Bestenliste der LLM-API-Anbieter – Vergleich von über 500 Endpunkten für KI-Modelle
Leistungsvergleich von API-Anbietern über mehr als 500 Endpunkte für KI-Modelle von OpenAI, Google, DeepSeek und weiteren Anbietern anhand zentraler Metriken wie Preis, Ausgabegeschwindigkeit, Latenz, Kontextfenster und mehr.
Weitere Details, auch zu unserer Methodik, finden Sie in unseren FAQs.
Weitere Analyse | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Claude Opus 5 (max) | 1M | Proprietär | 61 | $2.34 | 54 | 75.74 | 84.93 | -- | ||
Claude Opus 5 (max) | 1M | Proprietär | 61 | $2.34 | 55 | 69.32 | 78.39 | -- | ||
Claude Opus 5 (max) | 1M | Proprietär | 61 | $3.31 | 54 | 66.17 | 75.40 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietär | 60 | $1.80 | 57 | 35.94 | 44.74 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietär | 60 | $2.52 | 55 | 31.72 | 40.81 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietär | 60 | $1.80 | 53 | 39.14 | 48.57 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietär | 60 | $3.15 | 74 | 112.28 | 119.01 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietär | 60 | $3.33 | 71 | 163.01 | 170.02 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietär | 60 | $10.17 | 62 | 121.72 | 129.82 | -- | ||
GPT-5.6 Sol (max) | 262k | Proprietär | 59 | $1.67 | 116 | 124.18 | 128.49 | -- | ||
GPT-5.6 Sol (max) | 1M | Proprietär | 59 | $1.23 | 66 | 139.09 | 146.69 | -- | ||
Claude Opus 5 (high) | 1M | Proprietär | 59 | $1.23 | 54 | 20.31 | 29.49 | -- | ||
Claude Opus 5 (high) | 1M | Proprietär | 59 | $1.67 | 55 | 20.98 | 30.06 | -- | ||
Claude Opus 5 (high) | 1M | Proprietär | 59 | $1.23 | 53 | 23.63 | 33.05 | -- | ||
GPT-5.6 Sol (xhigh) | 1M | Proprietär | 58 | $0.83 | 65 | 48.05 | 55.79 | -- | ||
Kimi K3 (max) | 1.05M | Offen | 57 | $0.86 | 37 | 2.87 | 71.01 | 54.51 | ||
Kimi K3 (max) | 1.05M | Offen | 57 | $0.91 | 176 | 1.14 | 15.38 | 11.40 | ||
Kimi K3 (max) | 1.05M | Offen | 57 | $1.27 | 133 | 1.97 | 20.69 | 14.98 | ||
Kimi K3 (max) | 1M | Offen | 57 | $1.46 | 55 | 0.94 | 46.46 | 36.42 | ||
Kimi K3 (max) | 1.05M | Offen | 57 | $1.03 | 36 | 3.84 | 73.51 | 55.74 | ||
Kimi K3 (max) | 1.05M | Offen | 57 | $0.80 | 76 | 2.22 | 35.06 | 26.28 | ||
Kimi K3 (max) | 1.05M | Offen | 57 | $0.67 | 102 | 1.63 | 26.16 | 19.62 | ||
Kimi K3 (max) | 1.05M | Offen | 57 | $3.18 | 105 | 1.64 | 25.48 | 19.07 | ||
Kimi K3 (max) | 205k | Offen | 57 | $0.81 | 186 | 1.08 | 14.55 | 10.77 | ||
Kimi K3 (max) (FAST) | 1M | Offen | 57 | $1.30 | 124 | 0.99 | 21.17 | 16.15 | ||
Claude Opus 5 (medium) | 1M | Proprietär | 56 | $0.72 | 54 | 7.49 | 16.79 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietär | 56 | $0.72 | 53 | 13.29 | 22.74 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietär | 56 | $0.95 | 53 | 4.62 | 14.02 | -- | ||
GPT-5.6 Sol (high) | 1M | Proprietär | 56 | $0.55 | 62 | 12.87 | 20.99 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietär | 55 | $0.51 | 122 | 171.60 | 175.69 | -- | ||
GPT-5.6 Terra (max) | 262k | Proprietär | 55 | $0.98 | 170 | 137.81 | 140.75 | -- | ||
Grok 4.5 (high) | 500k | Proprietär | 54 | $0.36 | 59 | 11.79 | 20.20 | -- | ||
GPT-5.6 Sol (medium) | 1M | Proprietär | 54 | $0.39 | 61 | 7.89 | 16.09 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietär | 53 | $2.22 | 83 | 213.41 | 219.42 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietär | 53 | $1.64 | 84 | 237.36 | 243.34 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietär | 53 | $1.72 | 82 | 198.39 | 204.51 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietär | 53 | $1.96 | 70 | 164.15 | 171.29 | -- | ||
GPT-5.6 Terra (xhigh) | 1M | Proprietär | 52 | $0.31 | 116 | 25.28 | 29.59 | -- | ||
GPT-5.6 Luna (max) | 1M | Proprietär | 51 | $0.05 | 178 | 135.99 | 138.80 | -- | ||
GPT-5.6 Luna (max) | 262k | Proprietär | 51 | $0.34 | 202 | 128.48 | 130.96 | -- | ||
GLM-5.2 (max) | 205k | Offen | 51 | $0.36 | 171 | 5.79 | 20.44 | 11.72 | ||
GLM-5.2 (max) | 1M | Offen | 51 | $0.42 | 245 | 1.42 | 11.61 | 8.16 | ||
GLM-5.2 (max) (NVFP4) | 1M | Offen | 51 | $0.48 | 233 | 0.90 | 11.64 | 8.59 | ||
GLM-5.2 (max) (FP8) | 1.05M | Offen | 51 | $0.42 | 43 | 2.20 | 60.62 | 46.74 | ||
GLM-5.2 (max) | 261k | Offen | 51 | $0.45 | 113 | 1.96 | 24.03 | 17.65 | ||
GLM-5.2 (max) (NVFP4) | 1M | Offen | 51 | -- | 254 | 1.24 | 11.08 | 7.87 | ||
GLM-5.2 (max) | 262k | Offen | 51 | $0.38 | 189 | 1.42 | 14.64 | 10.58 | ||
GLM-5.2 (max) (FP4) | 1.05M | Offen | 51 | $0.25 | 56 | 1.30 | 45.77 | 35.58 | ||
GLM-5.2 (max) (FP4) | 432k | Offen | 51 | $1.06 | 230 | 1.13 | 12.00 | 8.70 | ||
GLM-5.2 (max) | 1.05M | Offen | 51 | $0.44 | 247 | 1.67 | 11.78 | 8.09 | ||
GLM-5.2 (max) | 1M | Offen | 51 | -- | 357 | 1.00 | 8.00 | 5.60 | ||
GLM-5.2 (max) | 262k | Offen | 51 | $1.57 | 81 | 1.97 | 32.83 | 24.69 | ||
GLM-5.2 (max) | 1M | Offen | 51 | $0.48 | 294 | 1.10 | 9.60 | 6.80 | ||
GLM-5.2 (max) (FP8) | 1.05M | Offen | 51 | -- | -- | -- | -- | -- | ||
GLM-5.2 (max) (FP8) | 1.05M | Offen | 51 | $0.62 | 53 | 1.66 | 48.95 | 37.83 | ||
Muse Spark 1.1 (xhigh) | 1.05M | Proprietär | 51 | $0.29 | 216 | 2.90 | 14.49 | 9.27 | ||
Claude Opus 5 (low) | 1M | Proprietär | 51 | $0.43 | 52 | 2.85 | 12.41 | -- | ||
Claude Opus 5 (low) | 1M | Proprietär | 51 | $0.43 | 53 | 4.70 | 14.11 | -- | ||
Claude Opus 5 (low) | 1M | Proprietär | 51 | $0.55 | 52 | 2.71 | 12.29 | -- | ||
Gemini 3.5 Flash AI Studio | 1M | Proprietär | 50 | $0.69 | 179 | 24.97 | 27.77 | -- | ||
Gemini 3.6 Flash AI Studio | 1M | Proprietär | 50 | $0.56 | 200 | 15.67 | 18.16 | -- | ||
DeepSeek V4 Flash 0731 (max) | 1M | Offen | 50 | $0.03 | 110 | 1.33 | 24.04 | 18.17 | ||
DeepSeek V4 Flash 0731 (max) | 1M | Offen | 50 | $0.06 | 73 | 0.83 | 35.23 | 27.52 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 50 | $0.13 | 35 | 1.64 | 73.81 | 57.74 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 50 | $0.08 | 84 | 0.92 | 30.55 | 23.71 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 50 | $0.09 | 105 | 1.49 | 25.35 | 19.09 | ||
GPT-5.6 Sol (low) | 1M | Proprietär | 49 | $0.24 | 61 | 3.74 | 11.98 | -- | ||
GPT-5.6 Luna (xhigh) | 1M | Proprietär | 49 | $0.03 | 168 | 46.39 | 49.37 | -- | ||
GPT-5.6 Terra (high) | 1M | Proprietär | 49 | $0.22 | 116 | 3.33 | 7.65 | -- | ||
Kimi K3 (low) | 1.05M | Offen | 47 | $0.24 | 36 | 3.69 | 72.79 | 55.28 | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | Proprietär | 46 | $0.34 | 126 | 32.39 | 36.35 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | Proprietär | 46 | $0.43 | 138 | 29.23 | 32.86 | -- | ||
GPT-5.6 Luna (high) | 1M | Proprietär | 46 | $0.02 | 168 | 11.71 | 14.68 | -- | ||
Qwen3.7 Max | 991k | Proprietär | 46 | $1.08 | 203 | 2.31 | 16.64 | 11.87 | ||
GPT-5.6 Terra (medium) | 1M | Proprietär | 46 | $0.12 | 113 | 1.83 | 6.26 | -- | ||
Gemini 3.5 Flash (medium) | 1M | Proprietär | 45* | -- | 182 | 17.04 | 19.78 | -- | ||
MiniMax-M3 (MXFP8) | 1M | Offen | 44 | $0.18 | 68 | 1.07 | 37.72 | 29.32 | ||
MiniMax-M3 | 262k | Offen | 44 | $0.11 | 308 | 1.12 | 9.24 | 6.50 | ||
MiniMax-M3 | 1M | Offen | 44 | $0.20 | 62 | 0.93 | 41.16 | 32.19 | ||
MiniMax-M3 | 1M | Offen | 44 | $0.13 | 110 | 1.31 | 24.10 | 18.23 | ||
MiniMax-M3 | 524k | Offen | 44 | $0.13 | 29 | 1.32 | 88.48 | 69.73 | ||
MiniMax-M3 (FP8) | 1.05M | Offen | 44 | $0.45 | 175 | 1.94 | 16.19 | 11.40 | ||
MiniMax-M3 (FP8) | 1M | Offen | 44 | $0.12 | 84 | 1.66 | 31.34 | 23.74 | ||
MiniMax-M3 | 512k | Offen | 44 | $0.14 | 73 | 1.55 | 35.92 | 27.50 | ||
MiniMax-M3 | 1.05M | Offen | 44 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) (FP4) | 1.05M | Offen | 44 | $0.27 | 38 | 2.14 | 130.52 | 115.22 | ||
DeepSeek V4 Pro (max) | 1M | Offen | 44 | $0.90 | 84 | 1.61 | 59.48 | 51.93 | ||
DeepSeek V4 Pro (max) | 1.05M | Offen | 44 | $0.23 | 65 | 1.71 | 76.79 | 67.38 | ||
DeepSeek V4 Pro (max) | 1M | Offen | 44 | $0.76 | 165 | 0.97 | 30.51 | 26.51 | ||
DeepSeek V4 Pro (max) (FP8) | 1.05M | Offen | 44 | $0.31 | 54 | 1.72 | 91.26 | 80.36 | ||
DeepSeek V4 Pro (max) | 1.05M | Offen | 44 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) | 1M | Offen | 44 | $0.90 | 68 | 1.57 | 72.93 | 64.04 | ||
DeepSeek V4 Pro (max) | 1.05M | Offen | 44 | $0.38 | 121 | 1.54 | 41.78 | 36.11 | ||
DeepSeek V4 Pro (max) | 1M | Offen | 44 | $0.05 | 64 | 1.61 | 77.21 | 67.85 | ||
GPT-5.3 Codex (xhigh) | 400k | Proprietär | 44* | -- | 124 | 84.77 | 88.80 | -- | ||
DeepSeek V4 Pro (high) (FP4) | 65.5k | Offen | 43 | $0.26 | 36 | 1.50 | 71.32 | 55.82 | ||
DeepSeek V4 Pro (high) | 1.05M | Offen | 43 | $0.36 | 91 | 1.57 | 28.98 | 21.91 | ||
DeepSeek V4 Pro (high) | 1M | Offen | 43 | $0.94 | 81 | 1.61 | 32.26 | 24.50 | ||
DeepSeek V4 Pro (high) | 1M | Offen | 43 | $0.04 | 66 | 1.51 | 39.36 | 30.25 | ||
DeepSeek V4 Pro (high) (FP8) | 1.05M | Offen | 43 | $0.29 | 52 | 1.83 | 49.61 | 38.20 | ||
DeepSeek V4 Pro (high) | 1M | Offen | 43 | $0.94 | 54 | 1.44 | 47.85 | 37.10 | ||
DeepSeek V4 Pro (high) | 1M | Offen | 43 | $0.78 | 181 | 0.99 | 14.77 | 11.01 | ||
DeepSeek V4 Pro (high) | 1.05M | Offen | 43 | $0.20 | 60 | 1.91 | 43.15 | 32.97 | ||
DeepSeek V4 Pro (high) | 131k | Offen | 43 | $0.68 | 146 | 0.55 | 17.56 | 13.60 | ||
MiMo-V2.5-Pro | 1.05M | Offen | 42 | $0.04 | 50 | 2.31 | 52.08 | 39.82 | ||
MiMo-V2.5-Pro | 1.05M | Offen | 42 | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | Offen | 42 | $0.18 | 107 | 0.95 | 24.33 | 18.70 | ||
MiMo-V2.5-Pro | 1M | Offen | 42 | $0.03 | 67 | 2.74 | 40.23 | 30.00 | ||
Kimi K2.7 Code (FP4) | 256k | Offen | 42 | $0.64 | 87 | 1.76 | 33.01 | 25.52 | ||
Kimi K2.7 Code (FP8) | 65.5k | Offen | 42 | $0.46 | 43 | 5.67 | 68.65 | 51.44 | ||
Kimi K2.7 Code | 262k | Offen | 42 | $0.28 | 287 | 1.15 | 10.68 | 7.78 | ||
Kimi K2.7 Code | 262k | Offen | 42 | $0.18 | 77 | 1.44 | 37.09 | 29.11 | ||
Kimi K2.7 Code | 262k | Offen | 42 | $0.30 | 227 | 0.51 | 12.55 | 9.83 | ||
Kimi K2.7 Code | 262k | Offen | 42 | $0.22 | 42 | 3.48 | 67.80 | 52.53 | ||
Kimi K2.7 Code | 262k | Offen | 42 | $0.20 | 108 | 0.96 | 26.12 | 20.55 | ||
Kimi K2.7 Code | 262k | Offen | 42 | $0.18 | 100 | 0.76 | 28.10 | 22.33 | ||
Kimi K2.7 Code | 256k | Offen | 42 | $0.22 | 42 | 2.85 | 67.31 | 52.65 | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietär | 42 | $0.42 | 61 | 1.65 | 9.79 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietär | 42 | $0.62 | 63 | 2.13 | 10.07 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 524k | Proprietär | 42 | $0.48 | 64 | 2.10 | 9.97 | -- | ||
Hy3 (FP8) | 256k | Offen | 41 | $0.03 | 70 | 2.77 | 38.50 | 28.58 | ||
Hy3 | 262k | Offen | 41 | $0.04 | 64 | 2.78 | 41.92 | 31.32 | ||
Hy3 (FP8) | 262k | Offen | 41 | $0.04 | 61 | 0.65 | 41.63 | 32.79 | ||
Hy3 | 262k | Offen | 41 | $0.03 | 73 | 3.21 | 37.61 | 27.52 | ||
GPT-5.6 Sol (Non-reasoning) | 1M | Proprietär | 41 | $0.24 | 60 | 1.05 | 9.38 | -- | ||
GPT-5.6 Sol (Non-reasoning) | 262k | Proprietär | 41 | $0.30 | 94 | 1.73 | 7.02 | -- | ||
Nex-N2-Pro (FP8) | 262k | Offen | 41 | -- | 131 | 1.60 | 20.68 | 15.27 | ||
Inkling (FP8) | 131k | Offen | 41 | $0.43 | 190 | 0.71 | 13.89 | 10.54 | ||
Inkling | 524k | Offen | 41 | $0.61 | 99 | 0.63 | 25.99 | 20.29 | ||
Inkling | 262k | Offen | 41 | -- | 80 | 1.84 | 32.93 | 24.87 | ||
GPT-5.6 Terra (low) | 1M | Proprietär | 40 | $0.09 | 112 | 1.64 | 6.10 | -- | ||
Inkling Small | 256k | Offen | 40 | $0.07 | 137 | 1.58 | 19.88 | 14.64 | ||
Inkling Small | 524k | Offen | 40 | $0.15 | 134 | 0.68 | 19.37 | 14.95 | ||
Qwen3.6 Plus | 1M | Proprietär | 40 | $0.36 | 56 | 2.11 | 110.40 | 99.34 | ||
Qwen3.7 Plus | 1M | Proprietär | 39 | $0.23 | 54 | 2.33 | 48.49 | 36.93 | ||
Agnes 2.5 Pro Alpha | 1M | Proprietär | 39 | -- | 134 | 2.72 | 21.40 | 14.95 | ||
GPT-5.6 Luna (medium) | 1M | Proprietär | 38 | $0.01 | 151 | 3.01 | 6.33 | -- | ||
Nemotron 3 Ultra | 262k | Offen | 38 | $0.16 | 252 | 1.08 | 12.09 | 9.02 | ||
Nemotron 3 Ultra | 262k | Offen | 38 | -- | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 512k | Offen | 38 | $0.40 | 145 | 0.72 | 19.83 | 15.67 | ||
Nemotron 3 Ultra | 262k | Offen | 38 | $0.23 | 85 | 6.12 | 38.94 | 26.91 | ||
Nemotron 3 Ultra BF16 | 262k | Offen | 38 | -- | 97 | 6.22 | 34.82 | 23.45 | ||
Nemotron 3 Ultra | 256k | Offen | 38 | $0.59 | 311 | 2.30 | 11.21 | 7.30 | ||
Nemotron 3 Ultra | 262k | Offen | 38 | $0.24 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Offen | 38 | $0.22 | -- | -- | -- | -- | ||
MiMo-V2.5 | 1.05M | Offen | 37 | $0.01 | 73 | 2.01 | 36.43 | 27.54 | ||
MiMo-V2.5 | 1M | Offen | 37 | $0.04 | 73 | 1.15 | 35.32 | 27.34 | ||
MiMo-V2.5 | 262k | Offen | 37 | $0.08 | 56 | 0.88 | 45.48 | 35.68 | ||
MiMo-V2.5 | 1.05M | Offen | 37 | $0.02 | -- | -- | -- | -- | ||
MiMo-V2.5 | 1M | Offen | 37 | $0.01 | 85 | 2.56 | 31.94 | 23.50 | ||
Qwen3.6 27B FP8 | 262k | Offen | 37 | $0.19 | 65 | 1.11 | 96.84 | 87.98 | ||
Qwen3.6 27B | 131k | Offen | 37 | $0.28 | 453 | 1.06 | 14.68 | 12.52 | ||
Qwen3.6 27B | 262k | Offen | 37 | $0.29 | 58 | 3.03 | 110.04 | 98.35 | ||
Qwen3.6 27B | 262k | Offen | 37 | $0.29 | 59 | 3.77 | 108.76 | 96.48 | ||
Qwen3.6 27B (FP8) | 262k | Offen | 37 | $0.19 | 42 | 3.54 | 151.25 | 135.75 | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | Proprietär | 36 | $0.10 | 346 | 10.30 | 11.75 | -- | ||
Grok 4.3 (medium) | 524k | Proprietär | 36* | -- | 180 | 8.53 | 11.30 | -- | ||
Grok 4.3 (medium) | 200k | Proprietär | 36* | -- | 153 | 11.88 | 15.15 | -- | ||
Grok 4.3 (medium) | 1M | Proprietär | 36* | -- | 127 | 11.57 | 15.52 | -- | ||
Grok 4.3 (low) | 524k | Proprietär | 35* | -- | 161 | 4.19 | 7.30 | -- | ||
Grok 4.3 (low) | 200k | Proprietär | 35* | -- | 157 | 5.56 | 8.76 | -- | ||
Grok 4.3 (low) | 1M | Proprietär | 35* | -- | 112 | 6.49 | 10.98 | -- | ||
Gemini 3.5 Flash (minimal) AI Studio | 1M | Proprietär | 35* | -- | 171 | 1.05 | 3.97 | -- | ||
Kimi K2.6 | 262k | Offen | 35* | -- | -- | -- | -- | -- | ||
Kimi K2.6 (FP4) | 262k | Offen | 35* | -- | 401 | 0.64 | 1.89 | -- | ||
Kimi K2.6 (FP8) | 262k | Offen | 35* | -- | 43 | 1.74 | 13.40 | -- | ||
Kimi K2.6 | 262k | Offen | 35* | -- | 60 | 1.22 | 9.62 | -- | ||
Kimi K2.6 (INT4) | 262k | Offen | 35* | -- | 91 | 1.43 | 6.93 | -- | ||
Kimi K2.6 (FP4) | 262k | Offen | 35* | -- | 37 | 0.92 | 14.52 | -- | ||
Kimi K2.6 | 262k | Offen | 35* | -- | 221 | 1.13 | 3.39 | -- | ||
Kimi K2.6 | 262k | Offen | 35* | -- | 182 | 1.49 | 4.23 | -- | ||
Kimi K2.6 (NVFP4) | 262k | Offen | 35* | -- | -- | -- | -- | -- | ||
Kimi K2.6 | 256k | Offen | 35* | -- | 35 | 2.89 | 17.02 | -- | ||
Kimi K2.6 | 262k | Offen | 35* | -- | 218 | 1.92 | 4.21 | -- | ||
Kimi K2.6 | 262k | Offen | 35* | -- | 43 | 2.00 | 13.72 | -- | ||
Claude Sonnet 4.6 (Non-reasoning, Low Effort) | 1M | Proprietär | 34* | -- | 44 | 1.72 | 13.11 | -- | ||
GLM-5.2 (FP4) | 432k | Offen | 34 | -- | 204 | 1.21 | 3.65 | -- | ||
GLM-5.2 | 262k | Offen | 34 | -- | 64 | 1.82 | 9.59 | -- | ||
GLM-5.2 | 205k | Offen | 34 | -- | 175 | 5.45 | 8.31 | -- | ||
GLM-5.2 (FP8) | 1.05M | Offen | 34 | -- | 59 | 1.30 | 9.75 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 1M | Proprietär | 34 | $0.10 | 107 | 0.79 | 5.48 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 262k | Proprietär | 34 | $0.20 | 133 | 0.70 | 4.46 | -- | ||
KAT-Coder-Pro V2 | 256k | Proprietär | 34 | -- | 108 | 1.87 | 6.50 | -- | ||
KAT-Coder-Pro V2 | 256k | Proprietär | 34 | -- | -- | -- | -- | -- | ||
Qwen3.5 397B A17B | 256k | Offen | 34 | $0.36 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B | 262k | Offen | 34 | $0.36 | 70 | 2.37 | 54.83 | 45.34 | ||
Qwen3.5 397B A17B | 262k | Offen | 34 | $0.13 | 72 | 2.21 | 53.52 | 44.35 | ||
Qwen3.5 397B A17B | 262k | Offen | 34 | $0.23 | 85 | 1.04 | 44.43 | 37.50 | ||
Qwen3.5 397B A17B (FP8) | 262k | Offen | 34 | $0.23 | 103 | 2.08 | 37.93 | 30.99 | ||
Qwen3.5 397B A17B (FP8) | 262k | Offen | 34 | $0.19 | 52 | 0.93 | 71.31 | 60.83 | ||
Qwen3.5 397B A17B | 262k | Offen | 34 | $0.13 | 11 | 1.94 | 338.44 | 290.85 | ||
Qwen3.5 397B A17B (FP8) | 262k | Offen | 34 | $0.36 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Offen | 34 | $0.36 | 120 | 1.99 | 32.79 | 26.62 | ||
Qwen3.5 397B A17B | 262k | Offen | 34 | $0.36 | 68 | 1.72 | 55.59 | 46.56 | ||
Hy3-preview | 262k | Offen | 34* | -- | -- | -- | -- | -- | ||
LongCat 2.0 (FP8) | 1M | Offen | 33 | $0.12 | 42 | 2.74 | 61.75 | 47.21 | ||
GPT-5.6 Luna (low) | 1M | Proprietär | 33 | $0.01 | 137 | 2.12 | 5.77 | -- | ||
Qwen3.5 122B A10B (FP8) | 262k | Offen | 32 | $0.17 | 52 | 1.89 | 50.23 | 38.67 | ||
Qwen3.5 122B A10B (FP4) | 262k | Offen | 32 | $0.12 | 157 | 0.66 | 16.61 | 12.76 | ||
Qwen3.5 122B A10B | 262k | Offen | 32 | $0.26 | 125 | 2.57 | 22.64 | 16.05 | ||
Qwen3.5 122B A10B (FP8) | 262k | Offen | 32 | $0.26 | -- | -- | -- | -- | ||
Qwen3.5 122B A10B | 262k | Offen | 32 | $0.26 | 107 | 1.87 | 25.28 | 18.73 | ||
Qwen3.5 397B A17B | 262k | Offen | 32* | -- | 71 | 2.19 | 9.25 | -- | ||
Qwen3.5 397B A17B (FP8) | 262k | Offen | 32* | -- | 44 | 0.92 | 12.19 | -- | ||
Qwen3.5 397B A17B | 262k | Offen | 32* | -- | 72 | 2.44 | 9.42 | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Offen | 32* | -- | 110 | 2.05 | 6.59 | -- | ||
Qwen3.5 397B A17B | 262k | Offen | 32* | -- | 12 | 1.70 | 42.83 | -- | ||
Qwen3.5 397B A17B | 262k | Offen | 32* | -- | 69 | 1.94 | 9.15 | -- | ||
Qwen3.6 35B A3B | 229k | Offen | 32 | $0.19 | 141 | 2.30 | 43.97 | 38.13 | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 32 | $0.17 | 72 | 2.15 | 84.33 | 75.21 | ||
Qwen3.6 35B A3B | 262k | Offen | 32 | $0.23 | 144 | 0.96 | 41.93 | 37.49 | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 32 | $0.09 | 68 | 0.64 | 87.79 | 79.76 | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 32 | $0.47 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B FP8 | 262k | Offen | 32 | $0.19 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | Offen | 32 | $0.08 | 103 | 1.34 | 58.34 | 52.17 | ||
Qwen3.6 35B A3B | 205k | Offen | 32 | $0.19 | 143 | 1.53 | 42.64 | 37.62 | ||
DeepSeek V4 Pro | 1M | Offen | 31* | -- | 85 | 1.66 | 7.55 | -- | ||
DeepSeek V4 Pro | 1.05M | Offen | 31* | -- | 52 | 1.45 | 11.15 | -- | ||
DeepSeek V4 Pro | 1M | Offen | 31* | -- | 211 | 0.96 | 3.33 | -- | ||
DeepSeek V4 Pro | 1M | Offen | 31* | -- | 63 | 1.52 | 9.41 | -- | ||
G9v3-39A5B | 131k | Offen | 31 | -- | -- | -- | -- | -- | ||
Qwen3.5 Omni Plus | 256k | Proprietär | 31* | -- | 53 | 2.36 | 11.83 | -- | ||
Ring-2.6-1T | 262k | Offen | 31 | $0.37 | -- | -- | -- | -- | ||
Qwen3.6 27B | 131k | Offen | 30 | $0.39 | 460 | 1.10 | 2.19 | -- | ||
Qwen3.6 27B FP8 | 262k | Offen | 30 | $0.23 | 63 | 1.11 | 9.05 | -- | ||
Qwen3.6 27B | 262k | Offen | 30 | $0.40 | 57 | 3.72 | 12.50 | -- | ||
Qwen3.6 27B | 262k | Offen | 30 | $0.40 | 60 | 2.86 | 11.12 | -- | ||
o3 | 200k | Proprietär | 30* | -- | 98 | 29.42 | 34.50 | -- | ||
o3 | 200k | Proprietär | 30* | -- | -- | -- | -- | -- | ||
o3 | 200k | Proprietär | 30* | -- | 120 | 8.41 | 12.57 | -- | ||
Step 3.7 Flash | 256k | Offen | 30 | $0.09 | 364 | 0.92 | 7.79 | 5.49 | ||
Step 3.7 Flash | 256k | Offen | 30 | -- | 199 | 0.53 | 13.07 | 10.03 | ||
Mistral Medium 3.5 | 262k | Offen | 30 | $0.46 | 134 | 1.88 | 20.57 | 14.96 | ||
Claude 4.5 Haiku | 200k | Proprietär | 30 | $0.23 | 116 | 11.99 | 16.30 | -- | ||
Claude 4.5 Haiku Vertex | 200k | Proprietär | 30 | $0.24 | 100 | 16.63 | 21.63 | -- | ||
Claude 4.5 Haiku | 200k | Proprietär | 30 | $0.22 | 99 | 18.99 | 24.05 | -- | ||
Claude 4.5 Haiku | 200k | Proprietär | 30 | $0.54 | 102 | 20.27 | 25.16 | -- | ||
Gemma 4 31B | 262k | Offen | 29 | -- | 35 | 1.37 | 65.03 | 49.42 | ||
Gemma 4 31B (FP8) | 262k | Offen | 29 | $0.04 | -- | -- | -- | -- | ||
Gemma 4 31B | 262k | Offen | 29 | $0.04 | -- | -- | -- | -- | ||
Gemma 4 31B | 131k | Offen | 29 | $0.25 | 1,454 | 0.99 | 2.53 | 1.19 | ||
Gemma 4 31B (AI Studio) | 262k | Offen | 29 | $0.00 | 35 | 1.10 | 64.26 | 49.03 | ||
Gemma 4 31B | 262k | Offen | 29 | $0.03 | 32 | 4.92 | 75.69 | 54.95 | ||
Gemma 4 31B | 262k | Offen | 29 | $0.01 | 28 | 1.50 | 82.35 | 62.77 | ||
Gemma 4 31B (FP8) | 262k | Offen | 29 | $0.03 | 51 | 3.76 | 47.77 | 34.17 | ||
Gemma 4 31B | 131k | Offen | 29 | $0.10 | 199 | 3.02 | 14.27 | 8.73 | ||
Gemma 4 31B | 256k | Offen | 29 | $0.04 | 124 | 2.06 | 20.11 | 14.01 | ||
Gemma 4 31B | 131k | Offen | 29 | $0.04 | 153 | 0.79 | 15.37 | 11.31 | ||
Gemma 4 31B (FP8) | 262k | Offen | 29 | $0.10 | 58 | 1.56 | 40.30 | 30.08 | ||
GPT-5.5 Instant (June 2026) | 400k | Proprietär | 29 | $0.54 | 168 | 1.00 | 15.93 | 11.94 | ||
DeepSeek V4 Flash | 1M | Offen | 29* | -- | 120 | 1.20 | 5.36 | -- | ||
DeepSeek V4 Flash | 1.05M | Offen | 29* | -- | -- | -- | -- | -- | ||
DeepSeek V4 Flash | 1M | Offen | 29* | -- | 152 | 0.73 | 4.03 | -- | ||
DeepSeek V4 Flash | 1M | Offen | 29* | -- | 59 | 1.53 | 9.97 | -- | ||
MiMo-V2.5-Pro | 1.05M | Offen | 28* | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | Offen | 28* | -- | 117 | 0.94 | 5.21 | -- | ||
MiMo-V2.5-Pro | 131k | Offen | 28* | -- | 61 | 3.24 | 11.37 | -- | ||
MiMo-V2.5-Pro | 1.05M | Offen | 28* | -- | 50 | 2.05 | 12.08 | -- | ||
Qwen3.5 122B A10B (FP4) | 262k | Offen | 28 | $0.09 | 185 | 0.66 | 3.36 | -- | ||
Qwen3.5 122B A10B | 262k | Offen | 28 | $0.19 | 140 | 2.56 | 6.12 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 1M | Proprietär | 27 | $0.01 | 162 | 0.82 | 3.91 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 262k | Proprietär | 27 | $0.09 | 150 | 6.31 | 9.64 | -- | ||
Hy3-preview | 262k | Offen | 26* | -- | -- | -- | -- | -- | ||
Ling-2.6-1T | 262k | Offen | 26* | -- | -- | -- | -- | -- | ||
Gemini 2.5 Pro Vertex | 1M | Proprietär | 26 | $0.22 | 113 | 26.81 | 31.25 | -- | ||
Gemini 2.5 Pro (AI Studio) | 1M | Proprietär | 26 | $0.22 | 136 | 22.36 | 26.03 | -- | ||
Gemma 4 26B A4B | 1M | Offen | 26 | $0.02 | 164 | 0.95 | 16.15 | 12.16 | ||
Gemma 4 26B A4B | 262k | Offen | 26 | $0.04 | 35 | 2.37 | 74.64 | 57.82 | ||
Gemma 4 26B A4B AI Studio | 262k | Offen | 26 | $0.00 | 47 | 1.07 | 54.26 | 42.55 | ||
Gemma 4 26B A4B | 256k | Offen | 26 | $0.03 | 108 | 0.97 | 24.07 | 18.48 | ||
Gemma 4 26B A4B | 262k | Offen | 26 | $0.03 | 31 | 0.76 | 82.60 | 65.47 | ||
Gemma 4 26B A4B | 256k | Offen | 26 | $0.03 | 35 | 1.49 | 72.25 | 56.61 | ||
Gemma 4 26B A4B | 256k | Offen | 26 | $0.20 | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 1.05M | Offen | 26 | $0.04 | -- | -- | -- | -- | ||
NVIDIA Nemotron 3 Super | 262k | Offen | 25 | $0.23 | 143 | 1.02 | 18.55 | 14.02 | ||
NVIDIA Nemotron 3 Super | 256k | Offen | 25 | $0.34 | 243 | 1.88 | 12.17 | 8.23 | ||
NVIDIA Nemotron 3 Super | 262k | Offen | 25 | $0.10 | 56 | 20.65 | 65.21 | 35.65 | ||
Gemini 3.1 Flash-Lite (AI Studio) | 1M | Proprietär | 25 | $0.04 | 312 | 6.13 | 7.73 | -- | ||
Grok 4.3 (Non-reasoning) | 524k | Proprietär | 25 | $0.91 | 178 | 0.71 | 3.53 | -- | ||
Grok 4.3 (Non-reasoning) | 1M | Proprietär | 25 | $0.29 | 120 | 0.73 | 4.91 | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 24 | $1.20 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | Offen | 24 | $0.49 | 160 | 0.90 | 4.03 | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 24 | $0.29 | 40 | 0.73 | 13.14 | -- | ||
Qwen3.6 35B A3B | 205k | Offen | 24 | $0.42 | 168 | 1.46 | 4.43 | -- | ||
Qwen3.6 35B A3B FP8 | 262k | Offen | 24 | $0.42 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 24 | $0.15 | 95 | 1.29 | 6.58 | -- | ||
Qwen3.6 35B A3B | 262k | Offen | 24 | $0.63 | 164 | 2.42 | 5.47 | -- | ||
Qwen3.5 35B A3B FP8 | 262k | Offen | 24 | $0.07 | 122 | 0.54 | 4.65 | -- | ||
Qwen3.5 35B A3B | 262k | Offen | 24 | $0.24 | 170 | 2.35 | 5.29 | -- | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.06 | 478 | 0.67 | 5.90 | 4.18 | ||
gpt-oss-120b (high) | 116k | Offen | 24 | $0.15 | 118 | 1.05 | 22.20 | 16.92 | ||
gpt-oss-120b (high) | 128k | Offen | 24 | $0.09 | 176 | 1.24 | 15.46 | 11.38 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.02 | 45 | 0.61 | 55.79 | 44.15 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.02 | 33 | 1.46 | 77.45 | 60.80 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.08 | 305 | 1.01 | 9.19 | 6.55 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.03 | 89 | 1.05 | 29.05 | 22.39 | ||
gpt-oss-120b (high) (Turbo) | 131k | Offen | 24 | $0.08 | 180 | 0.69 | 14.58 | 11.11 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.15 | 1,851 | 0.49 | 1.84 | 1.08 | ||
gpt-oss-120b (high) Vertex | 131k | Offen | 24 | $0.05 | 423 | 0.39 | 6.30 | 4.72 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.05 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | Offen | 24 | $0.05 | 184 | 0.26 | 13.87 | 10.89 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.10 | 710 | 1.40 | 4.93 | 2.82 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | -- | 170 | 0.89 | 15.59 | 11.76 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.08 | 125 | 0.75 | 20.72 | 15.97 | ||
gpt-oss-120b (high) (Base) | 128k | Offen | 24 | $0.08 | 221 | 1.03 | 12.35 | 9.06 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.12 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | Offen | 24 | $0.08 | 328 | 0.64 | 8.28 | 6.11 | ||
gpt-oss-120b (high) | 131k | Offen | 24 | $0.08 | 105 | 1.03 | 24.74 | 18.97 | ||
Claude 4.5 Haiku | 200k | Proprietär | 24* | -- | 90 | 1.26 | 6.83 | -- | ||
Claude 4.5 Haiku | 200k | Proprietär | 24* | -- | 102 | 1.03 | 5.94 | -- | ||
Claude 4.5 Haiku | 200k | Proprietär | 24* | -- | 90 | 0.98 | 6.54 | -- | ||
Claude 4.5 Haiku Vertex | 200k | Proprietär | 24* | -- | 92 | 0.66 | 6.09 | -- | ||
Command A+ | 200k | Offen | 23 | $0.00 | 209 | 0.44 | 12.38 | 9.56 | ||
Gemma 4 12B | 262k | Offen | 22 | $0.08 | 111 | 2.39 | 24.86 | 17.97 | ||
Gemma 4 31B | 262k | Offen | 22 | $0.02 | 28 | 4.07 | 21.62 | -- | ||
Gemma 4 31B | 131k | Offen | 22 | $0.25 | 1,212 | 0.92 | 1.33 | -- | ||
Gemma 4 31B | 262k | Offen | 22 | $0.04 | 134 | 1.24 | 4.96 | -- | ||
Gemma 4 31B (FP8) | 262k | Offen | 22 | $0.10 | 62 | 1.28 | 9.32 | -- | ||
Gemma 4 31B (FP8) | 262k | Offen | 22 | $0.03 | 56 | 2.85 | 11.83 | -- | ||
Gemma 4 31B (FP8) | 262k | Offen | 22 | $0.03 | 26 | 1.49 | 20.49 | -- | ||
Gemma 4 31B | 131k | Offen | 22 | $0.10 | 198 | 2.55 | 5.08 | -- | ||
Gemma 4 31B | 262k | Offen | 22 | $0.04 | 24 | 1.53 | 22.33 | -- | ||
Nova 2.0 Pro Preview (medium) | 256k | Proprietär | 22 | $0.18 | 118 | 14.71 | 35.85 | 16.92 | ||
Qwen3.5 9B (FP8) | 262k | Offen | 21 | $0.18 | 48 | 2.39 | 54.01 | 41.29 | ||
Qwen3.5 9B (FP8) | 262k | Offen | 21 | $0.31 | 86 | 0.74 | 29.84 | 23.28 | ||
Mercury 2 | 128k | Proprietär | 21 | $0.08 | 742 | 3.28 | 3.95 | -- | ||
Qwen3 Coder Next | 128k | Offen | 21 | $0.47 | 133 | 1.62 | 5.37 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Offen | 21 | $0.08 | 76 | 1.09 | 7.68 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Offen | 21 | $0.47 | -- | -- | -- | -- | ||
Qwen3 Coder Next (FP8) | 262k | Offen | 21 | $0.20 | 168 | 2.76 | 5.74 | -- | ||
Nova 2.0 Omni (medium) | 1M | Proprietär | 21* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (medium) | 1M | Proprietär | 21* | -- | -- | -- | -- | -- | ||
Apriel-v1.6-15B-Thinker | 131k | Offen | 21* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B | 1M | Offen | 20* | -- | 178 | 0.97 | 3.79 | -- | ||
Gemma 4 26B A4B | 262k | Offen | 20* | -- | 39 | 1.52 | 14.42 | -- | ||
Gemma 4 26B A4B (FP8) | 1.05M | Offen | 20* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | Offen | 20* | -- | 106 | 2.13 | 6.86 | -- | ||
Gemma 4 26B A4B | 256k | Offen | 20* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B | 262k | Offen | 20* | -- | 144 | 0.92 | 4.40 | -- | ||
Gemma 4 26B A4B (FP8) | 262k | Offen | 20* | -- | 28 | 0.71 | 18.64 | -- | ||
Gemma 4 26B A4B | 262k | Offen | 20* | -- | 37 | 2.96 | 16.64 | -- | ||
Qwen3.5 4B (FP8) | 262k | Offen | 20* | -- | 32 | 0.67 | 78.55 | 62.30 | ||
North Mini Code | 256k | Offen | 20 | $0.00 | 21 | 0.62 | 117.18 | 93.24 | ||
Nova 2.0 Pro Preview (low) | 256k | Proprietär | 20 | $0.23 | 123 | 11.68 | 32.00 | 16.25 | ||
Mistral Small 4 | 256k | Offen | 20 | $0.10 | 158 | 1.00 | 16.83 | 12.67 | ||
Devstral 2 | 262k | Offen | 19 | $0.00 | 43 | 1.47 | 13.16 | -- | ||
Nova 2.0 Lite (medium) | 1M | Proprietär | 19* | -- | 155 | 17.81 | 33.96 | 12.92 | ||
Qwen3.5 Omni Flash | 256k | Proprietär | 19* | -- | 242 | 1.86 | 3.93 | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietär | 18 | $0.24 | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietär | 18 | $0.24 | 138 | 16.25 | 34.32 | 14.46 | ||
Trinity Large Thinking | 262k | Offen | 18 | $0.20 | 253 | 1.45 | 11.34 | 7.91 | ||
Trinity Large Thinking (FP8) | 262k | Offen | 18 | $0.08 | 202 | 0.96 | 13.34 | 9.90 | ||
Magistral Medium 1.2 | 131k | Proprietär | 18 | $0.84 | 110 | 2.17 | 24.96 | 18.23 | ||
Nova 2.0 Lite (low) | 1M | Proprietär | 18* | -- | 156 | 10.57 | 26.55 | 12.78 | ||
HyperNova 60B 2605 | 131k | Offen | 18 | $0.02 | 349 | 0.93 | 8.10 | 5.74 | ||
Devstral Small 2 | 256k | Offen | 17 | $0.00 | 89 | 1.74 | 7.38 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 17 | $0.05 | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Offen | 17 | $0.04 | 160 | 0.77 | 16.42 | 12.52 | ||
Qwen3 Next 80B A3B | 262k | Offen | 17 | $0.19 | 205 | 2.41 | 14.61 | 9.76 | ||
Qwen3 Next 80B A3B (FP8) | 262k | Offen | 17 | $0.04 | 102 | 1.09 | 25.65 | 19.65 | ||
Qwen3 Next 80B A3B | 262k | Offen | 17 | $0.03 | -- | -- | -- | -- | ||
Nova 2.0 Omni (low) | 1M | Proprietär | 17* | -- | -- | -- | -- | -- | ||
G9v3-3B | 131k | Offen | 16 | $0.00 | -- | -- | -- | -- | ||
Qwen3.5 4B FP8 | 262k | Offen | 16* | -- | 19 | 0.96 | 26.91 | -- | ||
Mistral Large 3 | 256k | Offen | 16 | $0.08 | 192 | 1.15 | 3.75 | -- | ||
Mistral Large 3 | 256k | Offen | 16 | $0.08 | 99 | 1.50 | 6.56 | -- | ||
Mistral Large 3 | 262k | Offen | 16 | $0.08 | 43 | 1.22 | 12.88 | -- | ||
Nemotron 3 Nano Omni 30B A3B Reasoning | 262k | Offen | 15* | -- | -- | -- | -- | -- | ||
Nemotron 3 Nano Omni 30B A3B Reasoning (FP8) | 65.5k | Offen | 15* | -- | 324 | 1.01 | 8.73 | 6.18 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.04 | -- | -- | -- | -- | ||
gpt-oss-120b (low) Base | 128k | Offen | 15 | $0.02 | 261 | 0.97 | 10.57 | 7.67 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.03 | 734 | 1.25 | 4.65 | 2.72 | ||
gpt-oss-120b (low) Vertex | 131k | Offen | 15 | $0.01 | 408 | 0.38 | 6.52 | 4.91 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.02 | 98 | 0.77 | 26.17 | 20.32 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.0042 | 37 | 1.41 | 68.33 | 53.54 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.05 | 1,760 | 0.53 | 1.95 | 1.14 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.02 | 330 | 1.69 | 9.26 | 6.05 | ||
gpt-oss-120b (low) | 128k | Offen | 15 | $0.05 | 121 | 1.04 | 21.71 | 16.54 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 128k | Offen | 15 | $0.01 | 163 | 0.26 | 15.60 | 12.27 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.02 | 102 | 1.05 | 25.67 | 19.70 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | -- | 168 | 0.82 | 15.68 | 11.89 | ||
gpt-oss-120b (low) | 128k | Offen | 15 | $0.02 | 327 | 0.64 | 8.27 | 6.11 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.02 | 474 | 0.69 | 5.96 | 4.22 | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | Offen | 15 | $0.01 | 80 | 1.13 | 32.43 | 25.04 | ||
gpt-oss-20b (high) | 131k | Offen | 15 | $0.01 | 121 | 0.89 | 21.49 | 16.48 | ||
gpt-oss-20b (high) | 131k | Offen | 15 | $0.03 | 157 | 33.64 | 49.55 | 12.73 | ||
gpt-oss-20b (high) | 131k | Offen | 15 | $0.01 | 107 | 0.51 | 23.93 | 18.74 | ||
gpt-oss-20b (high) | 131k | Offen | 15 | $0.04 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | Offen | 15 | $0.02 | 273 | 0.71 | 9.87 | 7.33 | ||
gpt-oss-20b (high) | 128k | Offen | 15 | $0.08 | 146 | 0.75 | 17.85 | 13.68 | ||
gpt-oss-20b (high) | 131k | Offen | 15 | $0.02 | 62 | 1.08 | 41.39 | 32.25 | ||
gpt-oss-20b (high) Vertex | 131k | Offen | 15 | $0.03 | 312 | 3.32 | 11.35 | 6.42 | ||
gpt-oss-20b (high) | 131k | Offen | 15 | $0.03 | 311 | 0.94 | 8.97 | 6.42 | ||
gpt-oss-20b (high) | 131k | Offen | 15 | $0.03 | 942 | 0.80 | 3.46 | 2.12 | ||
gpt-oss-20b (high) | 131k | Offen | 15 | $0.02 | -- | -- | -- | -- | ||
Nova 2.0 Pro Preview | 256k | Proprietär | 14 | $0.26 | 96 | 1.01 | 6.24 | -- | ||
gpt-oss-20b (low) | 131k | Offen | 14* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Offen | 14* | -- | 934 | 0.81 | 3.48 | 2.14 | ||
gpt-oss-20b (low) | 128k | Offen | 14* | -- | 274 | 0.77 | 9.90 | 7.31 | ||
gpt-oss-20b (low) | 131k | Offen | 14* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Offen | 14* | -- | 93 | 0.94 | 27.69 | 21.40 | ||
gpt-oss-20b (low) | 128k | Offen | 14* | -- | 151 | 0.77 | 17.37 | 13.28 | ||
gpt-oss-20b (low) | 131k | Offen | 14* | -- | 101 | 13.01 | 37.74 | 19.78 | ||
gpt-oss-20b (low) | 131k | Offen | 14* | -- | 70 | 1.19 | 36.88 | 28.56 | ||
gpt-oss-20b (low) | 131k | Offen | 14* | -- | 291 | 0.85 | 9.45 | 6.88 | ||
gpt-oss-20b (low) Vertex | 131k | Offen | 14* | -- | 246 | 0.41 | 10.56 | 8.12 | ||
Llama 4 Maverick (FP8) | 1.05M | Offen | 14 | $0.04 | 45 | 0.93 | 11.94 | -- | ||
Llama 4 Maverick (FP8) | 128k | Offen | 14 | $0.03 | 116 | 1.46 | 5.76 | -- | ||
Llama 4 Maverick | 128k | Offen | 14 | $0.03 | 220 | 0.86 | 3.13 | -- | ||
Llama 4 Maverick | 131k | Offen | 14 | $0.06 | 129 | 1.12 | 4.99 | -- | ||
Llama 4 Maverick | 1.05M | Offen | 14 | $0.04 | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Offen | 14 | $0.03 | 42 | 0.66 | 12.65 | -- | ||
Llama 4 Maverick | 131k | Offen | 14 | $0.06 | 85 | 0.72 | 6.58 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Offen | 14 | $0.03 | 138 | 0.89 | 4.52 | -- | ||
NVIDIA Nemotron 3 Nano | 262k | Offen | 14 | $0.03 | 322 | 1.14 | 8.90 | 6.21 | ||
NVIDIA Nemotron 3 Nano (FP4) | 262k | Offen | 14 | $0.02 | 277 | 1.32 | 10.35 | 7.22 | ||
NVIDIA Nemotron 3 Nano | 262k | Offen | 14 | $0.02 | 178 | 3.33 | 17.35 | 11.22 | ||
Solar Pro 3 | 131k | Proprietär | 14 | $0.14 | 125 | 2.29 | 22.35 | 16.05 | ||
Ling 2.6 Flash | 262k | Offen | 14 | -- | 100 | 1.17 | 6.17 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 14* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Offen | 14* | -- | 184 | 0.75 | 3.47 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 14* | -- | 181 | 2.36 | 5.13 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 14* | -- | 130 | 0.67 | 4.51 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 14* | -- | 139 | 0.90 | 4.49 | -- | ||
Qwen3 Next 80B A3B | 131k | Offen | 14* | -- | 183 | 1.65 | 4.38 | -- | ||
Qwen3 Next 80B A3B | 131k | Offen | 14* | -- | 185 | 2.17 | 4.88 | -- | ||
Gemma 4 12B (Non-reasoning) | 262k | Offen | 13* | -- | 108 | 2.38 | 7.01 | -- | ||
Nova Premier | 1M | Proprietär | 13* | -- | 32 | 2.85 | 18.65 | -- | ||
Llama Nemotron Super 49B v1.5 | 131k | Offen | 12* | -- | 81 | 5.85 | 36.73 | 24.70 | ||
Mistral Small 4 | 262k | Offen | 12* | -- | 130 | 0.93 | 4.76 | -- | ||
Gemma 4 E4B | 262k | Offen | 12 | $0.01 | 82 | 0.81 | 31.19 | 24.30 | ||
Sarvam 105B (high) | 128k | Offen | 12* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite | 1M | Proprietär | 12* | -- | 152 | 1.08 | 4.37 | -- | ||
Celeris-1 | 131k | Proprietär | 12 | -- | 2,034 | 0.69 | 0.94 | -- | ||
Magistral Small 1.2 | 128k | Offen | 11 | $0.29 | 74 | 1.58 | 35.30 | 26.98 | ||
Magistral Small 1.2 | 131k | Offen | 11 | $0.29 | 137 | 0.84 | 19.10 | 14.61 | ||
Ministral 3 14B | 262k | Offen | 11 | $0.16 | 95 | 0.87 | 6.14 | -- | ||
Ministral 3 14B | 256k | Offen | 11 | $0.16 | 180 | 1.15 | 3.94 | -- | ||
Nova 2.0 Omni | 1M | Proprietär | 11* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 328k | Offen | 10 | $0.01 | 55 | 0.63 | 9.71 | -- | ||
Llama 4 Scout | 128k | Offen | 10 | $0.01 | -- | -- | -- | -- | ||
Llama 4 Scout Vertex | 1.31M | Offen | 10 | $0.01 | 136 | 0.83 | 4.52 | -- | ||
Llama 4 Scout | 131k | Offen | 10 | $0.02 | 69 | 1.15 | 8.41 | -- | ||
Llama 4 Scout | 128k | Offen | 10 | $0.01 | 155 | 0.83 | 4.06 | -- | ||
Llama 4 Scout | 131k | Offen | 10 | $0.01 | 54 | 0.84 | 10.13 | -- | ||
Llama 4 Scout | 131k | Offen | 10 | $0.01 | 448 | 0.89 | 2.01 | -- | ||
Hermes 4 70B (FP8) | 128k | Offen | 10* | -- | 89 | 1.39 | 29.41 | 22.42 | ||
Qwen3 Omni 30B A3B | 65.5k | Offen | 10* | -- | 102 | 1.99 | 26.62 | 19.70 | ||
Llama 3.3 70B | 131k | Offen | 9 | $0.14 | -- | -- | -- | -- | ||
Llama 3.3 70B Vertex | 128k | Offen | 9 | $0.11 | 129 | 0.69 | 4.55 | -- | ||
Llama 3.3 70B | 131k | Offen | 9 | $0.09 | 303 | 0.93 | 2.58 | -- | ||
Llama 3.3 70B | 131k | Offen | 9 | $0.02 | -- | -- | -- | -- | ||
Llama 3.3 70B (FP8) | 131k | Offen | 9 | $0.02 | 59 | 2.52 | 10.93 | -- | ||
Llama 3.3 70B | 128k | Offen | 9 | $0.09 | 292 | 1.93 | 3.65 | -- | ||
Llama 3.3 70B Base | 128k | Offen | 9 | $0.02 | 14 | 7.08 | 42.58 | -- | ||
Llama 3.3 70B | 128k | Offen | 9 | $0.11 | 77 | 0.90 | 7.38 | -- | ||
Llama 3.3 70B Turbo | 131k | Offen | 9 | $0.16 | 86 | 1.31 | 7.11 | -- | ||
Llama 3.3 70B | 128k | Offen | 9 | $0.11 | 101 | 2.37 | 7.31 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | Offen | 9 | $0.02 | 13 | 2.35 | 39.71 | -- | ||
Llama 3.3 70B | 24k | Offen | 9 | $0.05 | 54 | 3.56 | 12.85 | -- | ||
Llama 3.3 70B | 128k | Offen | 9 | $0.11 | 126 | 1.08 | 5.04 | -- | ||
Llama 3.3 70B | 128k | Offen | 9 | $0.08 | 67 | 1.22 | 8.73 | -- | ||
Llama 3.3 70B | 100k | Offen | 9 | $0.16 | 85 | 1.36 | 7.26 | -- | ||
Llama Nemotron Ultra Base | 131k | Offen | 9* | -- | 52 | 2.34 | 50.08 | 38.19 | ||
ERNIE 4.5 300B A47B | 131k | Offen | 9* | -- | -- | -- | -- | -- | ||
Hermes 4 405B (FP8) | 128k | Offen | 9* | -- | 32 | 2.63 | 81.09 | 62.77 | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | Offen | 9* | -- | 86 | 7.19 | 36.26 | 23.26 | ||
Ministral 3 8B | 256k | Offen | 9 | $0.18 | 251 | 1.06 | 3.05 | -- | ||
Ministral 3 8B | 262k | Offen | 9 | $0.18 | 118 | 0.73 | 4.97 | -- | ||
Gemma 4 E4B | 262k | Offen | 9* | -- | 82 | 0.80 | 6.86 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Offen | 9* | -- | 180 | 5.20 | 19.08 | 11.11 | ||
Hermes 4 405B (FP8) | 128k | Offen | 9* | -- | 35 | 2.36 | 16.45 | -- | ||
Llama Nemotron Super 49B v1.5 | 131k | Offen | 9* | -- | 98 | 6.45 | 11.53 | -- | ||
Llama 3.1 405B | 128k | Offen | 9* | -- | -- | -- | -- | -- | ||
LFM2.5-8B-A1B | 32.8k | Offen | 8* | -- | 338 | 1.46 | 8.85 | 5.91 | ||
Ring-flash-2.0 | 131k | Offen | 8* | -- | -- | -- | -- | -- | ||
Olmo 3.1 32B Think | 65.5k | Offen | 8* | -- | -- | -- | -- | -- | ||
Command A | 288k | Offen | 8* | -- | 59 | 1.84 | 10.32 | -- | ||
Command A | 256k | Offen | 8* | -- | 43 | 3.12 | 14.77 | -- | ||
Llama 3.1 Nemotron 70B | 131k | Offen | 8* | -- | 116 | 6.63 | 10.95 | -- | ||
NVIDIA Nemotron 3 Nano (FP4) | 262k | Offen | 7* | -- | 245 | 4.43 | 6.46 | -- | ||
NVIDIA Nemotron 3 Nano | 262k | Offen | 7* | -- | 177 | 0.43 | 3.26 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Offen | 7* | -- | 181 | 3.91 | 6.68 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Offen | 7* | -- | 166 | 1.12 | 4.12 | -- | ||
Hermes 4 70B (FP8) | 128k | Offen | 7* | -- | 93 | 1.36 | 6.74 | -- | ||
Ministral 3 3B | 256k | Offen | 7 | $0.13 | 408 | 0.98 | 2.20 | -- | ||
Ministral 3 3B | 131k | Offen | 7 | $0.13 | 206 | 0.66 | 3.09 | -- | ||
Granite 4.1 8B | 131k | Offen | 7* | -- | 103 | 0.79 | 5.62 | -- | ||
Sarvam 30B (high) | 64k | Offen | 7* | -- | -- | -- | -- | -- | ||
Phi-4 Mini | 128k | Offen | 6 | $0.00 | 43 | 0.84 | 12.53 | -- | ||
Jamba 1.7 Large | 256k | Offen | 5* | -- | 55 | 1.42 | 10.49 | -- | ||
Granite 4.0 H Small | 128k | Offen | 5* | -- | 46 | 10.49 | 21.45 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | Offen | 5* | -- | 95 | 1.89 | 7.13 | -- | ||
Phi-4 | 16.4k | Offen | 5* | -- | -- | -- | -- | -- | ||
Phi-4 | 16.4k | Offen | 5* | -- | 72 | 0.88 | 7.84 | -- | ||
Nova Micro | 130k | Proprietär | 5* | -- | 282 | 0.86 | 2.63 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL | 128k | Offen | 5* | -- | 210 | 1.12 | 3.51 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | Offen | 5* | -- | 87 | 5.54 | 11.28 | -- | ||
Phi-4 Multimodal | 128k | Offen | 5* | -- | 18 | 0.81 | 29.09 | -- | ||
Reka Flash 3 | 54k | Offen | 4* | -- | -- | -- | -- | -- | ||
Llama 3.2 11B (Vision) | 131k | Offen | 3* | -- | 37 | 1.70 | 15.08 | -- | ||
Olmo 3 7B | 65.5k | Offen | 3* | -- | -- | -- | -- | -- | ||
Apertus 70B Instruct | 64k | Offen | 2* | -- | -- | -- | -- | -- | ||
LFM2.5-VL-1.6B | 32.8k | Offen | 1* | -- | 474 | 1.25 | 2.30 | -- | ||
Tiny Aya Global | 8.19k | Offen | 1* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | Offen | 1* | -- | -- | -- | -- | -- | ||
Claude Sonnet 5 (low) | 1M | Proprietär | -- | -- | 61 | 1.68 | 9.88 | -- | ||
Claude Sonnet 5 (xhigh) | 1M | Proprietär | -- | -- | 71 | 36.78 | 43.78 | -- | ||
Claude Sonnet 5 (high) | 1M | Proprietär | -- | -- | 68 | 10.56 | 17.96 | -- | ||
Cogito v2.1 | 164k | Offen | -- | -- | -- | -- | -- | -- | ||
Claude Sonnet 5 (medium) | 1M | Proprietär | -- | -- | 64 | 3.64 | 11.50 | -- | ||