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 Fable 5.1 (max with fallback) | 1M | Proprietär | 53 | $7.63 | 65 | 212.01 | 219.69 | -- | ||
Claude Fable 5.1 (xhigh with fallback) | 1M | Proprietär | 53 | $5.98 | 60 | 84.83 | 93.21 | -- | ||
GPT-6 Astra (max) | 1M | Proprietär | 53 | $3.26 | 59 | 312.96 | 321.44 | -- | ||
GPT-6 Astra (max) | 524k | Proprietär | 53 | $3.26 | 80 | 124.25 | 130.50 | -- | ||
GPT-6 Astra (xhigh) | 1M | Proprietär | 53 | $2.31 | 55 | 125.02 | 134.12 | -- | ||
Claude Fable 5.1 (high with fallback) | 1M | Proprietär | 51 | $3.91 | 55 | 14.87 | 23.98 | -- | ||
GPT-6 Astra (high) | 1M | Proprietär | 51 | $1.72 | 52 | 36.95 | 46.49 | -- | ||
Claude Opus 5 (max) | 1M | Proprietär | 51 | $5.86 | 53 | 49.85 | 59.31 | -- | ||
Claude Opus 5 (max) | 1M | Proprietär | 51 | $5.86 | 52 | 48.08 | 57.75 | -- | ||
Claude Opus 5 (max) | 1M | Proprietär | 51 | $9.38 | 52 | 49.63 | 59.21 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietär | 50 | $8.75 | 61 | 83.53 | 91.78 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietär | 50 | $9.66 | 59 | 92.67 | 101.17 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietär | 50 | $43.25 | 57 | 74.50 | 83.30 | -- | ||
GPT-6 Astra (medium) | 1M | Proprietär | 50 | $1.54 | 51 | 3.85 | 13.70 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietär | 50 | $4.88 | 53 | 26.77 | 36.19 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietär | 50 | $7.75 | 53 | 29.18 | 38.53 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietär | 50 | $4.88 | 52 | 40.54 | 50.20 | -- | ||
Claude Fable 5.1 (medium with fallback) | 1M | Proprietär | 49 | $2.98 | 54 | 8.69 | 18.01 | -- | ||
Claude Opus 5 (high) | 1M | Proprietär | 48 | $3.61 | 51 | 11.51 | 21.34 | -- | ||
Claude Opus 5 (high) | 1M | Proprietär | 48 | $5.64 | 53 | 12.35 | 21.78 | -- | ||
Claude Opus 5 (high) | 1M | Proprietär | 48 | $3.61 | 52 | 16.65 | 26.22 | -- | ||
Muse Spark 1.3 (max) | 1.05M | Proprietär | 48 | $1.60 | 230 | 22.41 | 33.28 | 8.70 | ||
GPT-5.6 Sol (max) | 1M | Proprietär | 47 | $3.70 | 110 | 84.25 | 88.81 | -- | ||
GPT-5.6 Sol (max) | 1M | Proprietär | 47 | $1.99 | 61 | 119.96 | 128.11 | -- | ||
GPT-5.6 Sol (max) | 524k | Proprietär | 47 | -- | 99 | 90.98 | 96.03 | -- | ||
Claude Fable 5.1 (low with fallback) | 1M | Proprietär | 47 | $2.37 | 53 | 4.71 | 14.15 | -- | ||
GPT-6 Astra (low) | 1M | Proprietär | 46 | $0.82 | 51 | 2.42 | 12.25 | -- | ||
Muse Spark 1.3 (xhigh) | 1.05M | Proprietär | 45 | $1.37 | 208 | 22.12 | 34.15 | 9.62 | ||
Claude Opus 5 (medium) | 1M | Proprietär | 45 | $2.19 | 51 | 3.83 | 13.59 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietär | 45 | $2.19 | 51 | 5.01 | 14.81 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietär | 45 | $3.32 | 52 | 4.46 | 14.02 | -- | ||
GLM-5.3 (max) | 1M | Offen | 45 | $2.01 | 72 | 3.08 | 37.74 | 27.72 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $2.16 | 138 | 1.05 | 19.19 | 14.51 | ||
GLM-5.3 (max) | 164k | Offen | 45 | $2.05 | 50 | 12.11 | 62.11 | 40.00 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $1.73 | 39 | 1.05 | 65.04 | 51.19 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $1.97 | 114 | 1.13 | 23.06 | 17.54 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $2.58 | 231 | 0.63 | 11.47 | 8.67 | ||
GLM-5.3 (max) (FAST) | 1M | Offen | 45 | $4.08 | 387 | 1.00 | 7.47 | 5.17 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $8.68 | 79 | 2.26 | 34.05 | 25.43 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $1.43 | 122 | 1.48 | 21.93 | 16.36 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $1.90 | 276 | 1.02 | 10.08 | 7.25 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $2.01 | 249 | 1.02 | 11.06 | 8.03 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $6.82 | 145 | 0.87 | 18.17 | 13.84 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $2.01 | 215 | 1.08 | 12.69 | 9.28 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $2.01 | 210 | 0.84 | 12.77 | 9.54 | ||
GLM-5.3 (max) (FAST) | 1M | Offen | 45 | $2.15 | 209 | 1.28 | 13.23 | 9.56 | ||
GLM-5.3 (max) (FP4) | 1M | Offen | 45 | $8.68 | 373 | 1.97 | 8.68 | 5.37 | ||
Grok 4.6 (high) | 500k | Proprietär | 44 | $1.86 | 57 | 38.63 | 47.46 | -- | ||
Grok 4.6 (xhigh) | 500k | Proprietär | 44 | $2.32 | 55 | 41.74 | 50.90 | -- | ||
GPT-5.6 Sol (xhigh) | 1M | Proprietär | 44 | $1.18 | 58 | 45.77 | 54.43 | -- | ||
GPT-5.6 Sol (xhigh) | 524k | Proprietär | 44 | $1.26 | 95 | 29.85 | 35.14 | -- | ||
Kimi K3 (max) | 1.05M | Offen | 44 | $1.81 | 129 | 0.81 | 20.13 | 15.46 | ||
Kimi K3 (max) | 1.05M | Offen | 44 | $4.34 | 46 | 0.87 | 54.80 | 43.15 | ||
Kimi K3 (max) | 1.05M | Offen | 44 | $2.25 | 38 | 1.24 | 67.14 | 52.72 | ||
Kimi K3 (max) | 1.05M | Offen | 44 | $2.01 | 95 | 0.78 | 26.99 | 20.97 | ||
Kimi K3 (max) | 1.05M | Offen | 44 | $2.42 | 48 | 1.21 | 53.16 | 41.56 | ||
Kimi K3 (max) | 1.05M | Offen | 44 | $1.21 | 50 | 3.29 | 53.61 | 40.25 | ||
Kimi K3 (max) | 1.05M | Offen | 44 | $9.22 | 186 | 1.57 | 15.01 | 10.76 | ||
Kimi K3 (max) | 205k | Offen | 44 | $1.85 | 161 | 0.94 | 16.43 | 12.40 | ||
Kimi K3 (max) | 262k | Offen | 44 | $2.70 | 90 | 1.65 | 29.42 | 22.22 | ||
Kimi K3 (max) (FAST) | 1.05M | Offen | 44 | $3.77 | 246 | 1.79 | 11.95 | 8.13 | ||
Kimi K3 (max) | 1.05M | Offen | 44 | $2.00 | 35 | 4.69 | 75.98 | 57.03 | ||
Kimi K3 (max) | 1.05M | Offen | 44 | $1.69 | 230 | 0.77 | 11.65 | 8.70 | ||
Kimi K3 (max) (FAST) | 1.05M | Offen | 44 | $2.81 | -- | -- | -- | -- | ||
Kimi K3 (max) (ULTRA) | 1.05M | Offen | 44 | $3.93 | -- | -- | -- | -- | ||
Grok 4.6 (medium) | 500k | Proprietär | 43 | $1.50 | 52 | 36.05 | 45.60 | -- | ||
GPT-5.6 Sol (high) | 1M | Proprietär | 42 | $0.81 | 57 | 10.99 | 19.75 | -- | ||
GPT-5.6 Sol (high) | 524k | Proprietär | 42 | $0.85 | 91 | 8.26 | 13.74 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietär | 42 | $1.40 | 111 | 156.82 | 161.31 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietär | 42 | $1.95 | 140 | 112.99 | 116.57 | -- | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.25 | 107 | 2.45 | 25.82 | 18.70 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.30 | 181 | 0.73 | 14.53 | 11.04 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.29 | 102 | 1.61 | 26.06 | 19.56 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.43 | 30 | 1.44 | 84.71 | 66.62 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.29 | 107 | 1.35 | 24.81 | 18.77 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.29 | 23 | 1.22 | 110.65 | 87.54 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.36 | 107 | 0.71 | 24.09 | 18.71 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.30 | 179 | 1.53 | 15.46 | 11.15 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.28 | 230 | 0.70 | 11.59 | 8.71 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.42 | 103 | 2.40 | 26.56 | 19.33 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.28 | 107 | 1.22 | 24.54 | 18.65 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.14 | 64 | 11.91 | 50.85 | 31.15 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.28 | 136 | 1.25 | 19.56 | 14.65 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $1.19 | 285 | 0.54 | 9.32 | 7.03 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.33 | 100 | 1.14 | 26.07 | 19.95 | ||
GLM-5.3-Flash (FAST) | 1M | Offen | 42 | $0.46 | 467 | 6.48 | 11.84 | 4.29 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.56 | 88 | 1.04 | 29.30 | 22.61 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.76 | 144 | 1.50 | 18.81 | 13.85 | ||
Gemini 3.8 Flash (high) AI Studio | 1M | Proprietär | 41 | $1.24 | 278 | 14.54 | 16.34 | -- | ||
Qwen3.8 Max | 1M | Proprietär | 40 | $2.67 | 41 | 2.74 | 64.16 | 49.14 | ||
Qwen3.8 2.4T A95B | 262k | Offen | 40 | $1.87 | 109 | 1.05 | 23.96 | 18.33 | ||
Qwen3.8 2.4T A95B | 262k | Offen | 40 | $2.77 | 179 | 0.90 | 14.89 | 11.20 | ||
Qwen3.8 2.4T A95B | 262k | Offen | 40 | $2.89 | 89 | 1.43 | 29.63 | 22.56 | ||
Qwen3.8 2.4T A95B | 262k | Offen | 40 | $1.80 | 60 | 2.05 | 43.39 | 33.07 | ||
Qwen3.8 2.4T A95B (FP8) | 262k | Offen | 40 | $1.54 | 105 | 3.53 | 27.31 | 19.02 | ||
Qwen3.8 2.4T A95B | 984k | Offen | 40 | $2.16 | 41 | 2.75 | 64.03 | 49.02 | ||
Gemini 3.8 Flash (medium) AI Studio | 1M | Proprietär | 40 | $0.93 | -- | -- | -- | -- | ||
Qwen3.8-Flash-Next | 1M | Offen | 40 | $0.37 | 52 | 2.72 | 51.19 | 38.77 | ||
Qwen3.8-Flash-Next (NVFP4) | 262k | Offen | 40 | $0.44 | 112 | 1.29 | 23.60 | 17.85 | ||
Muse Spark 1.2 (xhigh) | 1.05M | Proprietär | 40 | $0.97 | 178 | 18.48 | 32.54 | 11.25 | ||
Claude Opus 5 (low) | 1M | Proprietär | 40 | $1.10 | 53 | 2.54 | 11.97 | -- | ||
Claude Opus 5 (low) | 1M | Proprietär | 40 | $1.10 | 52 | 2.72 | 12.31 | -- | ||
Claude Opus 5 (low) | 1M | Proprietär | 40 | $1.57 | 51 | 3.31 | 13.13 | -- | ||
Gemini 3.7 Flash (medium) AI Studio | 1M | Proprietär | 40* | -- | 279 | 5.32 | 7.12 | -- | ||
DeepSeek V4.1 Flash (max) | 1M | Offen | 40 | $0.27 | 214 | 1.17 | 12.83 | 9.33 | ||
DeepSeek V4.1 Flash (max) | 1M | Offen | 40 | $0.19 | -- | -- | -- | -- | ||
DeepSeek V4.1 Flash (max) | 1.05M | Offen | 40 | $0.90 | -- | -- | -- | -- | ||
DeepSeek V4.1 Flash (max) | 1M | Offen | 40 | $2.18 | 316 | 0.65 | 8.57 | 6.34 | ||
DeepSeek V4.1 Flash (max) | 1M | Offen | 40 | $0.34 | 297 | 1.30 | 9.73 | 6.74 | ||
GPT-5.6 Sol (medium) | 1M | Proprietär | 39 | $0.50 | 58 | 3.42 | 12.10 | -- | ||
Gemini 3.7 Flash (high) AI Studio | 1M | Proprietär | 39 | $0.93 | 288 | 10.49 | 12.23 | -- | ||
Grok 4.5 (high) | 500k | Proprietär | 39 | $1.04 | 61 | 6.84 | 15.04 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietär | 38 | $7.36 | 73 | 180.27 | 187.12 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietär | 38 | $4.75 | 73 | 179.57 | 186.43 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietär | 38 | $5.09 | 80 | 212.41 | 218.66 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietär | 38 | $6.21 | 77 | 201.54 | 208.01 | -- | ||
GPT-5.6 Terra (xhigh) | 1M | Proprietär | 38 | $0.63 | 100 | 17.16 | 22.15 | -- | ||
GPT-5.6 Terra (xhigh) | 524k | Proprietär | 38 | $0.67 | 106 | 15.51 | 20.22 | -- | ||
GPT-5.6 Luna (max) | 1M | Proprietär | 38 | $0.18 | 118 | 119.93 | 124.18 | -- | ||
GPT-5.6 Luna (max) | 1M | Proprietär | 38 | $1.02 | 228 | 75.76 | 77.95 | -- | ||
Gemini 3.7 Flash (low) AI Studio | 1M | Proprietär | 37* | -- | 298 | 0.81 | 2.48 | -- | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $0.67 | 85 | 1.70 | 31.28 | 23.67 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $1.61 | 67 | 3.08 | 40.23 | 29.72 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $6.15 | 70 | 1.85 | 37.66 | 28.65 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Offen | 36 | $0.60 | 90 | 1.66 | 29.56 | 22.32 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Offen | 36 | $6.17 | 161 | 1.04 | 16.54 | 12.40 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $1.65 | 184 | 1.67 | 15.27 | 10.88 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Offen | 36 | $1.00 | 114 | 0.92 | 22.78 | 17.49 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $0.70 | 72 | 1.87 | 36.72 | 27.88 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $0.83 | 41 | 0.99 | 62.30 | 49.05 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $8.43 | 69 | 2.41 | 38.77 | 29.09 | ||
Agnes 3.0 Flash | 1M | Proprietär | 36* | -- | 236 | 1.84 | 12.44 | 8.48 | ||
Grok 4.6 (low) | 500k | Proprietär | 35 | $0.48 | 52 | 5.64 | 15.22 | -- | ||
Agnes 2.5 Pro Beta | 1M | Proprietär | 35* | -- | -- | -- | -- | -- | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietär | 35 | $0.31 | 213 | 1.30 | 13.03 | 9.38 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietär | 35 | $0.12 | 143 | 0.93 | 18.41 | 13.99 | ||
GPT-5.6 Luna (xhigh) | 1M | Proprietär | 35 | $0.09 | 118 | 49.03 | 53.28 | -- | ||
GPT-5.6 Luna (xhigh) | 524k | Proprietär | 35 | $0.09 | 120 | 50.36 | 54.52 | -- | ||
Claude Sonnet 5 (xhigh) | 1M | Proprietär | 35 | $2.87 | 66 | 24.85 | 32.45 | -- | ||
DeepSeek V4 Flash 0731 (max) | 262k | Offen | 35 | $0.38 | 145 | 1.63 | 18.85 | 13.78 | ||
DeepSeek V4 Flash 0731 (max) (FAST) | 1M | Offen | 35 | $0.90 | 143 | 0.80 | 18.31 | 14.01 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 35 | $0.65 | 307 | 2.09 | 10.23 | 6.51 | ||
DeepSeek V4 Flash 0731 (max) | 1M | Offen | 35 | $0.22 | 213 | 1.43 | 13.16 | 9.38 | ||
DeepSeek V4 Flash 0731 (max) | 1M | Offen | 35 | $0.10 | 131 | 1.49 | 20.53 | 15.23 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 35 | $0.41 | 187 | 1.48 | 14.85 | 10.70 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 35 | $0.09 | 256 | 0.62 | 10.39 | 7.81 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 35 | $0.85 | 86 | 2.48 | 31.41 | 23.14 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 35 | $0.44 | 269 | 0.58 | 9.86 | 7.43 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 35 | $0.19 | 318 | 0.98 | 8.85 | 6.29 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 35 | $0.58 | 157 | 2.75 | 18.65 | 12.71 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 35 | $0.26 | 205 | 1.71 | 13.89 | 9.75 | ||
DeepSeek V4 Flash 0731 (max) | 1M | Offen | 35 | $0.10 | 57 | 0.90 | 45.04 | 35.32 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Offen | 35 | $0.33 | 56 | 0.96 | 45.78 | 35.86 | ||
DeepSeek V4 Flash 0731 (max) | 1M | Offen | 35 | $0.42 | 126 | 0.85 | 20.73 | 15.91 | ||
GPT-5.6 Terra (high) | 1M | Proprietär | 34 | $0.34 | 92 | 2.26 | 7.68 | -- | ||
GPT-5.6 Terra (high) | 524k | Proprietär | 34 | $0.35 | 108 | 2.44 | 7.09 | -- | ||
Gemini 3.6 Flash AI Studio | 1M | Proprietär | 34 | $0.93 | 183 | 18.73 | 21.45 | -- | ||
GLM-5.2 (max) | 1M | Offen | 34 | $0.87 | 149 | 0.75 | 17.51 | 13.41 | ||
GLM-5.2 (max) (FAST) | 524k | Offen | 34 | $1.04 | 272 | 1.88 | 11.05 | 7.34 | ||
GLM-5.2 (max) (FP8) | 1.05M | Offen | 34 | $0.88 | 77 | 1.78 | 34.38 | 26.08 | ||
GLM-5.2 (max) (NVFP4) | 1M | Offen | 34 | -- | 187 | 1.14 | 14.50 | 10.69 | ||
GLM-5.2 (max) | 262k | Offen | 34 | $0.96 | 209 | 1.21 | 13.16 | 9.56 | ||
GLM-5.2 (max) | 1M | Offen | 34 | $2.31 | 88 | 1.07 | 29.55 | 22.78 | ||
GLM-5.2 (max) (FP4) | 1.05M | Offen | 34 | $0.65 | 64 | 1.04 | 40.01 | 31.17 | ||
GLM-5.2 (max) (FP4) | 432k | Offen | 34 | $2.94 | 340 | 1.07 | 8.42 | 5.88 | ||
GLM-5.2 (max) | 262k | Offen | 34 | $1.05 | 238 | 0.69 | 11.20 | 8.41 | ||
GLM-5.2 (max) | 262k | Offen | 34 | $4.37 | 96 | 1.67 | 27.78 | 20.89 | ||
GLM-5.2 (max) | 1M | Offen | 34 | $0.87 | 317 | 0.80 | 8.68 | 6.31 | ||
GLM-5.2 (max) (NVFP4) | 1M | Offen | 34 | $1.01 | 246 | 1.05 | 11.19 | 8.11 | ||
GLM-5.2 (max) | 1M | Offen | 34 | $0.33 | 52 | 2.44 | 50.08 | 38.11 | ||
GLM-5.2 (max) | 1M | Offen | 34 | $0.64 | 228 | 1.68 | 12.64 | 8.77 | ||
GLM-5.2 (max) (FP8) | 1.05M | Offen | 34 | -- | -- | -- | -- | -- | ||
GLM-5.2 (max) | 1.05M | Offen | 34 | $0.65 | 132 | 1.82 | 20.74 | 15.14 | ||
GLM-5.2 (max) | 164k | Offen | 34 | $0.88 | 212 | 1.51 | 13.31 | 9.44 | ||
GLM-5.2 (max) | 1M | Offen | 34 | $0.96 | 75 | 7.83 | 40.94 | 26.49 | ||
GLM-5.2 (max) | 1.05M | Offen | 34 | $0.76 | 172 | 0.96 | 15.47 | 11.61 | ||
GLM-5.2 (max) (FP8) | 1.05M | Offen | 34 | $0.85 | 101 | 2.19 | 26.99 | 19.84 | ||
Qwen3.8 27B (xhigh) | 262k | Offen | 34 | $0.65 | 35 | 1.02 | 72.49 | 57.18 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | Offen | 34 | $0.92 | 66 | 1.75 | 39.36 | 30.09 | ||
Qwen3.8 27B (xhigh) | 1M | Offen | 34 | $0.82 | 45 | 3.84 | 59.75 | 44.73 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | Offen | 34 | $2.29 | 84 | 1.32 | 31.23 | 23.93 | ||
Qwen3.8 27B (xhigh) | 262k | Offen | 34 | $1.98 | 197 | 0.89 | 13.59 | 10.16 | ||
GPT-5.6 Sol (low) | 1M | Proprietär | 34 | $0.26 | 55 | 3.08 | 12.11 | -- | ||
Gemini 3.8 Flash (low) AI Studio | 1M | Proprietär | 34 | -- | -- | -- | -- | -- | ||
Gemini 3.5 Flash (medium) | 1M | Proprietär | 34* | -- | 226 | 12.59 | 14.80 | -- | ||
GPT-5.3 Codex (xhigh) | 400k | Proprietär | 33* | -- | 123 | 41.96 | 46.04 | -- | ||
GPT-5.6 Luna (high) | 1M | Proprietär | 32 | $0.04 | 101 | 8.47 | 13.42 | -- | ||
GPT-5.6 Luna (high) | 524k | Proprietär | 32 | $0.05 | 119 | 12.26 | 16.47 | -- | ||
Claude Sonnet 5 (high) | 1M | Proprietär | 32 | $1.79 | 61 | 2.30 | 10.53 | -- | ||
DeepSeek V4 Pro (max) (FP4) | 1.05M | Offen | 31 | $1.19 | 52 | 1.09 | 94.64 | 83.95 | ||
DeepSeek V4 Pro (max) | 1M | Offen | 31 | $9.65 | 93 | 1.75 | 54.27 | 47.14 | ||
DeepSeek V4 Pro (max) | 1.05M | Offen | 31 | $1.09 | 77 | 1.86 | 64.80 | 56.48 | ||
DeepSeek V4 Pro (max) | 1M | Offen | 31 | $0.71 | 86 | 1.99 | 58.58 | 50.79 | ||
DeepSeek V4 Pro (max) (FP8) | 1.05M | Offen | 31 | -- | 52 | 2.20 | 95.22 | 83.47 | ||
DeepSeek V4 Pro (max) | 1.05M | Offen | 31 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) | 1M | Offen | 31 | $9.70 | 115 | 1.32 | 43.77 | 38.09 | ||
DeepSeek V4 Pro (max) | 1M | Offen | 31 | $3.73 | 141 | 0.56 | 35.23 | 31.12 | ||
DeepSeek V4 Pro (max) | 1M | Offen | 31 | $0.12 | 82 | 1.66 | 60.86 | 53.13 | ||
Kimi K3 (low) | 1.05M | Offen | 30 | $1.15 | 35 | 3.90 | 75.93 | 57.62 | ||
Kimi K3 (low) | 1M | Offen | 30 | $1.87 | 89 | 0.79 | 28.82 | 22.42 | ||
Kimi K3 (low) | 1M | Offen | 30 | $0.88 | 154 | 0.99 | 17.27 | 13.02 | ||
GPT-5.6 Terra (medium) | 1M | Proprietär | 30 | $0.18 | 96 | 1.77 | 6.96 | -- | ||
Apodex 1.1 | 256k | Proprietär | 30* | -- | -- | -- | -- | -- | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | Proprietär | 30 | $0.67 | 112 | 28.27 | 32.73 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | Proprietär | 30 | $0.98 | 126 | 24.56 | 28.52 | -- | ||
DeepSeek V4 Pro (high) (FP4) | 65.5k | Offen | 30* | -- | 56 | 1.47 | 45.88 | 35.50 | ||
DeepSeek V4 Pro (high) | 1M | Offen | 30* | -- | 88 | 1.61 | 29.81 | 22.54 | ||
DeepSeek V4 Pro (high) | 1M | Offen | 30* | -- | 88 | 1.75 | 30.00 | 22.58 | ||
DeepSeek V4 Pro (high) | 1M | Offen | 30* | -- | 79 | 2.11 | 33.47 | 25.07 | ||
DeepSeek V4 Pro (high) (FP8) | 1.05M | Offen | 30* | -- | 51 | 2.01 | 51.04 | 39.19 | ||
DeepSeek V4 Pro (high) | 1M | Offen | 30* | -- | 119 | 1.30 | 22.17 | 16.69 | ||
DeepSeek V4 Pro (high) | 1.05M | Offen | 30* | -- | 76 | 1.75 | 34.33 | 26.04 | ||
DeepSeek V4 Pro (high) | 1M | Offen | 30* | -- | 144 | 0.57 | 17.86 | 13.82 | ||
MiniMax-M3 (MXFP8) | 1M | Offen | 30 | $0.46 | 129 | 0.93 | 20.25 | 15.45 | ||
MiniMax-M3 (NVFP4) | 262k | Offen | 30 | $0.40 | 169 | 1.20 | 16.00 | 11.85 | ||
MiniMax-M3 | 1M | Offen | 30 | $0.70 | 105 | 0.74 | 24.49 | 19.00 | ||
MiniMax-M3 | 1M | Offen | 30 | $0.46 | 147 | 1.13 | 18.14 | 13.61 | ||
MiniMax-M3 (FAST) | 1.05M | Offen | 30 | $1.09 | 426 | 1.59 | 7.45 | 4.69 | ||
MiniMax-M3 | 1M | Offen | 30 | $0.46 | 197 | 0.61 | 13.31 | 10.16 | ||
MiniMax-M3 (FP8) | 1.05M | Offen | 30 | $1.91 | 315 | 1.85 | 9.78 | 6.35 | ||
MiniMax-M3 (FP8) | 1M | Offen | 30 | $0.45 | 130 | 1.26 | 20.51 | 15.39 | ||
MiniMax-M3 | 524k | Offen | 30 | $0.64 | 163 | 2.80 | 18.11 | 12.25 | ||
MiniMax-M3 | 512k | Offen | 30 | $0.51 | 103 | 1.32 | 25.61 | 19.43 | ||
MiniMax-M3 | 524k | Offen | 30 | $0.44 | 24 | 0.97 | 104.31 | 82.67 | ||
MiniMax-M3 | 1.05M | Offen | 30 | -- | -- | -- | -- | -- | ||
MiniMax-M3 | 1.05M | Offen | 30 | $3.83 | 247 | 2.48 | 12.60 | 8.10 | ||
MiniMax-M3 | 524k | Offen | 30 | $0.50 | 175 | 0.96 | 15.26 | 11.44 | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietär | 29* | -- | 61 | 0.68 | 8.82 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietär | 29* | -- | 60 | 1.70 | 9.97 | -- | ||
Claude Sonnet 5 (medium) | 1M | Proprietär | 28 | $1.00 | 59 | 1.18 | 9.66 | -- | ||
GPT-5.6 Sol (Non-reasoning) | 1M | Proprietär | 28* | -- | 60 | 1.18 | 9.54 | -- | ||
GPT-5.6 Sol (Non-reasoning) | 1M | Proprietär | 28* | -- | 97 | 0.81 | 5.97 | -- | ||
Nex-N2-Pro (FP8) | 262k | Offen | 28* | -- | -- | -- | -- | -- | ||
Solar Pro 4 | 512k | Proprietär | 28* | -- | 74 | 1.99 | 35.61 | 26.90 | ||
GPT-5.6 Terra (low) | 1M | Proprietär | 28 | $0.14 | 93 | 1.58 | 6.95 | -- | ||
Qwen3.8 27B (medium) | 1M | Offen | 28 | $0.90 | 51 | 3.94 | 52.70 | 39.01 | ||
Qwen3.8 27B (medium) | 262k | Offen | 28 | $2.36 | 193 | 0.98 | 13.93 | 10.36 | ||
Agnes 2.5 Pro Alpha | 1M | Offen | 28 | -- | 172 | 4.02 | 18.55 | 11.63 | ||
Quasar 438B (max) | 1M | Proprietär | 27 | $2.02 | 174 | 1.00 | 15.37 | 11.49 | ||
GPT-5.5 Instant (June 2026) | 400k | Proprietär | 27 | $0.69 | 130 | 1.19 | 20.41 | 15.38 | ||
Qwen3.8 27B (low) | 1M | Offen | 26 | $0.83 | 50 | 4.04 | 54.34 | 40.24 | ||
Qwen3.8 27B (low) | 262k | Offen | 26 | $2.19 | 197 | 0.90 | 13.60 | 10.15 | ||
MiMo-V2.5-Pro | 1.05M | Offen | 26 | $0.07 | 38 | 4.29 | 70.89 | 53.28 | ||
MiMo-V2.5-Pro | 1.05M | Offen | 26 | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | Offen | 26 | $0.43 | 36 | 1.11 | 70.05 | 55.15 | ||
MiMo-V2.5-Pro | 1M | Offen | 26 | $0.05 | 39 | 6.14 | 70.14 | 51.20 | ||
Kimi K2.7 Code (FP4) | 256k | Offen | 26 | $1.89 | 221 | 1.80 | 14.17 | 10.10 | ||
Kimi K2.7 Code (FP8) | 65.5k | Offen | 26 | $1.20 | 58 | 5.16 | 51.94 | 38.22 | ||
Kimi K2.7 Code | 262k | Offen | 26 | $0.89 | 272 | 1.13 | 11.18 | 8.21 | ||
Kimi K2.7 Code | 262k | Offen | 26 | $0.76 | 222 | 0.48 | 12.76 | 10.03 | ||
Kimi K2.7 Code | 262k | Offen | 26 | $1.69 | 203 | 0.65 | 14.09 | 10.98 | ||
Kimi K2.7 Code | 262k | Offen | 26 | $0.55 | 53 | 3.74 | 55.69 | 42.43 | ||
Kimi K2.7 Code | 262k | Offen | 26 | $0.39 | 41 | 1.08 | 67.39 | 54.16 | ||
Kimi K2.7 Code | 262k | Offen | 26 | $0.52 | 122 | 0.69 | 23.10 | 18.31 | ||
Kimi K2.7 Code | 256k | Offen | 26 | $0.54 | 49 | 2.88 | 59.07 | 45.89 | ||
Inkling Small | 256k | Offen | 26 | $0.09 | 178 | 2.13 | 16.17 | 11.24 | ||
Inkling Small | 524k | Offen | 26 | $0.12 | 244 | 0.98 | 11.24 | 8.21 | ||
Inkling Small | 262k | Offen | 26 | $0.12 | 323 | 0.46 | 8.19 | 6.18 | ||
Qwen3.7 Plus | 1M | Proprietär | 26 | $0.33 | 66 | 2.21 | 39.97 | 30.21 | ||
Hy3 (FP8) | 256k | Offen | 26 | $0.07 | 96 | 2.93 | 28.94 | 20.81 | ||
Hy3 | 262k | Offen | 26 | $0.07 | 88 | 2.23 | 30.61 | 22.70 | ||
Hy3 (FP8) | 262k | Offen | 26 | $0.07 | 60 | 1.09 | 42.57 | 33.19 | ||
Hy3 | 262k | Offen | 26 | $0.07 | 100 | 2.99 | 27.90 | 19.92 | ||
Inkling (FP8) | 131k | Offen | 26 | $0.81 | 204 | 0.57 | 12.83 | 9.81 | ||
Inkling | 262k | Offen | 26 | $0.72 | 208 | 0.64 | 12.64 | 9.60 | ||
Inkling | 524k | Offen | 26 | $0.91 | 114 | 0.63 | 22.59 | 17.57 | ||
Inkling | 262k | Offen | 26 | $0.61 | 91 | 2.89 | 30.29 | 21.92 | ||
Inkling | 1M | Offen | 26 | $0.61 | 212 | 0.99 | 12.80 | 9.45 | ||
GPT-5.6 Luna (medium) | 1M | Proprietär | 25 | $0.02 | 107 | 2.62 | 7.27 | -- | ||
Ling 3.0 Flash | 131k | Offen | 25* | -- | 61 | 0.63 | 41.39 | 32.61 | ||
Ling 3.0 Flash | 262k | Offen | 25* | -- | 313 | 2.62 | 10.61 | 6.40 | ||
Grok 4.3 (medium) | 524k | Proprietär | 25* | -- | 282 | 3.87 | 5.64 | -- | ||
Grok 4.3 (medium) | 200k | Proprietär | 25* | -- | 174 | 9.13 | 12.00 | -- | ||
Grok 4.3 (medium) | 1M | Proprietär | 25* | -- | 109 | 11.36 | 15.95 | -- | ||
Ling-3.0-flash-VL | 262k | Offen | 25 | -- | 145 | 2.37 | 19.63 | 13.80 | ||
Claude Sonnet 5 (low) | 1M | Proprietär | 25 | $0.51 | 57 | 0.92 | 9.74 | -- | ||
Grok 4.3 (low) | 524k | Proprietär | 24* | -- | 259 | 2.58 | 4.51 | -- | ||
Grok 4.3 (low) | 200k | Proprietär | 24* | -- | 157 | 4.20 | 7.38 | -- | ||
Grok 4.3 (low) | 1M | Proprietär | 24* | -- | 112 | 4.87 | 9.34 | -- | ||
Gemini 3.5 Flash (minimal) AI Studio | 1M | Proprietär | 24* | -- | 203 | 0.84 | 3.30 | -- | ||
Nemotron 3 Ultra | 262k | Offen | 23 | $0.19 | 302 | 1.00 | 10.20 | 7.54 | ||
Nemotron 3 Ultra | 262k | Offen | 23 | -- | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Offen | 23 | $0.47 | 143 | 3.48 | 22.89 | 15.92 | ||
Nemotron 3 Ultra BF16 | 262k | Offen | 23 | $0.92 | 144 | 3.04 | 22.28 | 15.77 | ||
Nemotron 3 Ultra | 256k | Offen | 23 | $1.16 | 319 | 2.38 | 11.07 | 7.13 | ||
Nemotron 3 Ultra | 262k | Offen | 23 | $0.48 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Offen | 23 | $0.37 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Offen | 23 | $0.22 | 171 | 0.65 | 16.90 | 13.33 | ||
Claude Sonnet 4.6 (Non-reasoning, low) | 1M | Proprietär | 23* | -- | 42 | 1.33 | 13.18 | -- | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | Proprietär | 23 | $0.12 | 362 | 8.28 | 9.66 | -- | ||
GLM-5.2 (Non-reasoning) (FAST) | 524k | Offen | 22* | -- | 248 | 1.60 | 3.61 | -- | ||
GLM-5.2 (Non-reasoning) (FP4) | 432k | Offen | 22* | -- | 256 | 1.04 | 2.99 | -- | ||
GLM-5.2 (Non-reasoning) | 262k | Offen | 22* | -- | 92 | 1.70 | 7.14 | -- | ||
GLM-5.2 (Non-reasoning) | 1M | Offen | 22* | -- | 59 | 2.47 | 10.98 | -- | ||
GLM-5.2 (Non-reasoning) (FP8) | 1.05M | Offen | 22* | -- | 90 | 2.11 | 7.64 | -- | ||
GLM-5.2 (Non-reasoning) | 164k | Offen | 22* | -- | 176 | 1.42 | 4.27 | -- | ||
GLM-5.2 (Non-reasoning) | 1.05M | Offen | 22* | -- | 119 | 1.63 | 5.84 | -- | ||
GLM-5.2 (Non-reasoning) | 1M | Offen | 22* | -- | 274 | 0.85 | 2.67 | -- | ||
Qwen3.8 27B | 1M | Offen | 22* | -- | 50 | 4.01 | 13.95 | -- | ||
Qwen3.8 27B | 262k | Offen | 22* | -- | 218 | 0.94 | 3.23 | -- | ||
MiMo-V2.5 | 1.05M | Offen | 22 | $0.02 | 46 | 4.34 | 58.59 | 43.40 | ||
MiMo-V2.5 | 262k | Offen | 22 | $0.02 | 29 | 1.52 | 87.25 | 68.58 | ||
MiMo-V2.5 | 1.05M | Offen | 22 | $0.04 | -- | -- | -- | -- | ||
MiMo-V2.5 | 1M | Offen | 22 | $0.02 | 44 | 6.11 | 63.32 | 45.77 | ||
GPT-5.6 Terra (Non-reasoning) | 1M | Proprietär | 22* | -- | 92 | 0.87 | 6.33 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 1M | Proprietär | 22* | -- | 124 | 0.75 | 4.79 | -- | ||
Qwen3.6 27B FP8 | 262k | Offen | 22 | $0.37 | 67 | 0.96 | 93.60 | 85.14 | ||
Qwen3.6 27B | 131k | Offen | 22 | $0.60 | 444 | 1.22 | 15.12 | 12.77 | ||
Qwen3.6 27B | 262k | Offen | 22 | $0.62 | 58 | 2.95 | 110.09 | 98.46 | ||
Qwen3.6 27B | 262k | Offen | 22 | $0.62 | 57 | 3.66 | 112.46 | 99.99 | ||
Qwen3.6 27B (FP8) | 262k | Offen | 22 | $0.36 | 44 | 3.36 | 145.06 | 130.23 | ||
G9v3-39A5B | 131k | Offen | 22* | -- | -- | -- | -- | -- | ||
KAT-Coder-Pro V2 | 256k | Proprietär | 22* | -- | -- | -- | -- | -- | ||
GPT-5.6 Luna (low) | 1M | Proprietär | 22 | $0.01 | 98 | 2.20 | 7.32 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | Offen | 21* | -- | 84 | 2.03 | 7.96 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) (FP8) | 262k | Offen | 21* | -- | 42 | 0.94 | 12.90 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | Offen | 21* | -- | 86 | 2.14 | 7.93 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) (Base, FP4) | 262k | Offen | 21* | -- | 140 | 2.05 | 5.63 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | Offen | 21* | -- | 14 | 1.76 | 37.42 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | Offen | 21* | -- | 84 | 1.57 | 7.55 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1M | Offen | 21* | -- | 84 | 1.79 | 7.73 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1M | Offen | 21* | -- | 78 | 1.94 | 8.36 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1.05M | Offen | 21* | -- | 109 | 1.31 | 5.92 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1M | Offen | 21* | -- | 137 | 0.62 | 4.27 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1M | Offen | 21* | -- | 86 | 1.57 | 7.35 | -- | ||
Qwen3.5 Omni Plus | 256k | Proprietär | 20* | -- | 96 | 2.14 | 7.37 | -- | ||
o3 | 200k | Proprietär | 20* | -- | 103 | 25.55 | 30.40 | -- | ||
o3 | 200k | Proprietär | 20* | -- | -- | -- | -- | -- | ||
o3 | 200k | Proprietär | 20* | -- | 140 | 4.14 | 7.72 | -- | ||
Qwen3.6 27B (Non-reasoning) | 131k | Offen | 20* | -- | 452 | 1.19 | 2.29 | -- | ||
Qwen3.6 27B (Non-reasoning) (FP8) | 262k | Offen | 20* | -- | 71 | 1.82 | 8.89 | -- | ||
Qwen3.6 27B (Non-reasoning) FP8 | 262k | Offen | 20* | -- | 61 | 0.92 | 9.08 | -- | ||
Qwen3.6 27B (Non-reasoning) | 262k | Offen | 20* | -- | 58 | 3.63 | 12.32 | -- | ||
Qwen3.6 27B (Non-reasoning) | 262k | Offen | 20* | -- | 60 | 2.99 | 11.39 | -- | ||
LongCat 2.0 | 1M | Offen | 20 | $0.06 | -- | -- | -- | -- | ||
LongCat 2.0 (FP8) | 262k | Offen | 20 | $0.15 | 55 | 2.98 | 48.22 | 36.19 | ||
Step 3.7 Flash | 256k | Offen | 19* | -- | 113 | 2.67 | 24.80 | 17.71 | ||
Step 3.7 Flash | 256k | Offen | 19* | -- | 168 | 0.66 | 15.52 | 11.89 | ||
Qwen3.5 397B A17B | 262k | Offen | 19 | $0.47 | 84 | 2.24 | 45.96 | 37.79 | ||
Qwen3.5 397B A17B | 262k | Offen | 19 | $0.34 | 85 | 2.15 | 45.65 | 37.60 | ||
Qwen3.5 397B A17B | 262k | Offen | 19 | $0.30 | 52 | 0.96 | 71.67 | 61.12 | ||
Qwen3.5 397B A17B (FP8) | 262k | Offen | 19 | $0.31 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (FP8) | 262k | Offen | 19 | $0.23 | 40 | 0.96 | 93.90 | 80.33 | ||
Qwen3.5 397B A17B | 262k | Offen | 19 | $0.17 | 14 | 1.31 | 256.54 | 220.60 | ||
Qwen3.5 397B A17B (FP8) | 262k | Offen | 19 | $0.47 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Offen | 19 | $0.47 | 139 | 2.06 | 28.64 | 22.97 | ||
Qwen3.5 397B A17B | 262k | Offen | 19 | $0.47 | 83 | 1.64 | 45.79 | 38.16 | ||
DeepSeek V4 Flash (Non-reasoning) | 1.05M | Offen | 19* | -- | -- | -- | -- | -- | ||
DeepSeek V4 Flash (Non-reasoning) | 1M | Offen | 19* | -- | 121 | 0.74 | 4.86 | -- | ||
DeepSeek V4 Flash (Non-reasoning) | 1M | Offen | 19* | -- | 77 | 1.55 | 8.02 | -- | ||
Qwen3.6 35B A3B | 229k | Offen | 19 | $0.48 | 123 | 2.07 | 50.01 | 43.87 | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 19 | $0.27 | 111 | 2.20 | 55.32 | 48.62 | ||
Qwen3.6 35B A3B | 262k | Offen | 19 | $0.37 | 115 | 0.99 | 52.47 | 47.12 | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 19 | $0.14 | 100 | 0.70 | 59.84 | 54.12 | ||
Qwen3.6 35B A3B FP8 | 262k | Offen | 19 | $0.31 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | Offen | 19 | $0.12 | 124 | 0.82 | 48.21 | 43.38 | ||
Qwen3.6 35B A3B | 205k | Offen | 19 | $0.31 | 124 | 1.35 | 48.71 | 43.34 | ||
MiMo-V2.5-Pro (Non-reasoning) | 1.05M | Offen | 18* | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro (Non-reasoning) | 65.5k | Offen | 18* | -- | 30 | 1.09 | 17.86 | -- | ||
MiMo-V2.5-Pro (Non-reasoning) | 131k | Offen | 18* | -- | 36 | 6.73 | 20.64 | -- | ||
MiMo-V2.5-Pro (Non-reasoning) | 1.05M | Offen | 18* | -- | 37 | 5.55 | 18.97 | -- | ||
Muse Glimmer (high) | 131k | Offen | 18 | $0.09 | 91 | 0.80 | 28.16 | 21.88 | ||
Muse Glimmer (high) | 131k | Offen | 18 | $0.05 | 145 | 0.94 | 18.20 | 13.81 | ||
Muse Glimmer (high) | 131k | Offen | 18 | $0.06 | 61 | 1.12 | 42.07 | 32.76 | ||
Qwen3.5 122B A10B (Non-reasoning) (FP4) | 262k | Offen | 18* | -- | 143 | 0.89 | 4.38 | -- | ||
Qwen3.5 122B A10B (Non-reasoning) | 262k | Offen | 18* | -- | 136 | 2.43 | 6.12 | -- | ||
Claude 4.5 Haiku | 200k | Proprietär | 18 | $0.20 | 104 | 8.64 | 13.44 | -- | ||
Claude 4.5 Haiku Vertex | 200k | Proprietär | 18 | $0.24 | 107 | 16.36 | 21.03 | -- | ||
Claude 4.5 Haiku | 200k | Proprietär | 18 | $0.21 | 85 | 15.75 | 21.66 | -- | ||
Claude 4.5 Haiku | 200k | Proprietär | 18 | $0.57 | 85 | 27.56 | 33.43 | -- | ||
Ring-2.6-1T | 262k | Offen | 17 | $0.29 | 127 | 3.86 | 23.62 | 15.81 | ||
GPT-5.6 Luna (Non-reasoning) | 1M | Proprietär | 17* | -- | 107 | 0.90 | 5.58 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 1M | Proprietär | 17* | -- | 205 | 0.76 | 3.20 | -- | ||
Gemma 4 26B A4B | 1M | Offen | 17* | -- | 85 | 1.29 | 30.70 | 23.53 | ||
Gemma 4 26B A4B | 262k | Offen | 17* | -- | 107 | 1.57 | 24.97 | 18.71 | ||
Gemma 4 26B A4B AI Studio | 262k | Offen | 17* | -- | 46 | 1.03 | 54.99 | 43.17 | ||
Gemma 4 26B A4B | 256k | Offen | 17* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | Offen | 17* | -- | 28 | 0.87 | 88.96 | 70.47 | ||
Gemma 4 26B A4B | 256k | Offen | 17* | -- | 23 | 1.85 | 109.65 | 86.24 | ||
Gemma 4 26B A4B (FP8) | 1.05M | Offen | 17* | -- | -- | -- | -- | -- | ||
Qwen3.5 122B A10B (FP8) | 262k | Offen | 16 | $0.21 | 94 | 1.93 | 28.42 | 21.19 | ||
Qwen3.5 122B A10B (FP4) | 262k | Offen | 16 | $0.14 | 152 | 0.79 | 17.27 | 13.18 | ||
Qwen3.5 122B A10B | 262k | Offen | 16 | $0.32 | 127 | 2.33 | 21.97 | 15.71 | ||
Qwen3.5 122B A10B (FP8) | 262k | Offen | 16 | $0.32 | -- | -- | -- | -- | ||
Qwen3.5 122B A10B | 262k | Offen | 16 | $0.32 | 113 | 1.91 | 24.05 | 17.71 | ||
Gemma 4 31B | 262k | Offen | 15 | $0.07 | 64 | 2.23 | 37.37 | 27.29 | ||
Gemma 4 31B (NVFP4) | 262k | Offen | 15 | -- | 283 | 0.52 | 8.43 | 6.14 | ||
Gemma 4 31B (FP8) | 262k | Offen | 15 | $0.10 | -- | -- | -- | -- | ||
Gemma 4 31B | 262k | Offen | 15 | $0.10 | -- | -- | -- | -- | ||
Gemma 4 31B | 131k | Offen | 15 | $0.71 | -- | -- | -- | -- | ||
Gemma 4 31B (AI Studio) | 262k | Offen | 15 | $0.00 | 35 | 1.07 | 64.95 | 49.59 | ||
Gemma 4 31B | 262k | Offen | 15 | $0.05 | 27 | 2.10 | 84.17 | 63.72 | ||
Gemma 4 31B | 262k | Offen | 15 | $0.02 | 15 | 2.10 | 146.82 | 112.36 | ||
Gemma 4 31B | 262k | Offen | 15 | $0.10 | 20 | 1.86 | 113.06 | 86.33 | ||
Gemma 4 31B (FP8) | 262k | Offen | 15 | $0.10 | 52 | 3.62 | 46.39 | 33.21 | ||
Gemma 4 31B | 131k | Offen | 15 | $0.28 | 198 | 3.00 | 14.31 | 8.78 | ||
Gemma 4 31B | 256k | Offen | 15 | $0.10 | 97 | 1.97 | 24.97 | 17.86 | ||
Gemma 4 31B | 131k | Offen | 15 | $0.10 | -- | -- | -- | -- | ||
Gemma 4 31B (FP8) | 262k | Offen | 15 | $0.29 | 26 | 1.52 | 88.40 | 67.45 | ||
Claude 4.5 Haiku (Non-reasoning) | 200k | Proprietär | 15* | -- | 79 | 1.27 | 7.64 | -- | ||
Claude 4.5 Haiku (Non-reasoning) | 200k | Proprietär | 15* | -- | 101 | 0.83 | 5.78 | -- | ||
Claude 4.5 Haiku (Non-reasoning) | 200k | Proprietär | 15* | -- | 79 | 0.73 | 7.06 | -- | ||
Claude 4.5 Haiku (Non-reasoning) Vertex | 200k | Proprietär | 15* | -- | 85 | 0.87 | 6.75 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) | 262k | Offen | 15* | -- | 140 | 1.00 | 4.56 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) (FP8) | 262k | Offen | 15* | -- | 118 | 0.69 | 4.91 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) | 205k | Offen | 15* | -- | 140 | 1.39 | 4.96 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) FP8 | 262k | Offen | 15* | -- | -- | -- | -- | -- | ||
Qwen3.6 35B A3B (Non-reasoning) (FP8) | 262k | Offen | 15* | -- | 119 | 0.87 | 5.06 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) | 262k | Offen | 15* | -- | 134 | 2.06 | 5.78 | -- | ||
Qwen3.5 35B A3B (Non-reasoning) FP8 | 262k | Offen | 15* | -- | 154 | 0.72 | 3.97 | -- | ||
Qwen3.5 35B A3B (Non-reasoning) | 262k | Offen | 15* | -- | 165 | 2.08 | 5.12 | -- | ||
Qwen3.5 35B A3B (Non-reasoning) (FP8) | 262k | Offen | 15* | -- | 229 | 1.01 | 3.19 | -- | ||
Mistral Medium 3.5 | 262k | Offen | 15 | $0.44 | 147 | 2.25 | 19.26 | 13.61 | ||
Granite 4.2 30B | 131k | Offen | 15* | -- | 77 | 0.81 | 33.17 | 25.89 | ||
Grok 4.3 (Non-reasoning) | 524k | Proprietär | 15 | $0.28 | 242 | 0.65 | 2.72 | -- | ||
Grok 4.3 (Non-reasoning) | 1M | Proprietär | 15 | $0.14 | 112 | 0.74 | 5.23 | -- | ||
Gemma 4 12B | 262k | Offen | 14* | -- | 108 | 2.42 | 25.63 | 18.57 | ||
Nova 2.0 Pro Preview (medium) | 256k | Proprietär | 14* | -- | 115 | 12.43 | 34.26 | 17.46 | ||
Command A+ | 200k | Offen | 14 | $0.00 | 240 | 0.38 | 10.81 | 8.34 | ||
Gemma 4 31B (Non-reasoning) (NVFP4) | 262k | Offen | 14* | -- | 194 | 0.43 | 3.01 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Offen | 14* | -- | 33 | 1.42 | 16.39 | -- | ||
Gemma 4 31B (Non-reasoning) | 131k | Offen | 14* | -- | -- | -- | -- | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Offen | 14* | -- | 106 | 2.07 | 6.80 | -- | ||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | Offen | 14* | -- | 15 | 1.44 | 35.40 | -- | ||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | Offen | 14* | -- | 47 | 3.45 | 14.14 | -- | ||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | Offen | 14* | -- | 25 | 1.45 | 21.12 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Offen | 14* | -- | 56 | 2.10 | 11.10 | -- | ||
Gemma 4 31B (Non-reasoning) | 131k | Offen | 14* | -- | 201 | 2.93 | 5.42 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Offen | 14* | -- | 17 | 1.11 | 30.09 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Offen | 14* | -- | 16 | 1.76 | 33.55 | -- | ||
Qwen3.5 9B (FP8) | 262k | Offen | 14* | -- | 65 | 2.38 | 41.00 | 30.90 | ||
Qwen3.5 9B (FP8) | 262k | Offen | 14* | -- | 94 | 0.79 | 27.53 | 21.39 | ||
Nova 2.0 Omni (medium) | 1M | Proprietär | 14* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (medium) | 1M | Proprietär | 14* | -- | -- | -- | -- | -- | ||
Nemotron 3.5 Lightning (NVFP4) | 262k | Offen | 14 | $0.12 | -- | -- | -- | -- | ||
Nemotron 3.5 Lightning (BF16) | 1.05M | Offen | 14 | $0.09 | 266 | 1.11 | 10.50 | 7.51 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Offen | 14 | $0.10 | 288 | 0.55 | 9.22 | 6.94 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Offen | 14 | $0.12 | 257 | 13.10 | 22.82 | 7.78 | ||
Nemotron 3.5 Lightning (BF16) | 65.5k | Offen | 14 | $0.00 | 294 | 1.45 | 9.94 | 6.80 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Offen | 14 | $0.02 | 492 | 0.47 | 5.55 | 4.06 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Offen | 14 | $0.08 | 306 | 0.43 | 8.60 | 6.53 | ||
Nemotron 3 Super | 256k | Offen | 14 | $1.64 | 376 | 1.82 | 8.47 | 5.32 | ||
Nemotron 3 Super | 262k | Offen | 14 | $0.48 | 83 | 14.99 | 44.94 | 23.96 | ||
Apriel-v1.6-15B-Thinker | 131k | Offen | 13* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietär | 13* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietär | 13* | -- | 176 | 14.98 | 29.19 | 11.38 | ||
Qwen3.5 9B (Non-reasoning) (FP8) | 262k | Offen | 13* | -- | 94 | 0.77 | 6.08 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 1M | Offen | 13* | -- | 76 | 1.42 | 8.00 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 262k | Offen | 13* | -- | 19 | 1.57 | 27.76 | -- | ||
Gemma 4 26B A4B (Non-reasoning) (FP8) | 1.05M | Offen | 13* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (Non-reasoning) (FP8) | 262k | Offen | 13* | -- | 49 | 2.56 | 12.70 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 262k | Offen | 13* | -- | 171 | 0.90 | 3.83 | -- | ||
Gemma 4 26B A4B (Non-reasoning) (FP8) | 262k | Offen | 13* | -- | 23 | 0.82 | 22.76 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 262k | Offen | 13* | -- | 37 | 1.26 | 14.89 | -- | ||
Qwen3.5 4B (FP8) | 262k | Offen | 13* | -- | 32 | 0.70 | 78.65 | 62.36 | ||
North Mini Code | 256k | Offen | 13* | -- | 84 | 0.40 | 30.21 | 23.85 | ||
Nova 2.0 Pro Preview (low) | 256k | Proprietär | 13* | -- | 114 | 10.88 | 32.87 | 17.59 | ||
Nova 2.0 Lite (medium) | 1M | Proprietär | 12* | -- | 166 | 10.55 | 25.58 | 12.02 | ||
Qwen3.5 Omni Flash | 256k | Proprietär | 12* | -- | 221 | 1.90 | 4.16 | -- | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.08 | 474 | 0.72 | 5.99 | 4.22 | ||
gpt-oss-120b (high) | 116k | Offen | 12 | $0.23 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | Offen | 12 | $0.12 | 118 | 1.29 | 22.51 | 16.97 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.02 | 51 | 1.36 | 50.30 | 39.15 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.11 | 313 | 0.75 | 8.73 | 6.38 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.04 | 105 | 1.17 | 25.03 | 19.09 | ||
gpt-oss-120b (high) (Turbo) | 131k | Offen | 12 | $0.11 | 222 | 0.76 | 12.03 | 9.02 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.04 | 269 | 0.37 | 9.66 | 7.44 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.03 | 49 | 0.62 | 52.01 | 41.12 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.23 | 1,765 | 0.55 | 1.97 | 1.13 | ||
gpt-oss-120b (high) Vertex | 131k | Offen | 12 | $0.06 | 218 | 0.41 | 11.87 | 9.17 | ||
gpt-oss-120b (high) | 128k | Offen | 12 | $0.07 | 285 | 0.24 | 9.02 | 7.02 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.15 | 700 | 0.97 | 4.54 | 2.86 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.06 | 169 | 0.75 | 15.55 | 11.84 | ||
gpt-oss-120b (high) (Base) | 128k | Offen | 12 | $0.11 | 302 | 1.02 | 9.30 | 6.62 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.19 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.11 | 68 | 0.94 | 37.72 | 29.42 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.11 | 185 | 0.48 | 14.02 | 10.83 | ||
Ling 3.0 Tiny | 262k | Offen | 12 | $0.00 | 171 | 2.71 | 17.35 | 11.71 | ||
Granite 4.2 8B | 131k | Offen | 12 | $0.06 | 105 | 0.75 | 24.66 | 19.13 | ||
Granite 4.2 8B | 131k | Offen | 12 | $0.02 | 76 | 0.61 | 33.54 | 26.34 | ||
Nova 2.0 Lite (low) | 1M | Proprietär | 12* | -- | 168 | 8.28 | 23.18 | 11.93 | ||
HyperNova 60B 2605 (high) | 131k | Offen | 12* | -- | 353 | 0.60 | 7.67 | 5.66 | ||
Mercury 2 | 128k | Proprietär | 12 | $0.07 | 838 | 4.58 | 5.18 | -- | ||
Mistral Small 4 | 256k | Offen | 11 | $0.05 | 169 | 0.73 | 15.55 | 11.86 | ||
Qwen3 Next 80B A3B (Reasoning) | 262k | Offen | 11* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B (Reasoning) Vertex | 262k | Offen | 11* | -- | 161 | 0.71 | 16.24 | 12.42 | ||
Qwen3 Next 80B A3B (Reasoning) | 262k | Offen | 11* | -- | 196 | 2.43 | 15.15 | 10.18 | ||
Qwen3 Next 80B A3B (Reasoning) | 262k | Offen | 11* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (low) | 1M | Proprietär | 11* | -- | -- | -- | -- | -- | ||
Trinity Large Thinking | 262k | Offen | 11 | $0.35 | 319 | 1.31 | 9.14 | 6.27 | ||
G9v3-3B | 131k | Offen | 11* | -- | -- | -- | -- | -- | ||
Qwen3.5 4B (Non-reasoning) FP8 | 262k | Offen | 11* | -- | 23 | 0.74 | 22.03 | -- | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) Base | 128k | Offen | 10* | -- | 297 | 1.02 | 9.44 | 6.74 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 269 | 0.35 | 9.63 | 7.42 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 729 | 1.29 | 4.72 | 2.74 | ||
gpt-oss-120b (low) Vertex | 131k | Offen | 10* | -- | 212 | 0.36 | 12.17 | 9.45 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 55 | 0.65 | 46.40 | 36.60 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 57 | 1.34 | 45.25 | 35.13 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 1,768 | 0.53 | 1.94 | 1.13 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 334 | 0.81 | 8.31 | 5.99 | ||
gpt-oss-120b (low) | 128k | Offen | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 128k | Offen | 10* | -- | 296 | 0.23 | 8.68 | 6.76 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 72 | 0.97 | 35.81 | 27.87 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 159 | 0.80 | 16.48 | 12.54 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 148 | 0.55 | 17.45 | 13.52 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 473 | 0.69 | 5.98 | 4.23 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 102 | 0.98 | 25.49 | 19.61 | ||
Qwen3 Coder Next | 128k | Offen | 10 | $0.78 | 89 | 1.01 | 6.63 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Offen | 10 | $0.12 | 73 | 1.03 | 7.90 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Offen | 10 | $0.78 | -- | -- | -- | -- | ||
Qwen3 Coder Next (FP8) | 262k | Offen | 10 | $0.33 | 166 | 2.48 | 5.50 | -- | ||
Nova 2.0 Pro Preview (Non-reasoning) | 256k | Proprietär | 10* | -- | 115 | 1.03 | 5.40 | -- | ||
gpt-oss-20b (low) | 131k | Offen | 10* | -- | 931 | 0.84 | 3.53 | 2.15 | ||
gpt-oss-20b (low) | 128k | Offen | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Offen | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Offen | 10* | -- | 256 | 0.59 | 10.35 | 7.80 | ||
gpt-oss-20b (low) | 128k | Offen | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Offen | 10* | -- | 187 | 6.94 | 20.33 | 10.72 | ||
gpt-oss-20b (low) | 131k | Offen | 10* | -- | 231 | 1.13 | 11.93 | 8.64 | ||
gpt-oss-20b (low) Vertex | 131k | Offen | 10* | -- | 402 | 0.32 | 6.54 | 4.97 | ||
Mistral Large 3 | 256k | Offen | 10 | $0.10 | 208 | 1.09 | 3.50 | -- | ||
Mistral Large 3 | 256k | Offen | 10 | $0.10 | 97 | 1.43 | 6.59 | -- | ||
Mistral Large 3 | 262k | Offen | 10 | $0.10 | 75 | 1.07 | 7.77 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 10* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Offen | 10* | -- | 308 | 0.63 | 2.25 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 10* | -- | 102 | 0.92 | 5.83 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 10* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 10* | -- | 152 | 0.68 | 3.96 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 10* | -- | 173 | 1.53 | 4.42 | -- | ||
Qwen3 Next 80B A3B | 131k | Offen | 10* | -- | 187 | 1.75 | 4.43 | -- | ||
Qwen3 Next 80B A3B | 131k | Offen | 10* | -- | 181 | 2.23 | 4.99 | -- | ||
Devstral 2 | 262k | Offen | 9 | $0.00 | 141 | 2.25 | 5.80 | -- | ||
Gemma 4 12B (Non-reasoning) | 262k | Offen | 9* | -- | 104 | 2.34 | 7.13 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Offen | 9 | $0.04 | 84 | 0.78 | 6.75 | -- | ||
Llama 4 Maverick (FP8) | 128k | Offen | 9 | $0.04 | 391 | 1.27 | 2.55 | -- | ||
Llama 4 Maverick | 128k | Offen | 9 | $0.04 | 234 | 0.75 | 2.89 | -- | ||
Llama 4 Maverick | 1.05M | Offen | 9 | $0.04 | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Offen | 9 | $0.03 | 74 | 0.50 | 7.25 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Offen | 9 | $0.03 | 56 | 0.95 | 9.92 | -- | ||
Nova Premier | 1M | Proprietär | 9* | -- | 33 | 2.82 | 17.89 | -- | ||
Granite 4.2 3B | 131k | Offen | 9 | $0.01 | 217 | 0.43 | 11.95 | 9.22 | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.01 | 223 | 0.59 | 11.78 | 8.95 | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.01 | 235 | 26.76 | 37.39 | 8.50 | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.01 | 117 | 0.44 | 21.85 | 17.13 | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | Offen | 9 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | Offen | 9 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.01 | 209 | 1.16 | 13.11 | 9.56 | ||
gpt-oss-20b (high) Vertex | 131k | Offen | 9 | $0.01 | 409 | 0.34 | 6.45 | 4.89 | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.02 | 959 | 0.78 | 3.39 | 2.09 | ||
Llama Nemotron Super 49B v1.5 | 131k | Offen | 9* | -- | 95 | 4.25 | 30.66 | 21.13 | ||
Mistral Small 4 (Non-reasoning) | 262k | Offen | 9* | -- | 155 | 0.75 | 3.97 | -- | ||
Gemma 4 E4B | 262k | Offen | 9* | -- | 43 | 0.83 | 58.62 | 46.24 | ||
Nemotron 3 Nano | 262k | Offen | 9 | $0.02 | 231 | 1.11 | 11.93 | 8.65 | ||
Nemotron 3 Nano (FP4) | 262k | Offen | 9 | $0.02 | 305 | 0.99 | 9.19 | 6.56 | ||
Nemotron 3 Nano | 262k | Offen | 9 | $0.02 | 97 | 5.21 | 30.86 | 20.52 | ||
Sarvam 105B (high) | 128k | Offen | 9* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (Non-reasoning) | 1M | Proprietär | 9* | -- | 155 | 1.06 | 4.30 | -- | ||
Magistral Small 1.2 | 128k | Offen | 9* | -- | 72 | 1.60 | 36.17 | 27.66 | ||
LFM2.5-2.6B | 32.8k | Offen | 8* | -- | -- | -- | -- | -- | ||
Devstral Small 2 | 256k | Offen | 8 | $0.00 | 139 | 2.23 | 5.83 | -- | ||
Nova 2.0 Omni (Non-reasoning) | 1M | Proprietär | 8* | -- | -- | -- | -- | -- | ||
Solar Pro 3 | 131k | Proprietär | 8 | $0.08 | 155 | 2.52 | 18.67 | 12.92 | ||
Qwen3 Omni 30B A3B (Reasoning) | 65.5k | Offen | 8* | -- | 101 | 1.92 | 26.62 | 19.76 | ||
Llama 3.3 70B | 131k | Offen | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B Vertex | 128k | Offen | 8* | -- | 157 | 0.64 | 3.82 | -- | ||
Llama 3.3 70B | 131k | Offen | 8* | -- | 299 | 0.81 | 2.49 | -- | ||
Llama 3.3 70B | 131k | Offen | 8* | -- | 43 | 1.72 | 13.30 | -- | ||
Llama 3.3 70B (FP8) | 131k | Offen | 8* | -- | 86 | 2.64 | 8.48 | -- | ||
Llama 3.3 70B | 128k | Offen | 8* | -- | 277 | 2.16 | 3.96 | -- | ||
Llama 3.3 70B Base | 128k | Offen | 8* | -- | 4 | 16.43 | 142.22 | -- | ||
Llama 3.3 70B | 128k | Offen | 8* | -- | 80 | 0.88 | 7.10 | -- | ||
Llama 3.3 70B Turbo | 131k | Offen | 8* | -- | 82 | 1.39 | 7.49 | -- | ||
Llama 3.3 70B | 128k | Offen | 8* | -- | 116 | 2.22 | 6.54 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | Offen | 8* | -- | 16 | 2.05 | 34.11 | -- | ||
Llama 3.3 70B | 24k | Offen | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B | 128k | Offen | 8* | -- | 149 | 1.11 | 4.46 | -- | ||
Llama 3.3 70B | 100k | Offen | 8* | -- | 80 | 1.35 | 7.60 | -- | ||
ERNIE 4.5 300B A47B | 131k | Offen | 8* | -- | -- | -- | -- | -- | ||
Hermes 4 405B (FP8) | 128k | Offen | 7* | -- | 44 | 2.52 | 59.95 | 45.94 | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | Offen | 7* | -- | 137 | 3.82 | 22.01 | 14.55 | ||
Gemma 4 E4B (Non-reasoning) | 262k | Offen | 7* | -- | 46 | 0.77 | 11.61 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Offen | 7* | -- | 91 | 6.83 | 34.34 | 22.00 | ||
Hermes 4 405B (Non-reasoning) (FP8) | 128k | Offen | 7* | -- | 43 | 2.41 | 14.05 | -- | ||
Llama Nemotron Super 49B v1.5 (Non-reasoning) | 131k | Offen | 7* | -- | 144 | 3.02 | 6.49 | -- | ||
LFM2.5-8B-A1B | 32.8k | Offen | 7* | -- | -- | -- | -- | -- | ||
Ring-flash-2.0 | 131k | Offen | 7* | -- | -- | -- | -- | -- | ||
Olmo 3.1 32B Think | 65.5k | Offen | 7* | -- | -- | -- | -- | -- | ||
Command A | 288k | Offen | 7* | -- | 57 | 1.67 | 10.37 | -- | ||
Command A | 256k | Offen | 7* | -- | 42 | 3.01 | 14.94 | -- | ||
Llama 3.1 Nemotron 70B | 131k | Offen | 7* | -- | 126 | 3.22 | 7.18 | -- | ||
Nemotron 3 Nano (Non-reasoning) (FP4) | 262k | Offen | 7* | -- | 288 | 0.99 | 2.73 | -- | ||
Nemotron 3 Nano (Non-reasoning) | 262k | Offen | 7* | -- | 102 | 0.64 | 5.56 | -- | ||
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 131k | Offen | 7* | -- | 100 | 5.71 | 10.70 | -- | ||
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 131k | Offen | 7* | -- | 168 | 1.11 | 4.09 | -- | ||
Granite 4.1 8B | 131k | Offen | 7* | -- | 126 | 0.74 | 4.71 | -- | ||
Sarvam 30B (high) | 64k | Offen | 7* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 328k | Offen | 6 | $0.06 | 22 | 0.88 | 23.53 | -- | ||
Llama 4 Scout | 128k | Offen | 6 | $0.12 | 133 | 0.87 | 4.64 | -- | ||
Llama 4 Scout Vertex | 1.31M | Offen | 6 | $0.16 | 145 | 0.70 | 4.14 | -- | ||
Llama 4 Scout | 131k | Offen | 6 | $0.17 | -- | -- | -- | -- | ||
Llama 4 Scout | 128k | Offen | 6 | $0.11 | 167 | 0.80 | 3.79 | -- | ||
Llama 4 Scout | 131k | Offen | 6 | $0.11 | 22 | 1.63 | 24.87 | -- | ||
Celeris-1 | 131k | Proprietär | 6 | $0.05 | 1,418 | 0.60 | 0.95 | -- | ||
Phi-4 Mini | 128k | Offen | 6* | -- | 45 | 0.86 | 12.05 | -- | ||
Granite 4.0 H Small | 128k | Offen | 6* | -- | 15 | 29.59 | 63.25 | -- | ||
Ministral 3 14B | 262k | Offen | 6 | $0.14 | 84 | 0.93 | 6.86 | -- | ||
Ministral 3 14B | 256k | Offen | 6 | $0.14 | 241 | 0.92 | 2.99 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | Offen | 6* | -- | 96 | 1.90 | 7.09 | -- | ||
Phi-4 | 16.4k | Offen | 6* | -- | 40 | 2.57 | 14.94 | -- | ||
Phi-4 | 16.4k | Offen | 6* | -- | 56 | 0.93 | 9.82 | -- | ||
Nova Micro | 130k | Proprietär | 6* | -- | 287 | 0.89 | 2.64 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | 128k | Offen | 6* | -- | 199 | 1.07 | 3.59 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) (FP8) | 131k | Offen | 6* | -- | 128 | 4.58 | 8.48 | -- | ||
Phi-4 Multimodal | 128k | Offen | 6* | -- | 17 | 0.87 | 30.21 | -- | ||
Reka Flash 3 | 54k | Offen | 6* | -- | -- | -- | -- | -- | ||
Ministral 3 8B | 256k | Offen | 5 | $0.07 | 243 | 1.02 | 3.08 | -- | ||
Ministral 3 8B | 262k | Offen | 5 | $0.07 | 90 | 0.72 | 6.28 | -- | ||
Llama 3.2 11B (Vision) | 131k | Offen | 5* | -- | 23 | 1.27 | 23.15 | -- | ||
Olmo 3 7B | 65.5k | Offen | 5* | -- | -- | -- | -- | -- | ||
Apertus 70B Instruct | 64k | Offen | 5* | -- | -- | -- | -- | -- | ||
Ministral 3 3B | 256k | Offen | 5 | $0.04 | 527 | 0.89 | 1.84 | -- | ||
Ministral 3 3B | 131k | Offen | 5 | $0.04 | 214 | 0.61 | 2.94 | -- | ||
LFM2.5-VL-1.6B | 32.8k | Offen | 5* | -- | -- | -- | -- | -- | ||
Tiny Aya Global | 8.19k | Offen | 5* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | Offen | 5* | -- | -- | -- | -- | -- | ||
Cogito v2.1 | 164k | Offen | -- | -- | -- | -- | -- | -- | ||