rankings":[{"id":"speed","title":"Fastest models","unit":"tokens/sec","detail":"Output speed · higher is better","models":[{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek V4.1 Flash 1017","provider":"DeepSeek","providerId":"deepseek","hostingProviderId":"inco","logo":"/providers/deepseek.svg","offeringId":"aa:44c47896-619e-4135-98d8-04ebb63e1b6d","hostingProvider":"Inco (FAST)","metric":"speed","value":1075.2746652607,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017/providers","asOf":"2026-11-02T21:05:33.228000+00:00","settings":"DeepSeek V4.1 Flash 1017 (max) (FAST) · Artificial Analysis: DeepSeek V4.1 Flash 1017 (max) (FAST); host Inco (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":1},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","provider":"DeepSeek","providerId":"deepseek","hostingProviderId":"baseten","logo":"/providers/deepseek.svg","offeringId":"aa:f174c93f-ffac-4fbb-ab0f-80dab56dddb7","hostingProvider":"Baseten (FAST)","metric":"speed","value":830.033723946405,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash/providers","asOf":"2026-11-02T21:05:23.617000+00:00","settings":"DeepSeek V4.1 Flash (max) (FAST) · Artificial Analysis: DeepSeek V4.1 Flash (max) (FAST); host Baseten (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":2},{"id":"minimax-m3-1-flash","name":"MiniMax M3.1 Flash","provider":"MiniMax","providerId":"minimax","hostingProviderId":"inco","logo":"/providers/minimax.ico","offeringId":"aa:3e40bad2-ec5c-4dbf-9de3-9b24984b5722","hostingProvider":"Inco","metric":"speed","value":812.59694042717,"source":"https://artificialanalysis.ai/models/minimax-m3-1-flash/providers","asOf":"2026-11-02T21:06:38.392000+00:00","settings":"MiniMax-M3.1-Flash · Artificial Analysis: MiniMax-M3.1-Flash; host Inco; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":3},{"id":"glm-5-3","name":"GLM-5.3","provider":"Z.ai","providerId":"zai","hostingProviderId":"systalyze","logo":"/providers/zai.svg","offeringId":"aa:3678e24d-dae7-4eea-b0ca-22c302678fae","hostingProvider":"Systalyze","metric":"speed","value":688.21704344481,"source":"https://artificialanalysis.ai/models/glm-5-3/providers","asOf":"2026-11-02T21:06:11.906000+00:00","settings":"GLM-5.3 (max) · Artificial Analysis: GLM-5.3 (max); host Systalyze; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":4},{"id":"kimi-k3","name":"Kimi K3","provider":"Moonshot AI","providerId":"moonshot-ai","hostingProviderId":"inco","logo":"/providers/moonshot-ai.svg","offeringId":"aa:a5ddda6c-ec98-4830-830b-ac290c6210aa","hostingProvider":"Inco (FAST)","metric":"speed","value":481.693840628291,"source":"https://artificialanalysis.ai/models/kimi-k3/providers","asOf":"2026-11-02T21:06:11.860000+00:00","settings":"Kimi K3 (max) (FAST) · Artificial Analysis: Kimi K3 (max) (FAST); host Inco (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":5}]},{"id":"latency","title":"Lowest latency","unit":"TTFT","detail":"Time to first token · lower is better","models":[{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek V4.1 Flash 1017","provider":"DeepSeek","providerId":"deepseek","hostingProviderId":"baseten","logo":"/providers/deepseek.svg","offeringId":"aa:9ab844b3-ce43-469c-ad1c-e95ae878b4b6","hostingProvider":"Baseten (FAST)","metric":"latency","value":0.181869622000022,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017/providers","asOf":"2026-11-02T21:05:33.228000+00:00","settings":"DeepSeek V4.1 Flash 1017 (max) (FAST) · Artificial Analysis: DeepSeek V4.1 Flash 1017 (max) (FAST); host Baseten (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":1},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","provider":"DeepSeek","providerId":"deepseek","hostingProviderId":"togetherai","logo":"/providers/deepseek.svg","offeringId":"aa:c3e90c10-db83-4b42-b7c9-13e2a191a0c7","hostingProvider":"Together AI","metric":"latency","value":0.311037242499993,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash/providers","asOf":"2026-11-02T21:05:23.617000+00:00","settings":"DeepSeek V4.1 Flash (max) · Artificial Analysis: DeepSeek V4.1 Flash (max); host Together AI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":2},{"id":"minimax-m3-1-flash","name":"MiniMax M3.1 Flash","provider":"MiniMax","providerId":"minimax","hostingProviderId":"togetherai","logo":"/providers/minimax.ico","offeringId":"aa:5554d2be-ca99-4853-87d6-3f90182f44ec","hostingProvider":"Together AI","metric":"latency","value":0.583990292000067,"source":"https://artificialanalysis.ai/models/minimax-m3-1-flash/providers","asOf":"2026-11-02T21:06:38.392000+00:00","settings":"MiniMax-M3.1-Flash · Artificial Analysis: MiniMax-M3.1-Flash; host Together AI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":3},{"id":"glm-5-3","name":"GLM-5.3","provider":"Z.ai","providerId":"zai","hostingProviderId":"togetherai","logo":"/providers/zai.svg","offeringId":"aa:f8c50530-0333-4ec9-860a-872ea57f98ef","hostingProvider":"Together AI","metric":"latency","value":0.596873245999973,"source":"https://artificialanalysis.ai/models/glm-5-3/providers","asOf":"2026-11-02T21:06:11.906000+00:00","settings":"GLM-5.3 (max) · Artificial Analysis: GLM-5.3 (max); host Together AI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":4},{"id":"minimax-m3","name":"MiniMax M3","provider":"MiniMax","providerId":"minimax","hostingProviderId":"minimax","logo":"/providers/minimax.ico","offeringId":"open-import-minimax-m3-minimax","hostingProvider":"MiniMax","metric":"latency","value":0.699039579499981,"source":"https://artificialanalysis.ai/models/minimax-m3","asOf":"2026-11-02T22:18:13.301725+00:00","settings":"MiniMax-M3 · Explicit first-party AA measurement; reasoning configuration retained. Cross-provider medians are excluded. Retrieval time is not measurement time.","providerPosition":1,"position":5}]},{"id":"price","title":"Most affordable","unit":"$/1M tokens","detail":"50% input + 50% output · lower is better","models":[{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek V4.1 Flash 1017","provider":"DeepSeek","providerId":"deepseek","hostingProviderId":"deepinfra","logo":"/providers/deepseek.svg","offeringId":"aa:70bb5da0-0732-4130-b626-20165376ff80","hostingProvider":"DeepInfra","metric":"price","value":0.196,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017/providers","asOf":"2026-11-02T21:05:33.228000+00:00","settings":"Input $0.098/1M · Output $0.294/1M · Artificial Analysis: DeepSeek V4.1 Flash 1017 (max); host DeepInfra; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":1},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","provider":"DeepSeek","providerId":"deepseek","hostingProviderId":"deepinfra","logo":"/providers/deepseek.svg","offeringId":"aa:077ec157-ab1f-48d9-a7cb-b3678f512a87","hostingProvider":"DeepInfra","metric":"price","value":0.28,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash/providers","asOf":"2026-11-02T21:05:23.617000+00:00","settings":"Input $0.14/1M · Output $0.42/1M · Artificial Analysis: DeepSeek V4.1 Flash (max); host DeepInfra; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":2},{"id":"glm-5-3-flash","name":"GLM-5.3-Flash","provider":"Z.ai","providerId":"zai","hostingProviderId":"zai","logo":"/providers/zai.svg","offeringId":"open-import-glm-5-3-flash-zai","hostingProvider":"Z.ai","metric":"price","value":0.325,"source":"https://artificialanalysis.ai/models/glm-5-3-flash","asOf":"2026-11-02T22:18:13.301725+00:00","settings":"Input $0.15/1M · Output $0.5/1M · Explicit first-party AA measurement; reasoning configuration retained. Cross-provider medians are excluded. Retrieval time is not measurement time.","providerPosition":1,"position":3},{"id":"minimax-m3-1-flash","name":"MiniMax M3.1 Flash","provider":"MiniMax","providerId":"minimax","hostingProviderId":"gmi","logo":"/providers/minimax.ico","offeringId":"aa:8e90a589-a404-40fc-bf52-0920031859c9","hostingProvider":"GMI","metric":"price","value":0.35624999999999996,"source":"https://artificialanalysis.ai/models/minimax-m3-1-flash/providers","asOf":"2026-11-02T21:06:38.392000+00:00","settings":"Input $0.1425/1M · Output $0.57/1M · Artificial Analysis: MiniMax-M3.1-Flash; host GMI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":4},{"id":"glm-5-3","name":"GLM-5.3","provider":"Z.ai","providerId":"zai","hostingProviderId":"multiverse-computing","logo":"/providers/zai.svg","offeringId":"aa:daefee47-17f9-45c4-b0a4-f4ba0212cfc4","hostingProvider":"Multiverse Computing","metric":"price","value":0.42000000000000004,"source":"https://artificialanalysis.ai/models/glm-5-3/providers","asOf":"2026-11-02T21:06:11.906000+00:00","settings":"Input $0.2/1M · Output $0.64/1M · Artificial Analysis: GLM-5.3 (max); host Multiverse Computing; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.","providerPosition":1,"position":5}]}]}