Claude Fable 5 10.00 50.00 1.0M 128K compare (7) 64.9 #1 62.0 #1 Claude Opus 4.8 5.00 25.00 1.0M 128K compare (7) 61.4 #2 56.7 #4 GPT-5.5 5.00 30.00 1.1M 128K compare (6) 60.2 #3 59.1 #2 Claude Opus 4.7 5.00 25.00 1.0M 128K compare (7) 57.3 #4 52.5 #7 Gemini 3.1 Pro Preview 2.00 12.00 1.0M 66K compare (4) 57.2 #5 55.5 #5 GPT-5.4 2.50 15.00 1.1M 128K compare (6) 56.8 #6 57.2 #3 Qwen3.7 Max 1.25 3.75 1.0M 66K compare (2) 56.6 #7 50.1 #9 Gemini 3.5 Flash 1.50 9.00 1.0M 66K compare (5) 55.3 #8 45.0 #19 MiniMax M3 0.3 1.20 1.0M 512K compare (3) 54.7 #9 43.4 #24 Kimi K2.6 0.68 3.40 262K 262K compare (5) 53.9 #10 47.1 #13 MiMo V2.5 Pro 0.435 0.87 1.1M 131K compare (2) 53.8 #11 45.5 #18 GPT-5.3 Codex 1.75 14.00 400K 128K compare (4) 53.6 #12 53.1 #6 Qwen3.7 Plus 0.4 1.60 1.0M 66K compare (2) 53.3 #13 46.5 #14 Grok 4.3 1.25 2.50 1.0M N/A compare (4) 53.2 #14 41.0 #32 Qwen3.6 Max Preview 1.04 6.24 262K 66K compare (2) 51.8 #15 44.9 #20 DeepSeek V4 Pro 0.435 0.87 1.0M 384K compare (4) 51.5 #16 47.5 #12 GLM-5.1 0.98 3.08 203K 64K compare (4) 51.4 #17 43.4 #25 GPT-5.2 1.75 14.00 410K 128K compare (6) 51.3 #18 48.7 #10 Qwen3.6 Plus 0.325 1.95 1.0M 66K compare (2) 50.0 #19 42.9 #27 GLM-5 0.573 1.92 203K 131K compare (9) 49.8 #20 44.2 #22 MiniMax M2.7 0.27 1.08 205K 131K compare (4) 49.6 #21 41.9 #29 MiMo V2 Pro 1.00 3.00 1.0M 128K compare (1) 49.2 #22 41.4 #30 GPT-5.2 Codex 1.75 14.00 400K 128K compare (4) 49.0 #23 43.0 #26 GPT-5.4 Mini 0.75 4.50 1.1M 128K compare (5) 48.9 #24 51.5 #8 Grok 4.20 1.25 2.50 2.0M N/A compare (4) 48.5 #25 40.5 #34 Gemini 3 Pro 2.00 12.00 N/A N/A compare (3) 48.4 #26 46.5 #15 Nemotron 3 Ultra 550B A55B 0.5 2.40 1.0M 66K compare (3) 47.7 #27 37.6 #41 GPT-5.1 1.25 10.00 410K 128K compare (6) 47.7 #28 44.7 #21 Kimi K2.5 0.35 1.89 262K 98K compare (12) 46.8 #29 39.6 #35 GLM-5 Turbo 1.20 4.00 262K 131K compare (2) 46.8 #30 36.8 #44 DeepSeek V4 Flash 0.0983 0.197 1.0M 384K compare (4) 46.5 #32 38.7 #37 Claude Opus 4.6 5.00 25.00 1.0M 128K compare (7) 46.5 #31 47.6 #11 Qwen3.6 27B 0.289 2.40 262K 131K compare (2) 45.8 #33 36.5 #46 Qwen3.5 397B A17B 0.39 2.34 262K 66K compare (4) 45.0 #34 41.3 #31 GPT-5 Codex 0.125 10.00 400K 128K compare (4) 44.6 #36 38.9 #36 GPT-5 1.25 10.00 410K 128K compare (9) 44.6 #35 36.0 #50 Claude Sonnet 4.6 3.00 15.00 1.0M 128K compare (7) 44.4 #37 46.4 #16 GPT-5.4 Nano 0.2 1.25 1.1M 128K compare (5) 44.0 #38 43.9 #23 KwaiPilot KAT 2 Pro Coder 0.3 1.20 256K 80K compare (2) 43.8 #39 45.6 #17 Qwen3.6 35B A3B 0.15 1.00 262K 262K compare (1) 43.5 #40 35.2 #53 GPT-5.1 Codex 1.25 10.00 400K 128K compare (4) 43.1 #42 36.6 #45 Claude Opus 4.5 5.00 25.00 410K 64K compare (9) 43.1 #41 42.9 #28 GLM-5V Turbo 1.20 4.00 200K 128K compare (1) 42.9 #43 36.2 #49 Step 3.7 Flash 0.2 1.15 256K N/A compare (2) 42.6 #44 37.1 #43 Qwen3.5 27B 0.195 1.56 262K 66K compare (2) 42.1 #45 34.9 #54 GLM-4.7 0.4 1.75 205K 131K compare (13) 42.1 #46 36.3 #48 MiniMax M2.5 0.15 0.9 1.0M 197K compare (7) 41.9 #47 37.4 #42 Qwen3.5 122B A10B 0.26 2.08 262K 66K compare (3) 41.6 #48 34.7 #56 Grok 4 1.25 2.50 256K N/A compare (6) 41.5 #49 40.5 #33 GPT-5 Mini 0.25 2.00 1.0M 128K compare (8) 41.2 #50 35.3 #52 Kimi K2 Thinking 0.574 1.20 262K 33K compare (14) 40.9 #51 34.8 #55 o3 Pro 20.00 80.00 200K 100K compare (4) 40.7 #52 N/A Qwen3 Max Thinking 0.78 3.90 262K 66K compare (2) 39.8 #53 30.5 #70 MiniMax M2.1 0.29 0.95 1.0M 197K compare (8) 39.4 #54 32.8 #62 Mistral Medium 3.5 1.50 7.50 262K N/A compare (4) 39.2 #55 35.4 #51 Grok 4.1 Reasoning 0.2 0.5 2.0M 30K compare (4) 38.6 #57 30.9 #67 GPT-5.1 Codex Mini 0.25 2.00 400K 128K compare (4) 38.6 #56 36.4 #47 Ring 2.6 1T 0.075 0.625 262K 66K compare (1) 38.5 #58 33.3 #60 o3 2.00 8.00 200K 100K compare (5) 38.4 #59 38.4 #38 Step 3.5 Flash 0.09 0.3 262K 16K compare (2) 37.8 #60 31.6 #65 Qwen3.5 35B A3B 0.14 1.00 262K 66K compare (2) 37.1 #61 30.3 #71 Claude Sonnet 4.5 3.00 15.00 1.0M 64K compare (10) 37.1 #62 33.5 #59 MiniMax M2 0.255 1.00 205K 197K compare (9) 36.1 #63 29.2 #75 Nemotron Super 3 120B A12B 0.09 0.45 1.0M 262K compare (2) 36.0 #66 31.2 #66 KwaiPilot KAT 1 Pro Coder 0.03 1.20 256K 32K compare (1) 36.0 #65 18.3 #114 Claude Opus 4.1 15.00 75.00 200K 32K compare (7) 36.0 #64 N/A Grok 4 Reasoning 0.2 0.5 2.0M 256K compare (2) 35.1 #67 27.4 #78 Gemini 3 Flash 0.5 3.00 1.0M 65K compare (3) 35.0 #68 37.8 #40 InclusionAI Ling 2.6 1T 0.075 0.625 262K 33K compare (2) 33.6 #69 33.1 #61 Gemini 3.1 Flash Lite Preview 0.25 1.50 1.0M 66K compare (4) 33.5 #70 30.1 #73 GPT OSS 120B 0.039 0.18 131K 131K compare (21) 33.3 #71 28.6 #76 o4 Mini 1.00 4.00 200K 100K compare (5) 33.1 #72 25.6 #86 Claude Sonnet 4 3.00 15.00 1.0M 64K compare (10) 33.0 #74 30.6 #68 Claude Opus 4 5.00 25.00 410K 32K compare (9) 33.0 #73 N/A Mercury 2 0.25 0.75 128K 50K compare (3) 32.8 #75 30.6 #69 Qwen3.5 9B 0.1 0.15 262K 82K compare (2) 32.4 #76 25.3 #88 DeepSeek V3.2 0.229 0.343 164K 66K compare (12) 32.1 #77 34.6 #57 Arcee Trinity Large Thinking 0.22 0.85 262K 80K compare (2) 31.9 #78 27.2 #79 Qwen3 Max 0.359 1.43 262K 66K compare (4) 31.4 #79 26.4 #81 Claude Haiku 4.5 1.00 5.00 200K 64K compare (9) 31.0 #80 29.6 #74 Claude Sonnet 3.7 3.00 15.00 200K 128K compare (10) 30.8 #81 26.7 #80 o1 15.00 60.00 200K 100K compare (5) 30.7 #82 20.5 #103 MiMo V2 Flash 0.1 0.3 262K 66K compare (3) 30.3 #83 25.8 #85 GLM-4.6 0.43 1.74 205K 131K compare (10) 30.2 #84 30.2 #72 GLM-4.7 Flash 0.06 0.4 203K 131K compare (4) 30.1 #85 25.9 #84 Gemini 2.5 Pro 1.25 10.00 1.0M 66K compare (7) 29.5 #86 32.0 #63 DeepSeek V3.2 Speciale 0.58 1.68 164K N/A compare (1) 29.4 #87 37.9 #39 Grok 4.20 Non-Reasoning 1.25 2.50 2.0M N/A compare (3) 29.0 #88 22.0 #99 Grok 1 Code Fast 0.2 1.50 256K 10K compare (2) 28.7 #89 23.7 #92 DeepSeek V3.1 Terminus 0.27 0.95 164K 66K compare (6) 28.5 #90 31.9 #64 Qwen3 Coder Next 0.11 0.8 262K 66K compare (5) 28.3 #91 22.9 #94 DeepSeek V3.1 0.27 1.00 164K 66K compare (13) 28.1 #92 28.4 #77 GPT-5 Nano 0.05 0.4 5.0M 128K compare (8) 26.8 #93 20.3 #104 GLM-4.5 0.4 1.60 131K 98K compare (8) 26.4 #94 26.3 #82 Kimi K2 0.57 2.30 262K 33K compare (4) 26.3 #95 22.1 #97 GPT-4.1 2.00 8.00 1.0M 33K compare (6) 26.3 #96 21.8 #100 InclusionAI Ling 2.6 Flash 0.01 0.03 262K 33K compare (1) 26.2 #97 23.2 #93 Qwen3 Max Preview 1.20 6.00 262K 66K compare (2) 26.1 #98 25.5 #87 Solar Pro 3 0.15 0.6 128K N/A compare (1) 25.9 #100 13.3 #141 o3 Mini 1.10 4.40 200K 100K compare (5) 25.9 #99 17.9 #116 o1 Pro 150.00 600.00 200K 100K compare (3) 25.8 #101 N/A Gemini 2.5 Flash Preview 0.3 2.50 1.0M 66K compare (2) 25.7 #102 22.1 #96 o3 Mini High 1.10 4.40 200K 100K compare (1) 25.2 #103 17.3 #118 Grok 3 1.25 2.50 131K N/A compare (4) 25.2 #104 19.8 #106 Qwen3 Coder 480B A35B Instruct 0.22 1.30 262K 66K compare (8) 24.8 #105 24.6 #89 Sonar Reasoning Pro 2.00 8.00 128K 8K compare (3) 24.6 #106 N/A GPT OSS 20B 0.029 0.14 131K 131K compare (16) 24.5 #107 18.5 #113 MiniMax M1 80k 0.1 0.1 1.0M 40K compare (3) 24.4 #108 14.5 #131 o1 Preview 15.00 60.00 128K 33K compare (2) 23.7 #109 34.0 #58 Grok 4.1 Fast 1.25 2.50 2.0M 30K compare (2) 23.6 #110 19.5 #108 GLM-4.5 Air 0.125 0.85 131K 131K compare (6) 23.2 #111 23.8 #90 Grok 4 Fast 0.2 0.5 131K 30K compare (3) 23.1 #112 19.0 #111 GPT-4.1 Mini 0.4 1.60 1.0M 33K compare (5) 22.9 #113 18.5 #112 Mistral Large 3 0.5 1.20 262K 8K compare (5) 22.8 #114 22.7 #95 DeepSeek V3 324 0.2 0.4 164K 16K compare (13) 22.3 #115 22.0 #98 INTELLECT-3 0.2 1.10 131K N/A compare (1) 22.2 #116 19.1 #110 Devstral 2 0.4 2.00 256K N/A compare (1) 22.0 #117 23.7 #91 Mistral Medium 3.1 0.4 2.00 131K N/A compare (2) 21.3 #118 18.3 #115 Qwen3 VL 235B A22B Instruct 0.2 0.88 262K 129K compare (7) 20.8 #119 16.5 #120 o1 Mini 1.10 4.40 128K 66K compare (3) 20.4 #120 N/A Qwen3 Next 80B A3B Instruct 0.09 0.9 262K 66K compare (10) 20.1 #121 15.3 #128 Qwen3 Coder 30B A3B Instruct 0.07 0.26 262K 66K compare (5) 20.0 #122 19.4 #109 GPT-4.5 75.00 150.00 N/A N/A compare (1) 20.0 #123 N/A QwQ 32B 0.15 0.2 131K 16K compare (9) 19.7 #124 N/A Devstral Small 2 0.1 0.3 256K N/A compare (1) 19.5 #125 20.7 #102 Gemini 2.5 Flash Lite Preview 0.1 0.4 1.0M 66K compare (3) 19.4 #126 14.5 #129 Nova Premier 2.50 12.50 1.0M 32K compare (3) 19.0 #127 13.8 #135 Mistral Medium 3 0.4 2.00 131K 8K compare (3) 18.8 #130 13.6 #138 Magistral Medium 2.00 5.00 128K 64K compare (2) 18.8 #129 16.0 #122 DeepSeek R1 0.28 0.4 164K 66K compare (14) 18.8 #128 15.9 #123 Devstral Medium 0.4 2.00 256K N/A compare (1) 18.7 #132 15.9 #124 Claude Haiku 3.5 0.8 4.00 200K 8K compare (7) 18.7 #131 10.7 #157 Gemini 2.0 Flash 0.1 0.4 1.0M 8K compare (5) 18.5 #133 13.6 #137 Llama 4 Maverick 0.12 0.485 1.0M 16K compare (6) 18.4 #134 15.6 #127 Nova 2 Lite 0.3 2.50 1.0M 66K compare (3) 18.0 #135 12.5 #144 Claude Opus 3 15.00 75.00 200K 4K compare (5) 18.0 #136 19.5 #107 Sonar Reasoning 1.00 5.00 128K 8K compare (2) 17.9 #137 N/A Gemini 2.5 Flash 0.15 0.6 1.0M 66K compare (9) 17.8 #138 17.8 #117 Llama 3.1 405B Instruct 0.12 0.3 131K 16K compare (11) 17.4 #139 14.5 #130 Qwen3 VL 32B Instruct 0.104 0.416 262K 33K compare (3) 17.2 #140 15.6 #126 DeepSeek R1 Distill Qwen 32B 0.15 0.15 131K 33K compare (8) 17.2 #141 N/A GLM-4.6V 0.3 0.9 131K 33K compare (4) 17.1 #142 11.1 #151 Qwen3 235B A22B Instruct 0.09 0.58 262K 33K compare (10) 17.0 #143 14.0 #134 Magistral Small 0.5 1.50 128K 64K compare (3) 16.8 #144 11.1 #150 DeepSeek V3 0.2 0.2 164K 82K compare (11) 16.5 #145 16.4 #121 Qwen3 VL 30B A3B Instruct 0.13 0.52 262K 33K compare (5) 16.0 #146 14.3 #132 Ministral 3 14B 0.2 0.2 262K N/A compare (1) 16.0 #148 10.9 #154 DeepSeek R1 Distill Llama 70B 0.2 0.375 131K 16K compare (11) 16.0 #147 11.4 #147 DeepSeek R1 Distill Qwen 14B 0.07 0.07 131K 16K compare (5) 15.8 #149 N/A Qwen2.5 72B Instruct 0.12 0.3 131K 16K compare (8) 15.6 #150 11.9 #146 Sonar 1.00 1.00 128K 8K compare (3) 15.5 #151 N/A Sonar Pro 3.00 15.00 200K 8K compare (3) 15.2 #154 N/A QwQ 32B Preview 0.287 0.861 33K 16K compare (2) 15.2 #152 N/A Devstral Small 0.1 0.3 256K 64K compare (3) 15.2 #153 12.1 #145 Mistral Small 3.2 0.06 0.18 131K N/A compare (1) 15.1 #156 13.3 #140 Mistral Large 2 1.00 3.00 128K 16K compare (1) 15.1 #155 13.8 #136 Qwen3 30B A3B 0.051 0.29 131K 20K compare (7) 15.0 #157 14.2 #133 Ministral 3 8B 0.15 0.15 262K N/A compare (1) 14.8 #158 10.0 #161 Gemini 2.0 Flash Lite 0.075 0.3 1.0M 8K compare (3) 14.7 #159 N/A Llama 3.3 70B Instruct 0.1 0.2 131K 120K compare (20) 14.5 #160 10.7 #158 GPT-4o 2.50 10.00 131K 16K compare (6) 14.5 #161 16.6 #119 Qwen3 VL 8B Instruct 0.08 0.2 256K 33K compare (5) 14.3 #162 7.3 #169 Claude Sonnet 3.5 3.00 15.00 1.0M 16K compare (7) 14.2 #163 26.0 #83 Pixtral Large (25.02) 2.00 6.00 128K 4K compare (4) 14.0 #164 N/A Grok 2 2.00 10.00 131K 4K compare (2) 13.9 #165 N/A GPT-4 Turbo 10.00 30.00 128K 4K compare (4) 13.7 #166 21.5 #101 Nova Pro 0.8 3.20 300K 10K compare (4) 13.5 #167 11.0 #152 Llama 4 Scout 0.1 0.3 10.0M 16K compare (5) 13.5 #169 6.7 #174 Command A 1.56 1.56 256K 8K compare (5) 13.5 #168 9.9 #162 Llama 3.1 Nemotron 70B Instruct 0.6 0.6 131K 16K compare (2) 13.4 #170 10.8 #155 Grok Beta 5.00 15.00 131K N/A compare (1) 13.3 #171 N/A Qwen2.5 32B Instruct 0.06 0.2 131K 8K compare (3) 13.2 #172 N/A Nemotron Nano 3 30B A3B 0.05 0.2 262K 228K compare (2) 13.2 #174 15.8 #125 Nemotron Nano 2 9B 0.04 0.16 131K 16K compare (5) 13.2 #173 7.5 #167 GPT-4.1 Nano 0.1 0.4 1.0M 33K compare (5) 13.0 #175 11.2 #149 Qwen2.5 Coder 32B Instruct 0.05 0.1 131K 33K compare (9) 12.9 #176 N/A GPT-4 30.00 60.00 33K 8K compare (3) 12.8 #177 13.1 #142 Nova Lite 0.06 0.24 300K 10K compare (4) 12.7 #178 5.1 #177 GLM-4.5V 0.6 1.20 131K 32K compare (6) 12.7 #180 10.8 #156 Gemini 2.5 Flash Lite 0.075 0.3 1.0M 66K compare (6) 12.7 #179 7.4 #168 GPT-4o mini 0.15 0.6 131K 16K compare (6) 12.6 #181 N/A Qwen3 4B Instruct 0.01 0.03 262K 33K compare (2) 12.5 #183 9.0 #163 Qwen3 30B A3B Instruct 0.0481 0.193 262K 33K compare (3) 12.5 #182 13.3 #139 Llama 3.1 70B Instruct 0.12 0.3 131K 16K compare (13) 12.5 #185 10.9 #153 DeepSeek V2.5 1.20 1.20 33K N/A compare (1) 12.5 #184 N/A Granite 4.1 8B 0.05 0.1 131K N/A compare (1) 12.4 #186 7.3 #170 Claude Haiku 3 0.25 1.25 200K 4K compare (5) 12.3 #187 6.7 #173 OLMo 3 32B Think 0.15 0.5 66K 4K compare (1) 12.1 #188 10.5 #160 Mistral Saba 0.2 0.6 33K N/A compare (1) 12.1 #190 N/A DeepSeek R1 Distill Llama 8B 0.025 0.025 131K N/A compare (3) 12.1 #189 N/A Qwen Turbo 0.044 0.087 1.0M 16K compare (1) 12.0 #191 N/A Gemini 1.5 Pro 1.25 5.00 N/A N/A compare (2) 12.0 #192 19.8 #105 Llama 3.1 8B Instruct 0.02 0.03 200K 128K compare (21) 11.8 #193 4.9 #178 Qwen2 72B Instruct 0.9 0.9 33K N/A compare (1) 11.7 #194 N/A Ministral 3 3B 0.1 0.1 131K N/A compare (1) 11.2 #195 4.8 #179 Gemini 1.5 Flash 8B 0.037 0.3 N/A N/A compare (2) 11.1 #196 N/A Jamba 1.7 Large 2.00 8.00 256K 4K compare (2) 10.9 #197 7.8 #166 Granite 4 Small H 0.06 0.25 20K N/A compare (1) 10.8 #198 8.5 #165 Qwen3 Omni 30B A3B Instruct 0.25 0.97 66K 16K compare (1) 10.7 #200 7.2 #171 Jamba 1.5 Large 2.00 8.00 256K 8K compare (3) 10.7 #199 N/A Jamba 1.6 Large 2.00 8.00 256K N/A compare (1) 10.6 #201 N/A Hermes 3 Llama 3.1 70B 0.12 0.3 131K 16K compare (3) 10.6 #202 N/A LFM 2 24B A2B 0.03 0.12 128K N/A compare (1) 10.5 #204 3.6 #182 Gemini 1.5 Flash 0.075 0.3 8K N/A compare (2) 10.5 #203 N/A Phi-4 0.065 0.14 16K 16K compare (3) 10.4 #205 11.2 #148 Nova Micro 0.035 0.14 128K 10K compare (4) 10.3 #206 4.1 #180 Claude Sonnet 3 3.00 15.00 200K 4K compare (2) 10.3 #207 N/A Nemotron Nano 2 12B VL 0.1 0.1 131K 4K compare (2) 10.1 #208 5.9 #176 Qwen2.5 Coder 7B Instruct 0.01 0.03 131K 8K compare (4) 10.0 #209 N/A Mistral Large 0.5 1.50 262K 16K compare (8) 9.9 #210 N/A Mixtral 8x22B Instruct 0.6 0.6 66K 2K compare (6) 9.8 #211 N/A Llama 3.2 3B Instruct 0.015 0.02 131K 80K compare (10) 9.7 #213 N/A Llama 2 7B Chat 0.05 0.15 4K 4K compare (4) 9.7 #212 N/A Reka Flash 3 0.1 0.2 66K N/A compare (1) 9.5 #214 8.9 #164 DeepSeek R1 Distill Qwen 1.5B 0.09 0.09 131K N/A compare (3) 9.1 #216 N/A Claude 2 8.00 65.36 100K 8K compare (1) 9.1 #215 12.9 #143 Mistral Small 0.1 0.3 262K 8K compare (7) 9.0 #218 N/A Mistral Medium 0.4 2.00 131K 64K compare (4) 9.0 #217 N/A GPT-3.5 Turbo 0.5 1.50 16K 4K compare (4) 9.0 #219 10.7 #159 Llama 3 70B Instruct 0.12 0.3 131K 8K compare (9) 8.9 #220 6.8 #172 LFM 40B 0.1 0.2 131K N/A compare (1) 8.8 #222 N/A Gemma 3 12B 0.15 0.5 128K 32K compare (1) 8.8 #221 6.3 #175 Gemini 1.0 Pro 0.5 1.50 N/A N/A compare (2) 8.5 #223 N/A Phi-4 Mini N/A N/A N/A N/A compare (1) 8.4 #226 3.6 #183 Llama 2 70B Chat 0.5 0.9 4K 4K compare (6) 8.4 #225 N/A Llama 2 13B Chat 0.1 0.2 4K 4K compare (4) 8.4 #224 N/A Command R+ 1.56 1.56 128K 4K compare (6) 8.3 #227 N/A Jamba 1.7 Mini 0.2 0.4 256K N/A compare (1) 8.1 #228 3.1 #185 Jamba 1.5 Mini 0.2 0.4 256K 8K compare (3) 8.0 #229 N/A Jamba 1.6 Mini 0.2 0.4 256K N/A compare (1) 7.9 #230 N/A Mixtral 8x7B Instruct 0.07 0.15 33K 16K compare (9) 7.7 #231 N/A Mistral 7B Instruct 0.01 0.1 127K 16K compare (9) 7.4 #233 N/A Command R 0.15 0.15 128K 4K compare (5) 7.4 #232 N/A Granite 3.3 8B Instruct 0.03 0.2 8K 8K compare (2) 7.0 #234 3.4 #184 Llama 3 8B Instruct 0.03 0.04 32K 8K compare (9) 6.4 #235 4.0 #181 Llama 3.2 1B Instruct 0.027 0.08 131K 60K compare (6) 6.3 #237 0.6 #187 Gemma 3 4B 0.03 0.08 128K 8K compare (1) 6.3 #236 2.9 #186 55 Longco N/A N/A N/A N/A compare (1) N/A N/A 55 Shortco N/A N/A N/A N/A compare (1) N/A N/A Ada 0.1 N/A 8K N/A compare (1) N/A N/A Aion 1 4.00 8.00 131K 33K compare (1) N/A N/A Aion 1 Mini 0.7 1.40 131K 33K compare (1) N/A N/A Aion 2 0.8 1.60 131K 33K compare (1) N/A N/A Aion Llama 3.1 RP 8B 0.8 1.60 33K N/A compare (1) N/A N/A Allam 1 13B Instruct 1.80 1.80 8K 8K compare (1) N/A N/A Apply 3 0.85 1.25 256K 128K compare (1) N/A N/A Arcee Coder Large 0.5 0.8 33K N/A compare (1) N/A N/A Arcee Trinity Large Preview 0.25 1.00 131K N/A compare (1) N/A N/A Arcee Trinity Mini 0.045 0.15 131K N/A compare (2) N/A N/A Arcee Virtuoso Large 0.75 1.20 131K 64K compare (1) N/A N/A Arctic 1.5 Embed M 0.06 0.06 N/A N/A compare (1) N/A N/A Arctic 2 Embed L 0.1 0.1 8K N/A compare (1) N/A N/A Arctic Embed 2 M 0.07 N/A 8K N/A compare (1) N/A N/A Arctic Embed M 0.06 0.06 N/A N/A compare (1) N/A N/A Arctic Extract 11.10 11.10 N/A N/A compare (1) N/A N/A Arctic Tilt Entity 19.00 19.00 N/A N/A compare (1) N/A N/A Arctic Tilt Table 56.80 56.80 N/A N/A compare (1) N/A N/A AssemblyAI N/A N/A N/A N/A compare (1) N/A N/A AssemblyAI Best N/A N/A N/A N/A compare (1) N/A N/A Aura 1 N/A N/A N/A N/A compare (1) N/A N/A Aura 2 EN N/A N/A N/A N/A compare (1) N/A N/A Aura 2 ES N/A N/A N/A N/A compare (1) N/A N/A AutoGLM Phone 9B Multilingual 0.035 0.138 66K N/A compare (2) N/A N/A Aya Expanse 32B 0.5 1.50 128K 4K compare (1) N/A N/A Aya Expanse 8B 0.5 1.50 8K 4K compare (1) N/A N/A Babbage 2 0.4 0.4 16K 16K compare (1) N/A N/A Babbage 2 Finetuned 0.4 0.4 N/A N/A compare (1) N/A N/A BaiChuan M2 32B 0.07 0.07 131K N/A compare (1) N/A N/A Base ConversationalAI N/A N/A N/A N/A compare (1) N/A N/A Base Finance N/A N/A N/A N/A compare (1) N/A N/A Base General N/A N/A N/A N/A compare (1) N/A N/A Base Meeting N/A N/A N/A N/A compare (1) N/A N/A Base Phonecall N/A N/A N/A N/A compare (1) N/A N/A Base Video N/A N/A N/A N/A compare (1) N/A N/A Base Voicemail N/A N/A N/A N/A compare (1) N/A N/A BGE Base EN V1.5 0.008 N/A 154K N/A compare (2) N/A N/A BGE EN ICL 0.01 N/A 33K N/A compare (1) N/A N/A BGE Large EN 0.1 N/A 512 N/A compare (1) N/A N/A BGE Large EN V1.5 0.204 N/A 512 N/A compare (1) N/A N/A BGE Multilingual Gemma2 0.01 N/A 8K N/A compare (1) N/A N/A BGE Reranker Base 0.003 N/A N/A N/A compare (1) N/A N/A BGE Reranker M3 2 0.01 0.01 8K 8K compare (1) N/A N/A BGE Small EN V1.5 0.02 N/A 512 N/A compare (1) N/A N/A BGE-M3 0.01 0.01 60K N/A compare (2) N/A N/A Bison 1 Chat 0.125 0.125 8K 4K compare (1) N/A N/A Bison Chat 0.125 0.125 8K 4K compare (1) N/A N/A BRIA 3.2 N/A N/A N/A N/A compare (1) N/A N/A Chat Latest 5.00 30.00 400K 128K compare (1) N/A N/A Chirp N/A N/A N/A N/A compare (1) N/A N/A Chronos Hermes 2 13B 0.2 0.2 4K 4K compare (1) N/A N/A Claude 1 8.00 24.00 100K 8K compare (1) N/A N/A Claude Fable 10.00 50.00 1.0M 128K compare (1) N/A N/A Claude Haiku 1.00 5.00 200K 64K compare (1) N/A N/A Claude Instant 1 0.8 2.40 100K 8K compare (1) N/A N/A Claude Mythos 5 10.00 50.00 1.0M 128K compare (1) N/A N/A Claude Opus 4.6 N/A 150.00 N/A N/A compare (1) N/A N/A Claude Opus 4.7 Fast 30.00 150.00 1.0M 128K compare (1) N/A N/A Claude Opus 4.8 Fast 10.00 50.00 1.0M 128K compare (1) N/A N/A Claude Opus Latest 5.00 25.00 1.0M 128K compare (1) N/A N/A Claude Sonnet 3.00 15.00 1.0M 128K compare (1) N/A N/A Claude Sonnet 3.5 V2 3.00 15.00 200K 8K compare (1) N/A N/A Claude Sonnet 4.1 3.00 15.00 200K 64K compare (1) N/A N/A Code Llama 13B 0.2 0.2 16K 16K compare (1) N/A N/A Code Llama 13B Instruct 0.2 0.2 16K 16K compare (1) N/A N/A Code Llama 13B Python 0.2 0.2 16K 16K compare (1) N/A N/A Code Llama 34B 0.9 0.9 16K 16K compare (1) N/A N/A Code Llama 34B Instruct 0.35 0.9 16K 16K compare (3) N/A N/A Code Llama 34B Python 0.9 0.9 16K 16K compare (1) N/A N/A Code Llama 70B 0.9 0.9 4K 4K compare (1) N/A N/A Code Llama 70B Instruct 0.7 0.9 16K 16K compare (3) N/A N/A Code Llama 70B Python 0.9 0.9 4K 4K compare (1) N/A N/A Code Llama 7B 0.06 0.12 16K 16K compare (2) N/A N/A Code Llama 7B Instruct 0.2 0.2 16K 16K compare (1) N/A N/A Code Llama 7B Python 0.2 0.2 16K 16K compare (1) N/A N/A CodeGemma 2B 0.1 0.1 8K 8K compare (1) N/A N/A CodeGemma 7B 0.2 0.2 8K 8K compare (1) N/A N/A CodeQwen 1.5 7B 0.2 0.2 66K N/A compare (1) N/A N/A Coder 0.3 1.50 1.0M 16K compare (1) N/A N/A Coder Plus 0.502 1.00 131K 8K compare (1) N/A N/A Coder Turbo 0.287 0.861 131K 8K compare (1) N/A N/A Codestral 0.2 0.6 256K 8K compare (5) N/A N/A Codestral 2 0.3 0.9 128K N/A compare (1) N/A N/A Codestral Embed 0.15 N/A 8K N/A compare (2) N/A N/A Codex 5.1 N/A N/A N/A N/A compare (1) N/A N/A Codex 5.1 Max N/A N/A N/A N/A compare (1) N/A N/A Codex 5.1 Mini N/A N/A N/A N/A compare (1) N/A N/A Codex 5.2 N/A N/A N/A N/A compare (1) N/A N/A Codex 5.3 N/A N/A N/A N/A compare (1) N/A N/A Codex Mini 1.50 6.00 200K 100K compare (2) N/A N/A Cogito V1 Preview Llama 3B 0.1 0.1 131K N/A compare (1) N/A N/A Cogito V1 Preview Llama 70B 0.9 0.9 131K N/A compare (1) N/A N/A Cogito V1 Preview Llama 8B 0.2 0.2 131K N/A compare (1) N/A N/A Cogito V1 Preview Qwen 14B 0.2 0.2 131K N/A compare (1) N/A N/A Cogito V1 Preview Qwen 32B 0.9 0.9 131K N/A compare (1) N/A N/A Cogito V2 671B P1 1.20 1.20 164K N/A compare (1) N/A N/A Cogito V2.1 671B 1.25 1.25 128K N/A compare (2) N/A N/A Command 1.00 1.56 128K 4K compare (2) N/A N/A Command A Reasoning 1.56 1.56 256K 32K compare (1) N/A N/A Command A Translate 0.09 0.09 256K 8K compare (1) N/A N/A Command A Vision 1.56 1.56 256K 8K compare (1) N/A N/A Command Light 0.3 0.6 4K 4K compare (1) N/A N/A Command Light Text 0.3 0.6 4K 4K compare (1) N/A N/A Command Nightly 1.00 2.00 4K 4K compare (1) N/A N/A Command Plus 1.56 1.56 128K 4K compare (1) N/A N/A Command R7B 0.0375 0.15 128K 4K compare (2) N/A N/A Command Text 1.00 2.00 4K 4K compare (1) N/A N/A Computer Use N/A 12.00 N/A N/A compare (1) N/A N/A Computer Use Preview 3.00 12.00 8K 1K compare (2) N/A N/A Cydonia 24B V4.1 0.3 0.5 131K N/A compare (1) N/A N/A DALL-E 2 N/A N/A N/A N/A compare (2) N/A N/A DALL-E 3 N/A N/A N/A N/A compare (2) N/A N/A Davinci 2 2.00 2.00 16K 16K compare (1) N/A N/A Davinci 2 Finetuned 2.00 2.00 N/A N/A compare (1) N/A N/A DBRX Instruct 1.20 1.20 33K N/A compare (1) N/A N/A Deep Research 7.74 23.37 1.0M 33K compare (1) N/A N/A Deep Search N/A N/A N/A N/A compare (1) N/A N/A Deepgram Base N/A N/A N/A N/A compare (1) N/A N/A Deepgram Enhanced N/A N/A N/A N/A compare (1) N/A N/A Deepgram Nova N/A N/A N/A N/A compare (1) N/A N/A DeepSeek 0.58 1.68 N/A N/A compare (1) N/A N/A DeepSeek 4 Flash 0.19 0.51 N/A N/A compare (1) N/A N/A DeepSeek 4 Pro 1.74 3.48 N/A N/A compare (1) N/A N/A DeepSeek Coder 0.14 0.28 128K 4K compare (1) N/A N/A DeepSeek Coder 1.3B Base 0.1 0.1 16K 16K compare (1) N/A N/A DeepSeek Coder 2 Instruct 1.20 1.20 66K 8K compare (1) N/A N/A DeepSeek Coder 33B Instruct 0.9 0.9 16K 16K compare (1) N/A N/A DeepSeek Coder 6.7B 0.06 0.12 16K 4K compare (1) N/A N/A DeepSeek Coder 7B Base 0.2 0.2 4K 4K compare (1) N/A N/A DeepSeek Coder 7B Base v1.5 0.2 0.2 4K 4K compare (1) N/A N/A DeepSeek Coder 7B Instruct v1.5 0.2 0.2 4K 4K compare (1) N/A N/A DeepSeek Coder V2 Lite Base 0.5 0.5 164K 8K compare (1) N/A N/A DeepSeek Coder V2 Lite Instruct 0.5 0.5 164K 8K compare (1) N/A N/A DeepSeek Llama3.3 70B 0.2 0.6 131K N/A compare (1) N/A N/A DeepSeek Prover V2 1.20 1.20 164K N/A compare (1) N/A N/A DeepSeek Prover V2 671B 0.7 2.50 160K N/A compare (2) N/A N/A DeepSeek R1 528 0.2 0.25 164K 33K compare (12) N/A N/A DeepSeek R1 528 Turbo 1.00 3.00 33K N/A compare (1) N/A N/A DeepSeek R1 528B 0.55 2.19 131K 16K compare (2) N/A N/A DeepSeek R1 528B Qwen3 8B 0.06 0.09 128K 32K compare (1) N/A N/A DeepSeek R1 671B 0.8 0.8 131K N/A compare (1) N/A N/A DeepSeek R1 7B Qwen 0.08 0.15 131K 16K compare (1) N/A N/A DeepSeek R1 8B 0.1 0.2 66K 16K compare (1) N/A N/A DeepSeek R1 Basic 0.55 2.19 128K 20K compare (1) N/A N/A DeepSeek R1 Distill Qwen 7B 0.072 0.144 131K 16K compare (3) N/A N/A DeepSeek R1 Distill Qwen3 8B 0.2 0.2 131K N/A compare (1) N/A N/A DeepSeek R1 Turbo 0.7 2.50 64K 16K compare (3) N/A N/A DeepSeek V2 Lite Chat 0.5 0.5 164K N/A compare (1) N/A N/A DeepSeek V3 0324 0.2 0.77 131K 16K compare (1) N/A N/A DeepSeek V3 2SP 0.58 1.68 N/A N/A compare (1) N/A N/A DeepSeek V3 671B 0.287 1.15 131K 16K compare (1) N/A N/A DeepSeek V3 Turbo 0.4 1.30 64K 16K compare (2) N/A N/A DeepSeek V3.1 0.21 0.79 164K 33K compare (1) N/A N/A DeepSeek V3.2 Exp 0.27 0.41 164K 66K compare (4) N/A N/A DeepSeek V3.2 Thinking 0.62 1.85 128K 8K compare (1) N/A N/A DeepSeek-OCR 0.03 0.03 8K 8K compare (4) N/A N/A Devstral 0.4 2.00 262K 66K compare (2) N/A N/A Devstral 2 123B 0.4 2.00 256K 8K compare (1) N/A N/A DistilBERT SST-2 INT8 0.026 N/A N/A N/A compare (1) N/A N/A Dobby Llama 3.1 Mini 8B Unhinged Plus 0.2 0.2 131K N/A compare (1) N/A N/A Dobby Llama 3.3 70B Unhinged 0.9 0.9 131K N/A compare (1) N/A N/A Doc Turbo 0.087 0.144 262K 33K compare (1) N/A N/A Document AI N/A N/A N/A N/A compare (1) N/A N/A Dolphin 0.5 0.5 16K 16K compare (1) N/A N/A Dolphin 2.6 Mixtral 8x7B 0.5 0.5 33K N/A compare (1) N/A N/A Dolphin 2.9.2 Qwen2 72B 0.9 0.9 131K N/A compare (1) N/A N/A Dolphin 3 8B 0.08 0.15 128K 8K compare (1) N/A N/A E5 Base V2 0.06 0.06 N/A N/A compare (1) N/A N/A ElevenLabs 3 N/A N/A N/A N/A compare (1) N/A N/A ElevenLabs Multilingual 2 N/A N/A N/A N/A compare (2) N/A N/A Embed 2 English 0.1 N/A 4K N/A compare (1) N/A N/A Embed 2 English Light 0.1 N/A 1K N/A compare (1) N/A N/A Embed 2 Multilingual 0.1 N/A 768 N/A compare (1) N/A N/A Embed 3 English Image 0.1 N/A 512 N/A compare (1) N/A N/A Embed 3 English Light 0.1 N/A 1K N/A compare (2) N/A N/A Embed 3 English Light Image 0.1 N/A 512 N/A compare (1) N/A N/A Embed 3 Multilingual Image 0.1 N/A 512 N/A compare (1) N/A N/A Embed 3 Multilingual Light 0.1 N/A 1K N/A compare (2) N/A N/A Embed 3 Multilingual Light Image 0.1 N/A 512 N/A compare (1) N/A N/A Embed 4 0.12 0.47 128K N/A compare (5) N/A N/A Embed 4 Img 0.47 N/A N/A N/A compare (1) N/A N/A Embed 4 Txt 0.12 N/A N/A N/A compare (1) N/A N/A Embed English V3 0.1 N/A 1K N/A compare (4) N/A N/A Embed Multilingual V3 0.1 N/A 1K N/A compare (4) N/A N/A Enhanced Finance N/A N/A N/A N/A compare (1) N/A N/A Enhanced General N/A N/A N/A N/A compare (1) N/A N/A Enhanced Meeting N/A N/A N/A N/A compare (1) N/A N/A Enhanced Phonecall N/A N/A N/A N/A compare (1) N/A N/A ERNIE 4.5 21B A3B 0.07 0.28 120K 8K compare (1) N/A N/A ERNIE 4.5 21B A3B PT 0.1 0.1 4K 4K compare (1) N/A N/A ERNIE 4.5 21B A3B Thinking 0.07 0.28 131K 66K compare (1) N/A N/A ERNIE 4.5 300B A47B Paddle 0.28 1.10 123K 12K compare (1) N/A N/A ERNIE 4.5 300B A47B PT 0.1 0.1 4K 4K compare (1) N/A N/A ERNIE 4.5 VL 28B A3B 0.14 0.56 30K 8K compare (1) N/A N/A ERNIE 4.5 VL 28B A3B Thinking 0.39 0.39 131K 66K compare (1) N/A N/A ERNIE 4.5 VL 424B A47B 0.42 1.25 131K 16K compare (3) N/A N/A FireFunction V1 0.5 0.5 33K N/A compare (1) N/A N/A FireFunction V2 0.9 0.9 8K 8K compare (1) N/A N/A FireLLaVA 13B 0.2 0.2 4K 4K compare (1) N/A N/A Firesearch OCR V6 0.2 0.2 8K 8K compare (1) N/A N/A Flan-T5 3B XL 0.6 0.6 8K 8K compare (1) N/A N/A Flash 0.05 0.4 1.0M 33K compare (1) N/A N/A Flash US 0.05 0.4 1.0M 33K compare (1) N/A N/A Flux N/A N/A N/A N/A compare (1) N/A N/A FLUX 2 Dev N/A N/A N/A N/A compare (1) N/A N/A FLUX 2 Pro N/A N/A 67K N/A compare (1) N/A N/A FLUX Dev N/A N/A N/A N/A compare (2) N/A N/A FLUX Klein 2 4B N/A N/A N/A N/A compare (1) N/A N/A FLUX Klein 2 9B N/A N/A N/A N/A compare (1) N/A N/A FLUX Kontext Max N/A N/A 4K 4K compare (3) N/A N/A FLUX Kontext Pro N/A N/A 4K 4K compare (4) N/A N/A FLUX Pro N/A N/A N/A N/A compare (2) N/A N/A FLUX Realism N/A N/A N/A N/A compare (1) N/A N/A FLUX Schnell N/A N/A 512 N/A compare (2) N/A N/A FLUX.1 Dev 0.1 0.1 4K 4K compare (1) N/A N/A FLUX.1 Dev ControlNet Union 0.001 0.001 4K 4K compare (1) N/A N/A FLUX.1 Fill Pro N/A N/A N/A N/A compare (2) N/A N/A FLUX.1 Kontext Pro N/A N/A N/A N/A compare (1) N/A N/A FLUX.1 Pro Expand N/A N/A N/A N/A compare (1) N/A N/A FLUX.1 Schnell 0.1 0.1 4K 4K compare (2) N/A N/A FLUX1.1 Pro N/A N/A N/A N/A compare (5) N/A N/A FLUX1.1 Pro Ultra N/A N/A N/A N/A compare (4) N/A N/A Gemini 2.25 13.50 N/A N/A compare (2) N/A N/A Gemini 1 Embedding 0.15 N/A 2K 128 compare (3) N/A N/A Gemini 1 Live Embedding 0.15 N/A N/A N/A compare (2) N/A N/A Gemini 1.0 Pro Live 0.5 1.50 N/A N/A compare (2) N/A N/A Gemini 1.5 Flash 8B Live 0.037 0.3 N/A N/A compare (2) N/A N/A Gemini 1.5 Flash Live 0.075 0.3 N/A N/A compare (2) N/A N/A Gemini 1.5 Live Robotics ER 0.3 2.50 N/A N/A compare (2) N/A N/A Gemini 1.5 Pro Live 1.25 5.00 N/A N/A compare (2) N/A N/A Gemini 1.5 Robotics ER 0.3 2.50 N/A N/A compare (2) N/A N/A Gemini 1.6 Live RoboticsER 1.00 5.00 N/A N/A compare (2) N/A N/A Gemini 1.6 RoboticsER 1.00 5.00 N/A N/A compare (2) N/A N/A Gemini 2.0 Flash Image Generation N/A N/A 33K 33K compare (1) N/A N/A Gemini 2.0 Flash Lite Live 0.075 0.3 N/A N/A compare (2) N/A N/A Gemini 2.0 Flash Live 0.15 0.4 N/A N/A compare (2) N/A N/A Gemini 2.0 Flash Live Live 0.5 2.00 N/A N/A compare (2) N/A N/A Gemini 2.0 Flash Live TTS 0.5 N/A N/A N/A compare (2) N/A N/A Gemini 2.0 Flash TTS 0.5 N/A N/A N/A compare (2) N/A N/A Gemini 2.0 Live Embedding 0.2 N/A N/A N/A compare (2) N/A N/A Gemini 2.5 Computer Use Preview 1.25 10.00 128K 64K compare (2) N/A N/A Gemini 2.5 Flash Image 0.3 2.50 66K 66K compare (5) N/A N/A Gemini 2.5 Flash Lite Live 0.1 0.4 N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Lite Live Thinking N/A 0.4 N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Lite Thinking N/A 0.4 N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Live 0.15 2.00 N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Live Live 0.5 2.00 N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Live Native Audio N/A N/A 128K 64K compare (2) N/A N/A Gemini 2.5 Flash Live Native Audio Thinking N/A N/A N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Live Native Image Generation N/A N/A N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Live Preview Native Audio 0.3 2.00 1.0M 66K compare (2) N/A N/A Gemini 2.5 Flash Live Thinking N/A 3.50 N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Native Audio 0.3 2.50 1.0M 8K compare (2) N/A N/A Gemini 2.5 Flash Native Audio Preview 0.3 2.50 1.0M 8K compare (1) N/A N/A Gemini 2.5 Flash Native Audio Thinking N/A N/A N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Native Image Generation N/A N/A N/A N/A compare (2) N/A N/A Gemini 2.5 Flash Thinking N/A 3.50 N/A N/A compare (2) N/A N/A Gemini 2.5 Flash TTS Preview 0.3 2.50 8K 16K compare (1) N/A N/A Gemini 2.5 Pro Experimental 2.50 10.00 N/A N/A compare (2) N/A N/A Gemini 2.5 Pro Live 1.25 10.00 N/A N/A compare (2) N/A N/A Gemini 2.5 Pro Live Experimental 2.50 10.00 N/A N/A compare (2) N/A N/A Gemini 2.5 Pro Live Preview N/A N/A N/A N/A compare (2) N/A N/A Gemini 2.5 Pro Live Thinking N/A 10.00 N/A N/A compare (2) N/A N/A Gemini 2.5 Pro Live TTS 1.00 N/A N/A N/A compare (2) N/A N/A Gemini 2.5 Pro Preview 1.25 10.00 1.0M 66K compare (3) N/A N/A Gemini 2.5 Pro Preview TTS 1.25 10.00 1.0M 66K compare (2) N/A N/A Gemini 2.5 Pro Thinking N/A 10.00 N/A N/A compare (2) N/A N/A Gemini 2.5 Pro TTS 1.00 N/A N/A N/A compare (2) N/A N/A Gemini 3 Flash Live 0.5 3.00 N/A N/A compare (2) N/A N/A Gemini 3 Flash Live Live 0.75 4.50 N/A N/A compare (2) N/A N/A Gemini 3 Flash Preview 0.5 3.00 1.0M 66K compare (4) N/A N/A Gemini 3 Pro Image 2.00 12.00 66K 33K compare (3) N/A N/A Gemini 3 Pro Image Generation N/A N/A N/A N/A compare (2) N/A N/A Gemini 3 Pro Image Preview 2.00 12.00 66K 33K compare (3) N/A N/A Gemini 3 Pro Live 2.00 12.00 N/A N/A compare (2) N/A N/A Gemini 3 Pro Live Image N/A N/A N/A N/A compare (2) N/A N/A Gemini 3 Pro Live Image Generation N/A N/A N/A N/A compare (2) N/A N/A Gemini 3 Pro Preview 2.00 12.00 1.0M 66K compare (5) N/A N/A Gemini 3.1 Flash Image 0.5 3.00 131K 33K compare (3) N/A N/A Gemini 3.1 Flash Image Preview 0.25 1.50 131K 66K compare (4) N/A N/A Gemini 3.1 Flash Lite 0.25 1.50 1.0M 66K compare (5) N/A N/A Gemini 3.1 Flash Lite Live 0.25 1.50 N/A N/A compare (2) N/A N/A Gemini 3.1 Flash Lite Live Preview 0.25 1.50 N/A N/A compare (2) N/A N/A Gemini 3.1 Flash Lite Live Tuned 0.412 2.25 N/A N/A compare (2) N/A N/A Gemini 3.1 Flash Lite Tuned 0.412 2.25 N/A N/A compare (2) N/A N/A Gemini 3.1 Flash Live 0.75 4.50 N/A N/A compare (2) N/A N/A Gemini 3.1 Flash Live Image N/A N/A N/A N/A compare (2) N/A N/A Gemini 3.1 Flash Live Preview 0.75 4.50 131K 66K compare (1) N/A N/A Gemini 3.1 Flash Live TTS 1.00 N/A N/A N/A compare (2) N/A N/A Gemini 3.1 Flash TTS 1.00 N/A N/A N/A compare (2) N/A N/A Gemini 3.1 Pro 2.40 14.40 N/A N/A compare (1) N/A N/A Gemini 3.1 Pro Preview Custom Tools 2.00 12.00 1.0M 66K compare (3) N/A N/A Gemini 3.5 Flash Live 1.50 9.00 N/A N/A compare (2) N/A N/A Gemini 3.5 Live Translate N/A N/A N/A N/A compare (2) N/A N/A Gemini Deep Research Pro Preview 2.00 12.00 66K 33K compare (2) N/A N/A Gemini Embedding 2 0.2 N/A 8K 128 compare (3) N/A N/A Gemini Embedding 2 Preview 0.2 N/A 8K 128 compare (2) N/A N/A Gemini Enterprise 12.50 2.50 N/A N/A compare (2) N/A N/A Gemini Exp 0.3 2.50 2.1M 66K compare (1) N/A N/A Gemini Flash 0.3 2.50 1.0M 66K compare (2) N/A N/A Gemini Flash Lite 0.1 0.4 1.0M 66K compare (1) N/A N/A Gemini Live 2.25 13.50 N/A N/A compare (2) N/A N/A Gemini Live Enterprise 12.50 2.50 N/A N/A compare (2) N/A N/A Gemini Live Multimodal Embeddings 0.2 N/A N/A N/A compare (2) N/A N/A Gemini Multimodal Embeddings 0.2 N/A N/A N/A compare (2) N/A N/A Gemini Pro 1.25 10.00 1.0M 66K compare (2) N/A N/A Gemini Robotics-ER 1.5 Preview 0.3 2.50 1.0M 66K compare (2) N/A N/A Gemma 2 27B Instruct 0.35 0.65 8K 8K compare (2) N/A N/A Gemma 2 9B 0.2 0.2 8K 8K compare (1) N/A N/A Gemma 2 9B Instruct 0.2 0.2 8K 8K compare (2) N/A N/A Gemma 2B Instruct 0.1 0.1 8K 8K compare (1) N/A N/A Gemma 3 12B Instruct 0.05 0.1 131K 16K compare (6) N/A N/A Gemma 3 27B Instruct 0.06 0.16 131K 16K compare (6) N/A N/A Gemma 3 4B Instruct 0.04 0.08 131K 16K compare (3) N/A N/A Gemma 3N E4B IT 0.06 0.12 33K 2K compare (2) N/A N/A Gemma 4 26B A4B IT 0.06 0.3 262K 131K compare (5) N/A N/A Gemma 4 31B IT 0.12 0.36 262K 131K compare (3) N/A N/A Gemma 7B 0.2 0.2 8K 8K compare (1) N/A N/A Gemma 7B IT 0.05 0.08 8K 8K compare (3) N/A N/A Gen-3A Turbo N/A N/A N/A N/A compare (1) N/A N/A Gen-4 Aleph N/A N/A N/A N/A compare (1) N/A N/A Gen-4 Image N/A N/A N/A N/A compare (1) N/A N/A Gen-4 Image Turbo N/A N/A N/A N/A compare (1) N/A N/A Gen-4 Turbo N/A N/A N/A N/A compare (1) N/A N/A Generative N/A N/A N/A N/A compare (1) N/A N/A GLM-4 32B 0.1 0.1 128K 32K compare (2) N/A N/A GLM-4.5 Air FP8 0.2 1.10 128K N/A compare (1) N/A N/A GLM-4.5 AirX 1.10 4.50 128K 32K compare (1) N/A N/A GLM-4.5 X 2.20 8.90 128K 32K compare (1) N/A N/A GLM-4.7 Flash 0.06 0.4 131K N/A compare (1) N/A N/A GLM-4.7 FlashX 0.06 0.4 200K 128K compare (1) N/A N/A GLM-4.7 FP8 0.4 2.00 203K 16K compare (1) N/A N/A GLM-5 Code 1.20 5.00 200K 128K compare (1) N/A N/A GPT 5.00 30.00 1.1M 128K compare (2) N/A N/A GPT Audio 2.50 10.00 128K 16K compare (3) N/A N/A GPT Audio 1.5 2.50 10.00 128K 16K compare (2) N/A N/A GPT Audio Mini 0.6 2.40 128K 16K compare (3) N/A N/A GPT Chat Latest 5.00 30.00 400K 128K compare (1) N/A N/A GPT Image 5.00 10.00 N/A N/A compare (1) N/A N/A GPT Image 1 5.00 40.00 N/A N/A compare (3) N/A N/A GPT Image 1 Mini 2.00 8.00 N/A N/A compare (3) N/A N/A GPT Image 1.5 5.00 10.00 N/A N/A compare (3) N/A N/A GPT Image 2 5.00 10.00 N/A N/A compare (3) N/A N/A GPT Latest N/A N/A N/A N/A compare (1) N/A N/A GPT Mini 0.75 4.50 400K 128K compare (1) N/A N/A GPT Mini Audio N/A N/A N/A N/A compare (1) N/A N/A GPT Mini Audio Text N/A N/A N/A N/A compare (1) N/A N/A GPT Mini Realtime Audio N/A N/A N/A N/A compare (1) N/A N/A GPT Mini Realtime Image 0.8 N/A N/A N/A compare (1) N/A N/A GPT Mini Realtime Text 0.6 2.40 N/A N/A compare (1) N/A N/A GPT OSS 120B Safeguard 0.15 0.6 131K 66K compare (2) N/A N/A GPT OSS 20B Safeguard 0.07 0.2 131K 66K compare (5) N/A N/A GPT Realtime 4.00 16.00 32K 4K compare (2) N/A N/A GPT Realtime 1.5 4.00 16.00 32K 4K compare (2) N/A N/A GPT Realtime 2 4.00 24.00 128K 32K compare (1) N/A N/A GPT Realtime 2 Image N/A N/A N/A N/A compare (1) N/A N/A GPT Realtime 2 Text N/A N/A N/A N/A compare (1) N/A N/A GPT Realtime Audio N/A N/A N/A N/A compare (1) N/A N/A GPT Realtime Image 5.00 N/A N/A N/A compare (1) N/A N/A GPT Realtime Mini 0.6 2.40 128K 4K compare (2) N/A N/A GPT Realtime Text 4.00 16.00 N/A N/A compare (1) N/A N/A GPT Realtime Translate N/A 0.034 16K 2K compare (1) N/A N/A GPT Realtime Whisper N/A 0.017 16K 2K compare (1) N/A N/A GPT-1 Image 10.00 40.00 N/A N/A compare (1) N/A N/A GPT-1 Mini Image 2.00 N/A N/A N/A compare (1) N/A N/A GPT-1.5 Audio N/A N/A N/A N/A compare (1) N/A N/A GPT-1.5 Audio Text N/A N/A N/A N/A compare (1) N/A N/A GPT-1.5 Realtime Audio N/A N/A N/A N/A compare (1) N/A N/A GPT-1.5 Realtime Image N/A N/A N/A N/A compare (1) N/A N/A GPT-1.5 Realtime Text N/A N/A N/A N/A compare (1) N/A N/A GPT-3.5 Turbo 16k 3.00 4.00 16K 4K compare (3) N/A N/A GPT-3.5 Turbo 16k Finetuned 0.5 1.50 N/A N/A compare (1) N/A N/A GPT-3.5 Turbo 4k 1.50 2.00 N/A N/A compare (1) N/A N/A GPT-3.5 Turbo 4k Finetuned N/A N/A N/A N/A compare (1) N/A N/A GPT-3.5 Turbo Instruct 1.50 2.00 8K 4K compare (4) N/A N/A GPT-4 30.00 60.00 33K 4K compare (2) N/A N/A GPT-4 32k 60.00 120.00 33K 4K compare (1) N/A N/A GPT-4 Finetuned N/A N/A N/A N/A compare (1) N/A N/A GPT-4 Turbo 10.00 30.00 128K 4K compare (2) N/A N/A GPT-4 Turbo Vision 10.00 30.00 N/A N/A compare (1) N/A N/A GPT-4 Turbo Vision Preview 10.00 30.00 128K 4K compare (1) N/A N/A GPT-4.5 Preview 75.00 150.00 128K 16K compare (2) N/A N/A GPT-4o Audio N/A N/A N/A N/A compare (1) N/A N/A GPT-4o Audio 2.50 10.00 128K 16K compare (2) N/A N/A GPT-4o mini Audio 10.00 20.00 N/A N/A compare (1) N/A N/A GPT-4o mini Audio 0.15 0.6 128K 16K compare (2) N/A N/A GPT-4o mini Audio Text 0.15 0.6 N/A N/A compare (1) N/A N/A GPT-4o mini Realtime 0.6 2.40 128K 4K compare (2) N/A N/A GPT-4o mini Realtime Audio 10.00 20.00 N/A N/A compare (1) N/A N/A GPT-4o mini Realtime Text 0.6 2.40 N/A N/A compare (1) N/A N/A GPT-4o mini Search Preview 0.15 0.6 128K 16K compare (3) N/A N/A GPT-4o mini Transcribe 1.25 5.00 16K 2K compare (2) N/A N/A GPT-4o mini Transcribe Audio N/A N/A N/A N/A compare (1) N/A N/A GPT-4o mini Transcribe Text 1.25 N/A N/A N/A compare (1) N/A N/A GPT-4o mini TTS 0.6 10.00 N/A N/A compare (2) N/A N/A GPT-4o mini TTS Text 0.6 N/A N/A N/A compare (1) N/A N/A GPT-4o Realtime 5.00 20.00 128K 4K compare (2) N/A N/A GPT-4o Realtime Audio N/A N/A N/A N/A compare (1) N/A N/A GPT-4o Realtime Cached Audio N/A N/A N/A N/A compare (1) N/A N/A GPT-4o Realtime Cached Text 2.50 N/A N/A N/A compare (1) N/A N/A GPT-4o Realtime Preview Audio N/A N/A N/A N/A compare (1) N/A N/A GPT-4o Realtime Preview Text 5.00 20.00 N/A N/A compare (1) N/A N/A GPT-4o Realtime Text 5.00 20.00 N/A N/A compare (1) N/A N/A GPT-4o Search 2.50 10.00 128K 16K compare (2) N/A N/A GPT-4o Transcribe 2.50 10.00 16K 2K compare (2) N/A N/A GPT-4o Transcribe Audio N/A N/A N/A N/A compare (1) N/A N/A GPT-4o Transcribe Diarize 2.50 10.00 16K 2K compare (2) N/A N/A GPT-4o Transcribe Text 2.50 N/A N/A N/A compare (1) N/A N/A GPT-4o Transcribed Audio N/A N/A N/A N/A compare (1) N/A N/A GPT-4o Transcribed Text 2.50 N/A N/A N/A compare (1) N/A N/A GPT-5 Chat 1.25 10.00 128K 16K compare (4) N/A N/A GPT-5 Image 10.00 10.00 400K 128K compare (1) N/A N/A GPT-5 Mini Image 2.50 2.00 400K 128K compare (1) N/A N/A GPT-5 Pro 15.00 120.00 400K 272K compare (4) N/A N/A GPT-5 Search API 1.25 10.00 272K 128K compare (1) N/A N/A GPT-5.1 Chat 1.25 10.00 128K 32K compare (3) N/A N/A GPT-5.1 Codex Max 1.25 10.00 400K 128K compare (4) N/A N/A GPT-5.1 Instant 1.25 10.00 128K 16K compare (1) N/A N/A GPT-5.1 Thinking 1.25 10.00 400K 128K compare (1) N/A N/A GPT-5.2 Chat 1.75 14.00 128K 16K compare (4) N/A N/A GPT-5.2 Pro 21.00 168.00 400K 128K compare (4) N/A N/A GPT-5.3 Chat 1.75 14.00 128K 64K compare (4) N/A N/A GPT-5.4 Image 2 8.00 15.00 272K 128K compare (1) N/A N/A GPT-5.4 Long Context N/A N/A N/A N/A compare (1) N/A N/A GPT-5.4 Pro 30.00 180.00 1.1M 128K compare (4) N/A N/A GPT-5.4 Pro Long Context N/A N/A N/A N/A compare (1) N/A N/A GPT-5.5 Pro 30.00 180.00 1.1M 128K compare (4) N/A N/A Granite 2 13B Chat 0.6 0.6 8K 8K compare (1) N/A N/A Granite 2 13B Instruct 0.6 0.6 8K 8K compare (1) N/A N/A Granite 3 8B Instruct 0.2 0.2 8K 1K compare (1) N/A N/A Granite 4 Micro H 0.017 0.112 131K N/A compare (1) N/A N/A Granite 4.0 H Micro 0.017 0.112 131K N/A compare (1) N/A N/A Granite Guardian 3.2 2B 0.1 0.1 8K 8K compare (1) N/A N/A Granite Guardian 3.3 8B 0.2 0.2 8K 8K compare (1) N/A N/A Granite TTM R2 1024 96 0.38 0.38 512 512 compare (1) N/A N/A Granite TTM R2 1536 96 0.38 0.38 512 512 compare (1) N/A N/A Granite TTM R2 512 96 0.38 0.38 512 512 compare (1) N/A N/A Granite Vision 3.2 2B 0.1 0.1 8K 8K compare (1) N/A N/A Grok 1.25 5.00 N/A N/A compare (1) N/A N/A Grok 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 2 Vision 2.00 10.00 33K N/A compare (2) N/A N/A Grok 3 Beta 1.25 2.50 131K N/A compare (1) N/A N/A Grok 3 Fast 1.25 2.50 131K N/A compare (3) N/A N/A Grok 3 Mini 0.25 0.5 131K N/A compare (4) N/A N/A Grok 3 Mini Beta 1.25 2.50 131K N/A compare (1) N/A N/A Grok 3 Mini Fast 0.6 2.50 131K N/A compare (3) N/A N/A Grok 3 Mini Fast High 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 3 Mini Fast High Beta 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 3 Mini High 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 3 Mini High Beta 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 4 Fast Non-Reasoning 0.2 0.5 2.0M 256K compare (2) N/A N/A Grok 4.1 0.2 0.5 N/A N/A compare (1) N/A N/A Grok 4.1 Fast Non-Reasoning 0.2 0.5 2.0M 30K compare (4) N/A N/A Grok 4.2 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 4.20 Beta 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 4.20 Beta Non-Reasoning 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 4.20 Beta Reasoning 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 4.20 Experimental Beta 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 4.20 Experimental Beta Non-Reasoning 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 4.20 Experimental Beta Reasoning 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 4.20 Multi-Agent 1.25 2.50 2.0M N/A compare (4) N/A N/A Grok 4.20 Multi-Agent Beta 1.25 2.50 2.0M N/A compare (2) N/A N/A Grok 4.20 Multi-Agent Experimental Beta 1.25 2.50 N/A N/A compare (1) N/A N/A Grok 4.20 Reasoning 1.25 2.50 2.0M N/A compare (3) N/A N/A Grok Build 0.1 1.00 2.00 256K N/A compare (3) N/A N/A Grok Code Fast 1.00 2.00 256K N/A compare (2) N/A N/A Grok Codefast 1 0.2 1.50 N/A N/A compare (1) N/A N/A Grok Imagine Image N/A N/A N/A N/A compare (1) N/A N/A Grok Imagine Video N/A N/A N/A N/A compare (1) N/A N/A Grok Imagine Video 1.5 Preview N/A N/A N/A N/A compare (1) N/A N/A Grok Vision Beta 5.00 15.00 8K 8K compare (1) N/A N/A GTE Base 0.008 N/A 512 N/A compare (1) N/A N/A GTE Large 0.016 N/A 512 N/A compare (1) N/A N/A GTE Large EN 0.13 N/A 8K N/A compare (1) N/A N/A Hermes 2 Mixtral 8x7B DPO 0.5 0.5 33K N/A compare (1) N/A N/A Hermes 2 Pro Llama 3 8B 0.14 0.14 8K 8K compare (1) N/A N/A Hermes 2 Yi 34B 0.9 0.9 4K 4K compare (1) N/A N/A Hermes 3 405B 0.8 0.8 131K N/A compare (1) N/A N/A Hermes 3 70B 0.12 0.3 131K N/A compare (1) N/A N/A Hermes 3 8B 0.025 0.04 131K N/A compare (1) N/A N/A Hermes 3 Llama 3.1 405B 1.00 1.00 131K 16K compare (3) N/A N/A Hermes 4 405B 1.00 3.00 131K N/A compare (1) N/A N/A Hermes 4 70B 0.13 0.4 131K N/A compare (1) N/A N/A Hermes Llama2 13B 0.2 0.2 4K 4K compare (1) N/A N/A Hermes Llama2 70B 0.9 0.9 4K 4K compare (1) N/A N/A Hermes Llama2 7B 0.2 0.2 4K 4K compare (1) N/A N/A Hunyuan A13B Instruct 0.14 0.57 131K N/A compare (1) N/A N/A Hy3 Preview 0.063 0.21 262K N/A compare (1) N/A N/A Ideogram 3 N/A N/A N/A N/A compare (1) N/A N/A Image2Img N/A N/A N/A N/A compare (1) N/A N/A Image2Txt N/A N/A N/A N/A compare (1) N/A N/A Imagen N/A N/A 480 N/A compare (1) N/A N/A Imagen 3 N/A N/A N/A N/A compare (2) N/A N/A Imagen 3 Fast N/A N/A N/A N/A compare (2) N/A N/A Imagen 4 N/A N/A 480 N/A compare (3) N/A N/A Imagen 4 Fast N/A N/A 480 N/A compare (3) N/A N/A Imagen 4 Preview N/A N/A N/A N/A compare (1) N/A N/A Imagen 4 Ultra N/A N/A 480 N/A compare (4) N/A N/A IndicTrans2 EN Indic 1B 0.342 0.342 N/A N/A compare (1) N/A N/A Inflection 3 Pi 2.50 10.00 8K 1K compare (1) N/A N/A Inflection 3 Productivity 2.50 10.00 8K 1K compare (1) N/A N/A Interfaze Beta 1.50 3.50 1.0M 32K compare (1) N/A N/A InternVL3 38B 0.9 0.9 16K 16K compare (1) N/A N/A InternVL3 78B 0.9 0.9 16K 16K compare (1) N/A N/A InternVL3 8B 0.2 0.2 16K 16K compare (1) N/A N/A Jais 13B Chat 0.5 2.00 8K 8K compare (1) N/A N/A Jais 30B Chat 3.20 9.71 8K 8K compare (1) N/A N/A Jamba 1.5 0.2 0.4 256K N/A compare (2) N/A N/A Jamba Instruct 0.5 0.7 256K 8K compare (2) N/A N/A Jina Reranker 2 Base Multilingual 0.018 0.018 1K 1K compare (1) N/A N/A Jurassic-2 Light 3.00 3.00 8K 8K compare (1) N/A N/A Jurassic-2 Mid 10.00 10.00 8K 8K compare (2) N/A N/A Jurassic-2 Ultra 15.00 15.00 8K 8K compare (2) N/A N/A Kimi 0.68 3.41 262K 262K compare (2) N/A N/A Kimi K2 Instruct 0.5 2.00 262K 33K compare (9) N/A N/A Kimi K2 Preview 0.6 2.50 262K N/A compare (1) N/A N/A Kimi K2 Thinking Turbo 1.15 8.00 262K N/A compare (2) N/A N/A Kimi K2 Turbo 1.15 8.00 256K 16K compare (1) N/A N/A Kimi K2 Turbo Preview 1.15 8.00 262K N/A compare (1) N/A N/A Kimi K2.5 Thinking 0.6 3.00 N/A N/A compare (1) N/A N/A Kimi K2.6 0.95 4.00 262K N/A compare (1) N/A N/A Kimi K2.6 Thinking 0.95 4.00 N/A N/A compare (1) N/A N/A Kimi Thinking Preview 0.6 2.50 131K N/A compare (1) N/A N/A Kling 2.5 Turbo I2V N/A N/A N/A N/A compare (1) N/A N/A Kling 2.5 Turbo T2V N/A N/A N/A N/A compare (1) N/A N/A Kling 2.6 I2V N/A N/A N/A N/A compare (1) N/A N/A Kling 2.6 Motion Control N/A N/A N/A N/A compare (1) N/A N/A Kling 2.6 T2V N/A N/A N/A N/A compare (1) N/A N/A Kling 3.0 I2V N/A N/A N/A N/A compare (1) N/A N/A Kling 3.0 T2V N/A N/A N/A N/A compare (1) N/A N/A Kling v3.0 Motion Control N/A N/A N/A N/A compare (1) N/A N/A KwaiPilot KAT 32B Dev 0.9 0.9 131K N/A compare (1) N/A N/A KwaiPilot KAT 72B Dev Exp 0.9 0.9 131K N/A compare (1) N/A N/A KwaiPilot KAT Coder 0.9 0.9 262K N/A compare (1) N/A N/A KwaiPilot KAT Pro Coder 0.3 1.20 256K 128K compare (1) N/A N/A L3 70B Euryale V2.1 1.48 1.48 8K 8K compare (1) N/A N/A L3 Lunaris 1.8B Turbo 0.04 0.05 8K 8K compare (1) N/A N/A L3 Lunaris 8B 0.04 0.05 8K 8K compare (3) N/A N/A L3 Stheno 3.2 8B 0.05 0.05 8K N/A compare (2) N/A N/A L3.1 70B Euryale V2.2 0.65 0.75 131K 8K compare (2) N/A N/A L3.1 Euryale 70B 0.85 0.85 131K 16K compare (1) N/A N/A L3.1 Hanami X1 70B 3.00 3.00 16K N/A compare (1) N/A N/A L3.3 70B Euryale V2.3 0.65 0.75 131K N/A compare (1) N/A N/A L3.3 Euryale 70B 0.65 0.75 131K 16K compare (1) N/A N/A Leonardo AI Lucid Origin N/A N/A N/A N/A compare (1) N/A N/A Leonardo AI Phoenix 1.0 N/A N/A N/A N/A compare (1) N/A N/A LFM 7B 0.025 0.04 131K N/A compare (1) N/A N/A Linkup Search Deep N/A N/A N/A N/A compare (1) N/A N/A Llama 2 13B 0.1 0.2 4K 4K compare (2) N/A N/A Llama 2 70B 0.1 0.1 4K 4K compare (2) N/A N/A Llama 2 7B 0.05 0.2 4K 4K compare (2) N/A N/A Llama 3 70B 0.59 0.79 8K 8K compare (3) N/A N/A Llama 3 8B 0.05 0.08 8K 8K compare (4) N/A N/A Llama 3 8B Instruct AWQ 0.123 0.266 N/A N/A compare (1) N/A N/A Llama 3 8B Instruct Lite 0.14 0.14 N/A N/A compare (1) N/A N/A Llama 3.1 405B 1.20 1.20 128K 16K compare (3) N/A N/A Llama 3.1 405B Instruct Long 0.1 0.1 4K 4K compare (1) N/A N/A Llama 3.1 70B 0.36 0.36 128K 16K compare (3) N/A N/A Llama 3.1 70B Instruct FP8 Fast 0.293 2.25 N/A N/A compare (1) N/A N/A Llama 3.1 8B 0.03 0.05 131K 16K compare (4) N/A N/A Llama 3.1 8B Instruct AWQ 0.123 0.266 N/A N/A compare (1) N/A N/A Llama 3.1 8B Instruct FP8 0.152 0.287 32K N/A compare (1) N/A N/A Llama 3.1 8B Instruct FP8 Fast 0.045 0.384 N/A N/A compare (1) N/A N/A Llama 3.1 Nemotron 1 Ultra 253B 0.6 1.80 128K N/A compare (1) N/A N/A Llama 3.2 11B 0.16 0.16 128K 8K compare (1) N/A N/A Llama 3.2 11B Instruct 0.16 0.16 128K 4K compare (1) N/A N/A Llama 3.2 11B Vision Instruct 0.015 0.025 131K 16K compare (8) N/A N/A Llama 3.2 1B 0.05 0.05 131K 8K compare (3) N/A N/A Llama 3.2 3B 0.04 0.075 131K 8K compare (4) N/A N/A Llama 3.2 90B 0.72 0.72 128K 8K compare (1) N/A N/A Llama 3.2 90B Instruct 0.72 0.72 128K 4K compare (1) N/A N/A Llama 3.2 90B Vision Instruct 0.9 0.9 128K 16K compare (4) N/A N/A Llama 3.3 70B 0.36 0.36 128K 16K compare (6) N/A N/A Llama 3.3 70B Instruct FP8 Fast 0.293 2.25 24K N/A compare (1) N/A N/A Llama 3.3 70B Instruct Turbo 0.13 0.39 131K N/A compare (3) N/A N/A Llama 3.3 70B Maverick N/A N/A N/A N/A compare (2) N/A N/A Llama 3.3 70B Versatile 0.59 0.79 N/A N/A compare (1) N/A N/A Llama 3.3 Nemotron 1 Super 49B 0.1 0.4 131K N/A compare (1) N/A N/A Llama 3.3 Nemotron 1.5 Super 49B 0.1 0.4 131K 16K compare (2) N/A N/A Llama 4 17B 128E Instruct 0.72 0.72 1.0M 8K compare (1) N/A N/A Llama 4 17B 16E Instruct 0.72 0.72 10.5M 8K compare (1) N/A N/A Llama 4 17B Maverick 0.25 1.00 N/A N/A compare (1) N/A N/A Llama 4 17B Maverick Instruct 0.05 0.1 1.0M 16K compare (9) N/A N/A Llama 4 17B Scout Instruct 0.05 0.1 10.0M 16K compare (12) N/A N/A Llama 4 Maverick 17B 0.35 1.40 128K N/A compare (1) N/A N/A Llama 4 Maverick 17B Instruct 0.24 0.97 N/A N/A compare (1) N/A N/A Llama 4 Maverick 17B Instruct 0.24 0.97 128K 4K compare (1) N/A N/A Llama 4 Maverick Instruct 0.22 0.88 131K N/A compare (1) N/A N/A Llama 4 Scout 17B Instruct 0.17 0.66 10.0M 4K compare (1) N/A N/A Llama 4 Scout 17B Instruct 0.17 0.66 128K 4K compare (1) N/A N/A Llama 4 Scout Instruct 0.15 0.6 131K N/A compare (1) N/A N/A Llama Guard 7B 0.2 0.2 4K 4K compare (1) N/A N/A Llama3.1 Nemotron 70B Instruct 0.12 0.3 131K N/A compare (1) N/A N/A LlamaGuard 2 8B 0.2 0.2 8K 8K compare (1) N/A N/A LlamaGuard 3 11B Vision 0.35 0.35 128K N/A compare (1) N/A N/A LlamaGuard 3 1B 0.1 0.1 131K N/A compare (1) N/A N/A LlamaGuard 3 8B 0.02 0.03 131K 16K compare (6) N/A N/A LlamaGuard 4 12B 0.18 0.18 164K 16K compare (4) N/A N/A LLaVA Yi 34B 0.9 0.9 4K 4K compare (1) N/A N/A Long 0.072 0.287 10.0M 33K compare (1) N/A N/A Long Form N/A N/A N/A N/A compare (1) N/A N/A Lyria 3 Clip Preview N/A N/A 1.0M 66K compare (1) N/A N/A M2M100 1.2B 0.342 0.342 N/A N/A compare (1) N/A N/A Magistral 1.2 Medium 2.00 5.00 40K N/A compare (1) N/A N/A Magistral 1.2 Small 0.5 1.50 40K N/A compare (1) N/A N/A Magnum V4 72B 3.00 5.00 33K 2K compare (1) N/A N/A MAI DS R1 1.35 5.40 128K 8K compare (1) N/A N/A Mamba Codestral 7B 0.25 0.25 256K N/A compare (1) N/A N/A Mamba Codestral 7B 0.19 0.19 256K N/A compare (1) N/A N/A Marengo Embed 2.7 0.07 N/A 77 N/A compare (1) N/A N/A Math Plus 0.574 1.72 4K 3K compare (1) N/A N/A Math Turbo 0.287 0.861 4K 3K compare (1) N/A N/A MedLM Large N/A N/A 8K 1K compare (1) N/A N/A MedLM Medium N/A N/A 33K 8K compare (1) N/A N/A MeloTTS N/A N/A N/A N/A compare (1) N/A N/A Mercury 2 Edit 0.25 0.75 32K 8K compare (1) N/A N/A Mercury Coder Small Beta 0.25 1.00 32K 16K compare (1) N/A N/A MiMo V2.5 0.14 0.28 1.1M 131K compare (2) N/A N/A MiniMax M1 0.4 2.20 1.0M 40K compare (1) N/A N/A MiniMax M2 Her 0.3 1.20 66K 2K compare (1) N/A N/A MiniMax M2 MaaS 0.3 1.20 197K N/A compare (2) N/A N/A MiniMax M2.1 Lightning 0.3 2.40 1.0M 131K compare (2) N/A N/A MiniMax M2.5 Highspeed 0.6 2.40 205K 131K compare (1) N/A N/A MiniMax M2.5 Lightning 0.3 2.40 1.0M 8K compare (1) N/A N/A MiniMax M2.7 Highspeed 0.6 2.40 205K 131K compare (1) N/A N/A MiniMax Speech 2 HD N/A N/A N/A N/A compare (1) N/A N/A MiniMax Speech 2 Turbo N/A N/A N/A N/A compare (1) N/A N/A MiniMax Speech HD 2.6 N/A N/A N/A N/A compare (1) N/A N/A MiniMax Speech Turbo 2.6 N/A N/A N/A N/A compare (1) N/A N/A MiniMax-01 0.2 1.10 1.0M N/A compare (1) N/A N/A Ministral 14B 0.2 0.2 262K N/A compare (2) N/A N/A Ministral 3 14B Instruct 0.2 0.2 256K 8K compare (2) N/A N/A Ministral 3 3B Instruct 0.1 0.1 256K 8K compare (2) N/A N/A Ministral 3 8B Instruct 0.15 0.15 256K 8K compare (2) N/A N/A Ministral 3B 0.04 0.04 131K 4K compare (3) N/A N/A Ministral 8B 0.15 0.15 262K 4K compare (3) N/A N/A Mistral 3 7B Instruct 0.2 0.2 33K N/A compare (1) N/A N/A Mistral 7B 0.05 0.1 33K 8K compare (5) N/A N/A Mistral 7B OpenOrca 0.2 0.2 33K N/A compare (1) N/A N/A Mistral Embed 0.1 N/A 8K N/A compare (2) N/A N/A Mistral Large 3 675B Instruct 0.5 1.50 128K 8K compare (1) N/A N/A Mistral OCR 2.00 3.00 N/A N/A compare (3) N/A N/A Mistral OCR 4 N/A N/A N/A N/A compare (1) N/A N/A Mistral OCR 4 Annot N/A N/A N/A N/A compare (1) N/A N/A Mistral Saba 24B 0.79 0.79 33K N/A compare (1) N/A N/A Mistral Small 24B Instruct 0.05 0.08 33K 16K compare (3) N/A N/A Mistral Small 3.1 24B Instruct 0.1 0.3 131K N/A compare (3) N/A N/A Mistral Small 3.2 24B Instruct 0.075 0.2 128K 16K compare (3) N/A N/A Mistral Tiny 0.25 0.25 32K 8K compare (1) N/A N/A Mixtral 8x22B 1.20 1.20 66K 8K compare (2) N/A N/A Mixtral 8x7B 0.5 0.5 33K 8K compare (3) N/A N/A Model Router 0.14 N/A N/A N/A compare (1) N/A N/A Moonshot 1 128K 2.00 5.00 131K N/A compare (1) N/A N/A Moonshot 1 128K 430 2.00 5.00 131K N/A compare (1) N/A N/A Moonshot 1 128K Vision Preview 2.00 5.00 131K N/A compare (1) N/A N/A Moonshot 1 32K 1.00 3.00 33K N/A compare (1) N/A N/A Moonshot 1 32K 430 1.00 3.00 33K N/A compare (1) N/A N/A Moonshot 1 32K Vision Preview 1.00 3.00 33K N/A compare (1) N/A N/A Moonshot 1 8K 0.2 2.00 8K 8K compare (1) N/A N/A Moonshot 1 8K 430 0.2 2.00 8K 8K compare (1) N/A N/A Moonshot 1 8K Vision Preview 0.2 2.00 8K 8K compare (1) N/A N/A Moonshot 1 Auto 2.00 5.00 131K N/A compare (1) N/A N/A Morph V3 Fast 0.8 1.20 82K 38K compare (3) N/A N/A Morph V3 Large 0.9 1.90 262K 131K compare (3) N/A N/A MPT 30B Instruct 1.00 1.00 8K 8K compare (1) N/A N/A MPT 7B Instruct 0.5 N/A 8K 8K compare (1) N/A N/A MT Flash 0.16 0.49 16K 8K compare (1) N/A N/A MT Lite 0.12 0.36 16K 8K compare (1) N/A N/A MT Plus 0.25 0.75 16K 8K compare (2) N/A N/A MT Turbo 0.16 0.49 16K 8K compare (1) N/A N/A mT0 13B XXL 0.5 2.00 8K 8K compare (1) N/A N/A Multilingual E5 Large 0.1 0.1 N/A N/A compare (1) N/A N/A Multilingual E5 Large Instruct 0.025 N/A N/A N/A compare (2) N/A N/A Multilingual E5 Small 0.015 N/A N/A N/A compare (2) N/A N/A Multimodal Embedding 0.8 N/A 2K N/A compare (1) N/A N/A MythoMax L2 13B 0.06 0.06 4K 4K compare (4) N/A N/A Nano Banana Pro N/A N/A N/A N/A compare (1) N/A N/A Nemo 0.02 0.03 131K 16K compare (6) N/A N/A Nemo Base (24.07) 0.2 0.2 128K N/A compare (1) N/A N/A Nemo Instruct (24.07) 0.02 0.04 131K 512 compare (5) N/A N/A Nemotron 120B A12B 0.3 0.75 N/A N/A compare (1) N/A N/A Nemotron Nano 2 12B 0.2 0.2 131K 8K compare (2) N/A N/A Nemotron Nano 3 30B 0.06 0.24 262K 8K compare (1) N/A N/A Nemotron Super 3 120B 0.15 0.65 256K 33K compare (1) N/A N/A Nemotron Super 3 120B A12B 0.5 1.50 256K N/A compare (1) N/A N/A Neural N/A N/A N/A N/A compare (1) N/A N/A Nomic Embed Text 0.02 N/A 8K N/A compare (1) N/A N/A Nomic Embed Text 1 0.008 N/A 8K N/A compare (1) N/A N/A Nomic Embed Text 1.5 0.008 N/A 8K N/A compare (1) N/A N/A Nous Capybara 7B V1.9 0.2 0.2 33K N/A compare (1) N/A N/A Nova 2 N/A N/A N/A N/A compare (1) N/A N/A Nova 2 ATC N/A N/A N/A N/A compare (1) N/A N/A Nova 2 Automotive N/A N/A N/A N/A compare (1) N/A N/A Nova 2 ConversationalAI N/A N/A N/A N/A compare (1) N/A N/A Nova 2 Drivethru N/A N/A N/A N/A compare (1) N/A N/A Nova 2 Finance N/A N/A N/A N/A compare (1) N/A N/A Nova 2 General N/A N/A N/A N/A compare (1) N/A N/A Nova 2 Meeting N/A N/A N/A N/A compare (1) N/A N/A Nova 2 Multimodal Embeddings 0.135 N/A 8K N/A compare (1) N/A N/A Nova 2 Phonecall N/A N/A N/A N/A compare (1) N/A N/A Nova 2 Video N/A N/A N/A N/A compare (1) N/A N/A Nova 2 Voicemail N/A N/A N/A N/A compare (1) N/A N/A Nova 3 N/A N/A N/A N/A compare (2) N/A N/A Nova 3 General N/A N/A N/A N/A compare (1) N/A N/A Nova 3 Medical N/A N/A N/A N/A compare (1) N/A N/A Nova Canvas N/A N/A 3K N/A compare (1) N/A N/A Nova General N/A N/A N/A N/A compare (1) N/A N/A Nova Phonecall N/A N/A N/A N/A compare (1) N/A N/A Nova Pro 2 Preview 2.19 17.50 1.0M 64K compare (1) N/A N/A Nova Reel N/A N/A N/A N/A compare (1) N/A N/A Nova Sonic 0.06 0.24 N/A N/A compare (1) N/A N/A Nova Sonic 2 0.33 2.75 N/A N/A compare (1) N/A N/A NV Embed 4 QA 0.1 0.1 N/A N/A compare (1) N/A N/A o1 Mini Cached N/A N/A N/A N/A compare (1) N/A N/A o1 Preview Cached N/A N/A N/A N/A compare (1) N/A N/A o3 Deep Research 2.50 40.00 200K 100K compare (4) N/A N/A o4 Mini Deep Research 2.00 8.00 200K 100K compare (2) N/A N/A o4 Mini Dev RFT N/A N/A N/A N/A compare (1) N/A N/A o4 Mini High 1.10 4.40 200K 100K compare (1) N/A N/A OLMoCR 7B 0.27 1.50 16K 16K compare (1) N/A N/A OpenAI N/A N/A N/A N/A compare (1) N/A N/A OpenChat 3.5 7B 0.2 0.2 8K 8K compare (1) N/A N/A OpenThinker 7B 0.08 0.15 33K 8K compare (1) N/A N/A PaddleOCR VL 0.02 0.02 16K 16K compare (1) N/A N/A Palmyra Vision 7B 0.15 0.6 N/A N/A compare (1) N/A N/A Palmyra X4 2.50 10.00 128K 8K compare (1) N/A N/A Palmyra X5 0.6 6.00 1.0M 8K compare (2) N/A N/A Parallel AI Search Pro N/A N/A N/A N/A compare (1) N/A N/A Pegasus 1.2 N/A 7.50 N/A N/A compare (1) N/A N/A Perceptron Mk1 0.15 1.50 33K 8K compare (1) N/A N/A Phi-2 3B 0.1 0.1 2K 2K compare (1) N/A N/A Phi-3 Medium Instruct 0.17 0.68 128K 4K compare (1) N/A N/A Phi-3 Mini Instruct 0.1 0.1 131K 4K compare (2) N/A N/A Phi-3 Small Instruct 0.15 0.6 128K 4K compare (1) N/A N/A Phi-3 Vision Instruct 0.2 0.2 32K N/A compare (1) N/A N/A Phi-3.5 Mini Instruct 0.13 0.52 128K 4K compare (1) N/A N/A Phi-3.5 MoE Instruct 0.16 0.64 128K 4K compare (1) N/A N/A Phi-3.5 Vision Instruct 0.13 0.52 128K 4K compare (1) N/A N/A Phi-4 Mini Instruct 0.075 0.3 131K 128K compare (3) N/A N/A Phi-4 Mini MM N/A N/A N/A N/A compare (1) N/A N/A Phi-4 Mini Reasoning 0.08 0.32 131K 4K compare (1) N/A N/A Phi-4 Multimodal Instruct 0.08 0.32 131K 4K compare (1) N/A N/A Phi-4 Reasoning 0.125 0.5 33K 4K compare (1) N/A N/A Phi-4 Reasoning Plus N/A N/A N/A N/A compare (1) N/A N/A Phind CodeLlama 34B Python V1 0.9 0.9 16K 16K compare (1) N/A N/A Phind CodeLlama 34B V1 0.9 0.9 16K 16K compare (1) N/A N/A Phind CodeLlama 34B V2 0.9 0.9 16K 16K compare (1) N/A N/A Pixtral 12B 0.15 0.15 128K 4K compare (3) N/A N/A PLaMo Embedding 1B 0.019 N/A N/A N/A compare (1) N/A N/A PlayAI TTS N/A N/A 10K 10K compare (1) N/A N/A Plus Character 0.5 1.40 33K 4K compare (1) N/A N/A Plus Character JA 0.5 1.40 8K 512 compare (1) N/A N/A PPLX 70B Chat 0.7 2.80 4K 4K compare (1) N/A N/A PPLX 70B Online N/A 2.80 4K 4K compare (1) N/A N/A PPLX 7B Chat 0.07 0.28 8K 8K compare (1) N/A N/A PPLX 7B Online N/A 0.28 4K 4K compare (1) N/A N/A PPLX Embed 1.0 0.6B 0.004 N/A 33K N/A compare (1) N/A N/A PPLX Embed 1.4B 0.03 N/A 33K N/A compare (1) N/A N/A PPLX Embed Context 1 0.6B 0.008 N/A N/A N/A compare (1) N/A N/A PPLX Embed Context 1.4B 0.05 N/A N/A N/A compare (1) N/A N/A Prebuilt Document N/A N/A N/A N/A compare (1) N/A N/A Prebuilt Layout N/A N/A N/A N/A compare (1) N/A N/A Prebuilt Read N/A N/A N/A N/A compare (1) N/A N/A Pythia 12B 0.2 0.2 2K 2K compare (1) N/A N/A QVQ 72B Preview 1.72 5.16 33K 16K compare (1) N/A N/A QVQ Max 1.20 4.80 131K 8K compare (1) N/A N/A QVQ Plus 0.287 0.717 131K 8K compare (1) N/A N/A Qwen Max 1.60 6.40 33K 8K compare (1) N/A N/A Qwen Plus 0.115 0.287 1.0M 33K compare (2) N/A N/A Qwen Plus Thinking 0.26 0.78 1.0M 33K compare (1) N/A N/A Qwen TTS 230.00 1434.00 8K 8K compare (1) N/A N/A Qwen TTS Realtime 345.00 1721.00 8K 8K compare (1) N/A N/A Qwen VL Max 0.8 2.87 131K 8K compare (1) N/A N/A Qwen VL OCR 0.07 0.16 38K 8K compare (1) N/A N/A Qwen VL Plus 0.21 0.63 131K 8K compare (2) N/A N/A Qwen1.5 72B Chat 0.9 0.9 33K N/A compare (1) N/A N/A Qwen2 7B Instruct 0.2 0.2 33K N/A compare (1) N/A N/A Qwen2 VL 2B Instruct 0.1 0.1 33K N/A compare (1) N/A N/A Qwen2 VL 72B Instruct 0.13 0.4 131K 2K compare (3) N/A N/A Qwen2 VL 7B Instruct 0.02 0.06 131K N/A compare (2) N/A N/A Qwen2.5 0.5B Instruct 0.1 0.1 33K N/A compare (1) N/A N/A Qwen2.5 1.5B Instruct 0.1 0.1 33K N/A compare (1) N/A N/A Qwen2.5 14B 0.2 0.2 131K N/A compare (1) N/A N/A Qwen2.5 14B Instruct 0.2 0.2 131K 8K compare (2) N/A N/A Qwen2.5 14B Instruct 1M 0.805 3.22 1.0M 8K compare (1) N/A N/A Qwen2.5 32B 0.9 0.9 131K N/A compare (1) N/A N/A Qwen2.5 3B Instruct 0.044 0.13 33K 8K compare (1) N/A N/A Qwen2.5 72B 0.9 0.9 131K N/A compare (1) N/A N/A Qwen2.5 7B 0.2 0.2 131K N/A compare (1) N/A N/A Qwen2.5 7B Instruct 0.04 0.07 131K 33K compare (5) N/A N/A Qwen2.5 7B Instruct 1M 0.368 1.47 1.0M 8K compare (1) N/A N/A Qwen2.5 Coder 0.5B 0.1 0.1 33K N/A compare (1) N/A N/A Qwen2.5 Coder 0.5B Instruct 0.1 0.1 33K N/A compare (1) N/A N/A Qwen2.5 Coder 1.5B 0.1 0.1 33K N/A compare (1) N/A N/A Qwen2.5 Coder 1.5B Instruct 0.1 0.1 33K N/A compare (1) N/A N/A Qwen2.5 Coder 14B 0.2 0.2 33K N/A compare (1) N/A N/A Qwen2.5 Coder 14B Instruct 0.2 0.2 131K 8K compare (2) N/A N/A Qwen2.5 Coder 32B 0.9 0.9 33K N/A compare (1) N/A N/A Qwen2.5 Coder 3B 0.1 0.1 33K N/A compare (1) N/A N/A Qwen2.5 Coder 3B Instruct 0.01 0.03 33K N/A compare (3) N/A N/A Qwen2.5 Coder 7B 0.01 0.03 33K 8K compare (3) N/A N/A Qwen2.5 Math 72B Instruct 0.574 0.9 4K 4K compare (2) N/A N/A Qwen2.5 Math 7B Instruct 0.144 0.287 4K 3K compare (1) N/A N/A Qwen2.5 Turbo 7B Instruct 0.3 0.3 N/A N/A compare (1) N/A N/A Qwen2.5 VL 32B Instruct 0.2 0.6 131K 8K compare (3) N/A N/A Qwen2.5 VL 3B Instruct 0.2 0.2 131K 8K compare (2) N/A N/A Qwen2.5 VL 72B Instruct 0.13 0.4 131K 8K compare (7) N/A N/A Qwen2.5 VL 7B Instruct 0.2 0.2 131K 8K compare (2) N/A N/A Qwen3 0.6B 0.1 0.1 41K 8K compare (2) N/A N/A Qwen3 1.7B 0.1 0.1 131K 8K compare (2) N/A N/A Qwen3 1.7B FP8 Draft 0.1 0.1 262K N/A compare (1) N/A N/A Qwen3 1.7B FP8 Draft 131072 0.1 0.1 131K N/A compare (1) N/A N/A Qwen3 1.7B FP8 Draft 40960 0.1 0.1 41K N/A compare (1) N/A N/A Qwen3 14B 0.06 0.2 132K 41K compare (7) N/A N/A Qwen3 235B A22B 0.09 0.1 262K 131K compare (9) N/A N/A Qwen3 235B A22B FP8 Tput 0.2 0.6 40K N/A compare (1) N/A N/A Qwen3 235B A22B Instruct 2507 0.22 0.88 262K 16K compare (1) N/A N/A Qwen3 235B A22B Instruct MaaS 0.22 0.88 262K 16K compare (2) N/A N/A Qwen3 235B A22B Instruct Tput 0.2 0.6 262K N/A compare (2) N/A N/A Qwen3 235B A22B Thinking 0.1 0.1 262K 33K compare (9) N/A N/A Qwen3 30B 0.12 0.5 41K 16K compare (1) N/A N/A Qwen3 30B A3B Thinking 0.08 0.4 262K 33K compare (3) N/A N/A Qwen3 32B 0.05 0.1 131K 41K compare (15) N/A N/A Qwen3 4B 0.03 0.03 131K 20K compare (4) N/A N/A Qwen3 4B Thinking 0.01 0.03 N/A N/A compare (1) N/A N/A Qwen3 8B 0.035 0.138 131K 20K compare (6) N/A N/A Qwen3 Coder 0.22 1.80 1.0M 262K compare (2) N/A N/A Qwen3 Coder 30B A3B 0.15 0.6 262K 131K compare (2) N/A N/A Qwen3 Coder 480B A35B Instruct 0.45 1.80 262K 66K compare (1) N/A N/A Qwen3 Coder 480B A35B Instruct FP8 2.00 2.00 256K N/A compare (1) N/A N/A Qwen3 Coder 480B A35B Instruct MaaS 0.22 1.80 262K 33K compare (2) N/A N/A Qwen3 Coder 480B A35B Instruct Turbo 0.29 1.20 262K N/A compare (1) N/A N/A Qwen3 Coder 480B Instruct BF16 0.9 0.9 4K 4K compare (1) N/A N/A Qwen3 Coder Flash 0.195 0.975 1.0M 66K compare (2) N/A N/A Qwen3 Coder Plus 0.65 3.25 1.0M 66K compare (3) N/A N/A Qwen3 Embedding 0.6B 0.01 N/A 33K N/A compare (3) N/A N/A Qwen3 Embedding 4B 0.02 N/A 41K N/A compare (1) N/A N/A Qwen3 Embedding 8B 0.02 N/A 41K 4K compare (3) N/A N/A Qwen3 Next 80B A3B 0.14 1.20 128K 8K compare (2) N/A N/A Qwen3 Next 80B A3B Instruct MaaS 0.15 1.20 262K N/A compare (2) N/A N/A Qwen3 Next 80B A3B Thinking 0.0975 0.78 262K 66K compare (10) N/A N/A Qwen3 Next 80B A3B Thinking MaaS 0.15 1.20 262K N/A compare (2) N/A N/A Qwen3 Omni 30B A3B Captioner 3.81 3.06 66K 33K compare (1) N/A N/A Qwen3 Omni 30B A3B Thinking 0.25 0.97 66K 16K compare (1) N/A N/A Qwen3 Reranker 8B 0.05 0.05 41K 4K compare (1) N/A N/A Qwen3 VL 235B A22B 0.53 2.66 128K 8K compare (2) N/A N/A Qwen3 VL 235B A22B Instruct 0.4 1.60 131K 129K compare (1) N/A N/A Qwen3 VL 235B A22B Thinking 0.22 0.88 262K 33K compare (5) N/A N/A Qwen3 VL 235B A22B Thinking 0.4 4.00 131K 33K compare (1) N/A N/A Qwen3 VL 30B A3B Thinking 0.13 0.6 262K 33K compare (5) N/A N/A Qwen3 VL 32B Thinking 0.16 0.64 131K 33K compare (1) N/A N/A Qwen3 VL 8B 0.15 0.55 33K 8K compare (1) N/A N/A Qwen3 VL 8B Thinking 0.117 1.36 256K 33K compare (2) N/A N/A Qwen3 VL Flash 0.05 0.4 262K 33K compare (1) N/A N/A Qwen3 VL Plus 0.2 1.60 262K 33K compare (1) N/A N/A Qwen3.5 Flash 0.065 0.26 1.0M 66K compare (3) N/A N/A Qwen3.5 Plus 0.115 0.688 1.0M 66K compare (3) N/A N/A Qwen3.6 Flash 0.188 1.13 1.0M 66K compare (1) N/A N/A QwQ Plus 0.8 2.40 131K 8K compare (1) N/A N/A Recraft V2 N/A N/A N/A N/A compare (2) N/A N/A Recraft V3 N/A N/A N/A N/A compare (2) N/A N/A Recraft V4 N/A N/A N/A N/A compare (1) N/A N/A Recraft V4 Pro N/A N/A N/A N/A compare (1) N/A N/A Recraft V4.1 N/A N/A N/A N/A compare (1) N/A N/A Recraft V4.1 Pro N/A N/A N/A N/A compare (1) N/A N/A Recraft V4.1 Utility N/A N/A N/A N/A compare (1) N/A N/A Recraft V4.1 Utility Pro N/A N/A N/A N/A compare (1) N/A N/A Reka Edge 0.1 0.1 16K 16K compare (1) N/A N/A Relace Search 1.00 3.00 256K 128K compare (1) N/A N/A ReMM SLERP L2 13B 0.45 0.65 6K 4K compare (1) N/A N/A Rerank N/A N/A 32K 32K compare (1) N/A N/A Rerank 2 English N/A N/A 4K 4K compare (1) N/A N/A Rerank 2 Multilingual N/A N/A 4K 4K compare (1) N/A N/A Rerank 3 English N/A N/A 4K 4K compare (2) N/A N/A Rerank 3 Multilingual N/A N/A 4K 4K compare (2) N/A N/A Rerank 3.5 N/A N/A 4K 4K compare (2) N/A N/A Rerank 4 Fast 2.00 N/A 33K N/A compare (2) N/A N/A Rerank 4 Pro 2.50 N/A 33K N/A compare (2) N/A N/A ResNet-50 N/A N/A N/A N/A compare (1) N/A N/A Rnj 1 Instruct 0.15 0.15 33K N/A compare (2) N/A N/A Rocinante 12B 0.17 0.43 33K N/A compare (1) N/A N/A Rolm OCR 0.2 0.2 128K N/A compare (1) N/A N/A Scribe 1 N/A N/A N/A N/A compare (1) N/A N/A Scribe 1 Experimental N/A N/A N/A N/A compare (1) N/A N/A SEA-LION Gemma 4 27B Instruct 0.351 0.555 128K 4K compare (1) N/A N/A Seed 1.6 0.25 2.00 262K 33K compare (2) N/A N/A Seed 1.6 Flash 0.075 0.3 262K 33K compare (1) N/A N/A Seed 1.8 0.25 2.00 256K 64K compare (1) N/A N/A Seed 2 Lite 0.25 2.00 262K 131K compare (1) N/A N/A Seed 2 Mini 0.1 0.4 262K 131K compare (1) N/A N/A Seedance 1 Lite I2V N/A N/A N/A N/A compare (1) N/A N/A Seedance 1 Lite T2V N/A N/A N/A N/A compare (1) N/A N/A Seedance 1 Pro N/A N/A N/A N/A compare (1) N/A N/A Seedance 1 Pro Fast N/A N/A N/A N/A compare (1) N/A N/A Seedance 1.5 Pro N/A N/A N/A N/A compare (1) N/A N/A SeedDream 4 N/A N/A N/A N/A compare (1) N/A N/A SeedDream 4.5 N/A N/A N/A N/A compare (1) N/A N/A SeedDream 5 Lite N/A N/A N/A N/A compare (1) N/A N/A Skyfall 36B V2 0.55 0.8 33K N/A compare (1) N/A N/A Skywork R1 4 Lite 0.2 0.6 262K 66K compare (1) N/A N/A Smart Turn V2 N/A N/A N/A N/A compare (1) N/A N/A Snorkel Mistral PairRM DPO 0.2 0.2 33K N/A compare (1) N/A N/A Sonar Deep Research 2.00 8.00 128K N/A compare (2) N/A N/A Sonar Medium Chat 0.6 1.80 16K 16K compare (1) N/A N/A Sonar Medium Online N/A 1.80 12K 12K compare (1) N/A N/A Sonar Pro Search 3.00 15.00 200K 8K compare (1) N/A N/A Sonar Small Chat 0.07 0.28 16K 16K compare (1) N/A N/A Sonar Small Online N/A 0.28 12K 12K compare (1) N/A N/A Soniox STT 4 Async N/A N/A N/A 8K compare (1) N/A N/A Sora 2 N/A N/A N/A N/A compare (2) N/A N/A Sora 2 Pro N/A N/A N/A N/A compare (2) N/A N/A Sora 2 Pro High Res N/A N/A N/A N/A compare (2) N/A N/A Stable Conservative Upscale 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Creative Upscale 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Diffusion 3 N/A N/A N/A N/A compare (2) N/A N/A Stable Diffusion 3 Large N/A N/A 77 N/A compare (2) N/A N/A Stable Diffusion 3 Large Turbo N/A N/A N/A N/A compare (1) N/A N/A Stable Diffusion 3 Medium N/A N/A N/A N/A compare (1) N/A N/A Stable Diffusion 3.5 Large N/A N/A 77 N/A compare (2) N/A N/A Stable Diffusion 3.5 Large Turbo N/A N/A N/A N/A compare (1) N/A N/A Stable Diffusion 3.5 Medium N/A N/A N/A N/A compare (2) N/A N/A Stable Diffusion XL N/A N/A 77 N/A compare (1) N/A N/A Stable Fast Upscale 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Image Conservative N/A N/A N/A N/A compare (1) N/A N/A Stable Image Control Sketch 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Image Control Structure 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Image Core 1 N/A N/A 77 N/A compare (2) N/A N/A Stable Image Creative N/A N/A N/A N/A compare (1) N/A N/A Stable Image Erase N/A N/A N/A N/A compare (1) N/A N/A Stable Image Erase Object 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Image Inpaint N/A N/A N/A N/A compare (1) N/A N/A Stable Image Inpaint 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Image Outpaint N/A N/A N/A N/A compare (1) N/A N/A Stable Image Remove Background N/A N/A N/A N/A compare (1) N/A N/A Stable Image Remove Background 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Image Replace Background and Relight N/A N/A N/A N/A compare (1) N/A N/A Stable Image Search Recolor N/A N/A N/A N/A compare (1) N/A N/A Stable Image Search Recolor 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Image Search Replace N/A N/A N/A N/A compare (1) N/A N/A Stable Image Search Replace 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Image Sketch N/A N/A N/A N/A compare (1) N/A N/A Stable Image Structure N/A N/A N/A N/A compare (1) N/A N/A Stable Image Style N/A N/A N/A N/A compare (1) N/A N/A Stable Image Style Guide 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Image Style Transfer N/A N/A N/A N/A compare (1) N/A N/A Stable Image Ultra 1 N/A N/A 77 N/A compare (2) N/A N/A Stable Outpaint 1 N/A N/A 77 N/A compare (1) N/A N/A Stable Style Transfer 1 N/A N/A 77 N/A compare (1) N/A N/A StableCode 3B 0.1 0.1 4K 4K compare (1) N/A N/A Standard N/A N/A N/A N/A compare (1) N/A N/A StarCoder 16B 0.2 0.2 8K 8K compare (1) N/A N/A StarCoder 7B 0.2 0.2 8K 8K compare (1) N/A N/A StarCoder2 15B 0.2 0.2 16K 16K compare (1) N/A N/A StarCoder2 3B 0.1 0.1 16K 16K compare (1) N/A N/A StarCoder2 7B 0.2 0.2 16K 16K compare (1) N/A N/A STT N/A N/A N/A N/A compare (1) N/A N/A Switchpoint Router 0.85 3.40 131K N/A compare (1) N/A N/A Tavily Search N/A N/A N/A N/A compare (7) N/A N/A Tavily Search Advanced N/A N/A N/A N/A compare (1) N/A N/A Text Bison 0.125 0.125 8K 1K compare (1) N/A N/A Text Bison 1 0.125 0.125 8K 1K compare (1) N/A N/A Text Bison Safety Off 0.125 0.125 8K 1K compare (1) N/A N/A Text Bison Safety Recitation Off 0.125 0.125 8K 1K compare (1) N/A N/A Text Embedding 3 Large 0.13 N/A 8K N/A compare (3) N/A N/A Text Embedding 3 Small 0.02 N/A 8K N/A compare (3) N/A N/A Text Embedding 3.7 Large Exp 0.1 N/A 8K N/A compare (1) N/A N/A Text Embedding 4 0.1 N/A 2K N/A compare (1) N/A N/A Text Embedding 5 0.025 N/A 2K N/A compare (2) N/A N/A Text Embedding Ada 2 0.1 N/A 8K N/A compare (3) N/A N/A Text Embedding Preview 0.00625 N/A 3K N/A compare (1) N/A N/A Text Multilingual Embedding 2 0.025 N/A 2K N/A compare (2) N/A N/A Text Unicorn 10.00 28.00 8K 1K compare (1) N/A N/A Titan Embed Image V1 0.8 N/A 128 N/A compare (1) N/A N/A Titan Embed Text V1 0.1 N/A 8K N/A compare (1) N/A N/A Titan Embed Text V2 0.02 N/A 8K N/A compare (2) N/A N/A Titan Express Text V1 1.30 1.70 42K 8K compare (1) N/A N/A Titan Image Generator V1 N/A N/A N/A N/A compare (1) N/A N/A Titan Image Generator V2 N/A N/A N/A N/A compare (1) N/A N/A Titan Lite Text V1 0.3 0.4 42K 4K compare (1) N/A N/A Titan Premier Text V1 0.5 1.50 42K 32K compare (1) N/A N/A Tongyi Intent Detect 3 0.058 0.144 8K 1K compare (1) N/A N/A TTS N/A N/A N/A N/A compare (1) N/A N/A TTS 1 N/A N/A N/A N/A compare (2) N/A N/A TTS 1 HD N/A N/A N/A N/A compare (2) N/A N/A TTS HD N/A N/A N/A N/A compare (1) N/A N/A UAE 1 Large 0.016 N/A 512 N/A compare (1) N/A N/A UI-TARS 1.5 7B 0.1 0.2 131K 2K compare (1) N/A N/A UnslopNemo 12B 0.4 0.4 33K N/A compare (1) N/A N/A Veo 2 N/A N/A 1K N/A compare (2) N/A N/A Veo 3 N/A N/A 1K N/A compare (2) N/A N/A Veo 3 Fast N/A N/A 1K N/A compare (2) N/A N/A Veo 3.1 N/A N/A 1K N/A compare (3) N/A N/A Veo 3.1 Fast N/A N/A 1K N/A compare (3) N/A N/A Veo 3.1 Fast Preview N/A N/A 1K N/A compare (2) N/A N/A Veo 3.1 Lite Preview N/A N/A 1K N/A compare (1) N/A N/A Veo 3.1 Preview N/A N/A 1K N/A compare (2) N/A N/A Vercel V0 1 MD 3.00 15.00 128K 32K compare (1) N/A N/A Vercel V0 1.5 LG 15.00 75.00 512K N/A compare (1) N/A N/A Vercel V0 1.5 MD 3.00 15.00 128K 33K compare (1) N/A N/A Voxtral Mini 3B 0.04 0.04 128K 8K compare (1) N/A N/A Voxtral Mini Transcribe Realtime 0.006 N/A N/A N/A compare (1) N/A N/A Voxtral Mini TTS N/A 16.00 N/A N/A compare (1) N/A N/A Voxtral Small 24B 0.1 0.3 128K 8K compare (2) N/A N/A Voyage 2 0.1 N/A 4K N/A compare (1) N/A N/A Voyage 3 0.06 N/A 32K N/A compare (1) N/A N/A Voyage 3 Large 0.18 N/A 32K N/A compare (2) N/A N/A Voyage 3 Lite 0.02 N/A 32K N/A compare (1) N/A N/A Voyage 3.5 0.06 N/A 32K N/A compare (2) N/A N/A Voyage 3.5 Lite 0.02 N/A 32K N/A compare (2) N/A N/A Voyage 4 0.06 N/A 32K N/A compare (1) N/A N/A Voyage 4 Large 0.12 N/A 32K N/A compare (1) N/A N/A Voyage 4 Lite 0.02 N/A 32K N/A compare (1) N/A N/A Voyage Code 2 0.12 N/A 16K N/A compare (2) N/A N/A Voyage Code 3 0.18 N/A 32K N/A compare (2) N/A N/A Voyage Context 3 0.18 N/A 120K N/A compare (1) N/A N/A Voyage Finance 2 0.12 N/A 32K N/A compare (2) N/A N/A Voyage Large 2 0.12 N/A 16K N/A compare (1) N/A N/A Voyage Law 2 0.12 N/A 16K N/A compare (2) N/A N/A Voyage Lite 1 0.1 N/A 4K N/A compare (1) N/A N/A Voyage Lite 2 Instruct 0.1 N/A 4K N/A compare (1) N/A N/A Voyage Multilingual 2 0.14 0.14 N/A N/A compare (1) N/A N/A Voyage Multimodal 3 0.12 0.12 32K N/A compare (2) N/A N/A Voyage Rerank 2 0.05 N/A 16K 16K compare (1) N/A N/A Voyage Rerank 2 Lite 0.02 N/A 8K 8K compare (1) N/A N/A Voyage Rerank 2.5 0.05 N/A 32K N/A compare (2) N/A N/A Voyage Rerank 2.5 Lite 0.02 N/A 32K N/A compare (2) N/A N/A Voyage Rerank 3.5 N/A N/A 32K 32K compare (2) N/A N/A Wan 2.5 T2V Preview N/A N/A N/A N/A compare (1) N/A N/A Wan 2.6 I2V N/A N/A N/A N/A compare (1) N/A N/A Wan 2.6 I2V Flash N/A N/A N/A N/A compare (1) N/A N/A Wan 2.6 R2V N/A N/A N/A N/A compare (1) N/A N/A Wan 2.6 R2V Flash N/A N/A N/A N/A compare (1) N/A N/A Wan 2.6 T2V N/A N/A N/A N/A compare (1) N/A N/A Weaver 0.75 1.00 8K 2K compare (1) N/A N/A Whisper N/A N/A N/A N/A compare (4) N/A N/A Whisper 3 Large N/A N/A N/A N/A compare (1) N/A N/A Whisper 3 Large Turbo N/A N/A N/A N/A compare (3) N/A N/A Whisper Base N/A N/A N/A N/A compare (1) N/A N/A Whisper Large N/A N/A N/A N/A compare (1) N/A N/A Whisper Medium N/A N/A N/A N/A compare (1) N/A N/A Whisper Small N/A N/A N/A N/A compare (1) N/A N/A Whisper Tiny N/A N/A N/A N/A compare (1) N/A N/A WizardLM 2 8x22B 0.48 0.48 66K 8K compare (4) N/A N/A Yi 34B 0.9 0.9 4K 4K compare (1) N/A N/A Yi 34B 200K Capybara 0.9 0.9 200K N/A compare (1) N/A N/A Yi 34B Chat 0.9 0.9 4K 4K compare (1) N/A N/A Yi 6B 0.2 0.2 4K 4K compare (1) N/A N/A Yi Large 3.00 3.00 33K N/A compare (1) N/A N/A Zephyr 7B Beta 0.15 0.15 33K 16K compare (2) N/A N/A 
Anthropic
OpenAI
Google
Alibaba
MiniMax
Moonshot AI (Kimi)
Xiaomi
xAI
DeepSeek
Zhipu AI
NVIDIA
KwaiPilot
StepFun
Mistral AI
Inception
Arcee AI
Upstage
Perplexity
Prime Intellect
Amazon
Meta
Cohere
IBM
Allen AI
AI21 Labs
Nous Research
Liquid AI
Microsoft
Reka AI
Aion Labs
Relace
Snowflake
AssemblyAI
Deepgram
Baichuan
DeepCogito
Databricks
Hugging Face
ElevenLabs
Baidu
Fireworks AI
Black Forest Labs
Runway
Tencent
Ideogram
Inflection AI
InternLM
Core42
Linkup
01.AI
Twelve Labs
Morph
Nomic AI
PaddlePaddle (Baidu)
Writer
PlayAI
EleutherAI
Recraft
Essential AI
AI Singapore
ByteDance
Skywork
Stability AI
BigCode
Tavily
Vercel
Voyage