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 5.5 (max with fallback) | 1M | Proprietär | 58 | $5.98 | 96 | 562.48 | 567.67 | -- | ||
Claude Opus 5.5 (max with fallback) | 1M | Proprietär | 58 | $5.98 | 96 | 679.38 | 684.59 | -- | ||
Claude Opus 5.5 (max with fallback) | 1M | Proprietär | 58 | $11.63 | 96 | 605.98 | 611.21 | -- | ||
Claude Opus 5.5 (max with fallback) | 1M | Proprietär | 58 | $6.70 | 96 | 650.02 | 655.25 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietär | 56 | $5.46 | 133 | 343.12 | 346.89 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietär | 56 | $4.96 | 128 | 361.40 | 365.31 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietär | 56 | -- | 135 | 347.00 | 350.71 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietär | 56 | -- | 133 | 397.16 | 400.91 | -- | ||
Claude Opus 5.5 (xhigh with fallback) | 1M | Proprietär | 56 | $3.46 | 85 | 97.91 | 103.80 | -- | ||
Kimi K3.1 Pro | 1M | Proprietär | 55 | $2.11 | 73 | 2.97 | 37.00 | 27.23 | ||
Kimi K3.1 Pro High Speed | 1M | Proprietär | 55 | -- | 129 | 2.42 | 21.80 | 15.50 | ||
Claude Opus 5.5 (high with fallback) | 1M | Proprietär | 54 | $1.82 | 81 | 21.55 | 27.75 | -- | ||
Claude Fable 5.1 (max with fallback) | 1M | Proprietär | 53 | $7.63 | 68 | 163.20 | 170.50 | -- | ||
Claude Fable 5.1 (xhigh with fallback) | 1M | Proprietär | 53 | $5.98 | 65 | 60.95 | 68.67 | -- | ||
GPT-6 Astra (max) | 1M | Proprietär | 53 | $3.26 | 58 | 246.99 | 255.59 | -- | ||
GPT-6 Astra (max) | 524k | Proprietär | 53 | $3.35 | 61 | 262.52 | 270.70 | -- | ||
GPT-6 Astra (max) | 524k | Proprietär | 53 | $3.26 | 75 | 223.80 | 230.49 | -- | ||
GPT-6 Astra (max) (Fast) | 1M | Proprietär | 53 | $6.52 | -- | -- | -- | -- | ||
GPT-6 Astra (max) (Ultrafast) | 1M | Proprietär | 53 | $19.55 | -- | -- | -- | -- | ||
GPT-6 Astra (max) (Flex) | 1M | Proprietär | 53 | $1.63 | 103 | 166.70 | 171.55 | -- | ||
Gemini 4 Argon (high) AI Studio (1M output) | 1M | Proprietär | 53 | $1.99 | -- | -- | -- | -- | ||
Gemini 4 Argon (high) AI Studio | 1M | Proprietär | 53 | $1.99 | 102 | 47.24 | 52.13 | -- | ||
Gemini 4 Argon (high) (Vertex) | 1M | Proprietär | 53 | $1.99 | 79 | 57.01 | 63.33 | -- | ||
Muse Wonder (max) | 1.05M | Proprietär | 52 | $4.54 | 145 | 26.53 | 43.75 | 13.78 | ||
GPT-6 Astra (xhigh) | 1M | Proprietär | 52 | $2.31 | 54 | 132.31 | 141.52 | -- | ||
Claude Sonnet 5.5 (xhigh with fallback) | 1M | Proprietär | 52 | $2.01 | 111 | 26.07 | 30.57 | -- | ||
GPT-6.1 Sol (max) | 1M | Proprietär | 52 | $0.72 | 57 | 162.10 | 170.82 | -- | ||
GPT-6.1 Sol (max) | 1.05M | Proprietär | 52 | $0.73 | 61 | 208.54 | 216.71 | -- | ||
GPT-6.1 Sol (max) (Fast) | 1M | Proprietär | 52 | $1.45 | 100 | 133.95 | 138.97 | -- | ||
GPT-6.1 Sol (max) (Flex) | 1M | Proprietär | 52 | $0.36 | 71 | 171.61 | 178.67 | -- | ||
GPT-6.1 Sol (max) (Ultrafast) | 1M | Proprietär | 52 | $4.35 | 320 | 42.36 | 43.93 | -- | ||
Claude Opus 5.5 (medium with fallback) | 1M | Proprietär | 51 | $1.34 | 84 | 10.44 | 16.41 | -- | ||
Claude Fable 5.1 (high with fallback) | 1M | Proprietär | 51 | $3.91 | 60 | 25.55 | 33.94 | -- | ||
GPT-6.1 Sol (xhigh) | 1M | Proprietär | 51 | $0.39 | 51 | 60.09 | 69.83 | -- | ||
GPT-6 Astra (high) | 1M | Proprietär | 51 | $1.73 | 57 | 32.11 | 40.94 | -- | ||
GPT-6.1 Sol (high) | 1M | Proprietär | 50 | $0.32 | 51 | 31.33 | 41.18 | -- | ||
GPT-6 Astra (medium) | 1M | Proprietär | 50 | $1.54 | 55 | 4.04 | 13.10 | -- | ||
Claude Fable 5.1 (medium with fallback) | 1M | Proprietär | 49 | $2.98 | 59 | 3.76 | 12.28 | -- | ||
GPT-6.1 Sol (medium) | 1M | Proprietär | 48 | $0.21 | 49 | 3.96 | 14.25 | -- | ||
Claude Fable 5.1 (low with fallback) | 1M | Proprietär | 47 | $2.37 | 60 | 0.98 | 9.31 | -- | ||
Claude Sonnet 5.5 (high with fallback) | 1M | Proprietär | 47 | $0.88 | 108 | 10.34 | 14.98 | -- | ||
Grok 4.7 (xhigh) | 500k | Proprietär | 46 | $3.74 | 97 | 34.82 | 39.99 | -- | ||
Grok 4.7 (high) | 500k | Proprietär | 46 | $2.73 | 91 | 18.67 | 24.17 | -- | ||
MiMo-V2.6-Pro | 1M | Offen | 46 | $0.13 | 55 | 2.66 | 48.33 | 36.53 | ||
MiMo-V2.6-Pro | 1M | Offen | 46 | $0.96 | 40 | 2.07 | 65.16 | 50.47 | ||
MiMo-V2.6-Pro | 1.05M | Offen | 46 | $0.14 | 244 | 0.89 | 11.14 | 8.20 | ||
MiMo-V2.6-Pro (BF16) | 1M | Offen | 46 | $0.12 | 55 | 2.96 | 48.63 | 36.53 | ||
GPT-6 Astra (low) | 1M | Proprietär | 46 | $0.82 | 53 | 2.22 | 11.58 | -- | ||
GPT-6 Astra (low) | 524k | Proprietär | 46 | $0.84 | 59 | 2.66 | 11.18 | -- | ||
Qwen3.8 Max (0902) | 984k | Proprietär | 45 | $5.41 | 42 | 2.99 | 62.80 | 47.84 | ||
DeepSeek V4.1 Flash 1017 (max) | 1M | Offen | 45 | $1.01 | 369 | 0.26 | 7.04 | 5.42 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $0.24 | 158 | 1.47 | 17.32 | 12.68 | ||
DeepSeek V4.1 Flash 1017 (max) (FAST) | 1.05M | Offen | 45 | $2.03 | 868 | 0.20 | 3.09 | 2.30 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $0.29 | 686 | 1.28 | 4.93 | 2.92 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $0.62 | 163 | 1.91 | 17.24 | 12.26 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $0.23 | 351 | 0.57 | 7.70 | 5.70 | ||
DeepSeek V4.1 Flash 1017 (max) (ULTRA CHAT) | 1.05M | Offen | 45 | $0.37 | 1,267 | 0.54 | 2.52 | 1.58 | ||
DeepSeek V4.1 Flash 1017 (max) (ULTRA) | 1.05M | Offen | 45 | $0.37 | 546 | 1.33 | 5.91 | 3.66 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $0.16 | 407 | 0.84 | 6.98 | 4.92 | ||
DeepSeek V4.1 Flash 1017 (max) (FAST) | 1.05M | Offen | 45 | $0.26 | 525 | 1.51 | 6.28 | 3.81 | ||
DeepSeek V4.1 Flash 1017 (max) | 1M | Offen | 45 | $0.26 | 195 | 1.14 | 13.95 | 10.25 | ||
DeepSeek V4.1 Flash 1017 (max) | 1M | Offen | 45 | $0.61 | 71 | 0.85 | 36.23 | 28.30 | ||
DeepSeek V4.1 Flash 1017 (max) | 1M | Offen | 45 | $0.24 | 158 | 1.06 | 16.89 | 12.67 | ||
DeepSeek V4.1 Flash 1017 (max) | 1M | Offen | 45 | $0.24 | 153 | 0.67 | 17.04 | 13.09 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $0.32 | 339 | 0.31 | 7.68 | 5.90 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $0.83 | 161 | 2.02 | 17.53 | 12.40 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $1.05 | 240 | 0.62 | 11.02 | 8.32 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $0.26 | 471 | 1.49 | 6.80 | 4.25 | ||
DeepSeek V4.1 Flash 1017 (max) (FAST) | 1.05M | Offen | 45 | $2.14 | 1,068 | 11.93 | 14.27 | 1.87 | ||
DeepSeek V4.1 Flash 1017 (max) | 1M | Offen | 45 | $1.68 | 335 | 0.52 | 7.99 | 5.98 | ||
DeepSeek V4.1 Flash 1017 (max) | 1.05M | Offen | 45 | $0.28 | 188 | 0.49 | 13.81 | 10.66 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $1.97 | 124 | 0.89 | 21.10 | 16.17 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $2.01 | 85 | 2.86 | 32.29 | 23.54 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $1.97 | 143 | 0.75 | 18.19 | 13.95 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $1.97 | 182 | 1.16 | 14.91 | 11.00 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $0.97 | 95 | 1.10 | 27.43 | 21.06 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $2.96 | 181 | 0.65 | 14.46 | 11.05 | ||
GLM-5.3 (max) (FAST) | 1M | Offen | 45 | $4.08 | 679 | 0.78 | 4.46 | 2.94 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $2.00 | 92 | 2.15 | 29.45 | 21.84 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $1.43 | 107 | 3.47 | 26.82 | 18.68 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $1.97 | 55 | 0.88 | 46.13 | 36.20 | ||
GLM-5.3 (max) | 1.05M | Offen | 45 | $0.92 | 216 | 0.95 | 12.52 | 9.26 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $2.73 | 205 | 0.85 | 13.02 | 9.73 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $2.04 | 187 | 0.75 | 14.15 | 10.72 | ||
GLM-5.3 (max) (FAST) | 1M | Offen | 45 | $3.75 | 225 | 0.94 | 12.06 | 8.90 | ||
GLM-5.3 (max) (FP4) | 1.05M | Offen | 45 | $2.35 | 471 | 0.57 | 5.87 | 4.24 | ||
GLM-5.3 (max) (FP4 ULTRA CHAT) | 1.05M | Offen | 45 | $5.14 | 770 | 0.67 | 3.91 | 2.60 | ||
GLM-5.3 (max) | 164k | Offen | 45 | $2.04 | 93 | 2.51 | 29.25 | 21.39 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $4.99 | 141 | 1.60 | 19.33 | 14.18 | ||
GLM-5.3 (max) (FP4) | 786k | Offen | 45 | $3.36 | 235 | 0.75 | 11.41 | 8.53 | ||
GLM-5.3 (max) (FP4) | 1M | Offen | 45 | $1.19 | 246 | 1.96 | 12.12 | 8.13 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $1.81 | 143 | 0.91 | 18.43 | 14.01 | ||
GLM-5.3 (max) (FP4, FAST) | 1M | Offen | 45 | $5.29 | 617 | 1.59 | 5.64 | 3.24 | ||
GLM-5.3 (max) (FP4) | 1M | Offen | 45 | $1.97 | 201 | 1.47 | 13.88 | 9.93 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $1.42 | 106 | 3.13 | 26.77 | 18.92 | ||
GLM-5.3 (max) | 1M | Offen | 45 | $0.80 | 213 | 0.98 | 12.73 | 9.40 | ||
GLM-5.3 (max) | 262k | Offen | 45 | $12.94 | 229 | 1.30 | 12.22 | 8.74 | ||
Ling 3.1 Flash 1019 | 1M | Proprietär | 44 | $1.49 | -- | -- | -- | -- | ||
Step 5 Preview | 1M | Offen | 44 | $1.03 | 229 | 1.16 | 12.08 | 8.74 | ||
Claude Haiku 5.5 (max) | 1M | Proprietär | 43 | $0.21 | 236 | 301.64 | 303.76 | -- | ||
MiniMax-M3.1-Flash | 1.05M | Proprietär | 43 | $0.33 | 429 | 0.67 | 6.49 | 4.66 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.37 | 114 | 2.49 | 24.50 | 17.61 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.24 | 86 | 1.75 | 30.96 | 23.37 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.32 | 79 | 1.43 | 33.20 | 25.41 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.20 | 255 | 0.71 | 10.51 | 7.84 | ||
MiniMax-M3.1-Flash | 1.05M | Proprietär | 43 | $0.29 | 233 | 0.57 | 11.29 | 8.58 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.19 | 128 | 1.00 | 20.54 | 15.63 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.22 | 178 | 0.87 | 14.94 | 11.26 | ||
MiniMax-M3.1-Flash | 262k | Proprietär | 43 | $0.63 | 839 | 2.89 | 5.87 | 2.38 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.19 | 125 | 2.06 | 22.00 | 15.95 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.19 | 233 | 1.91 | 12.66 | 8.60 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.20 | 116 | 1.53 | 23.07 | 17.23 | ||
MiniMax-M3.1-Flash | 1M | Proprietär | 43 | $0.22 | 96 | 1.32 | 27.48 | 20.93 | ||
Claude Opus 5.5 (low with fallback) | 1M | Proprietär | 42 | $0.55 | 81 | 6.05 | 12.21 | -- | ||
Claude Opus 5.5 (low with fallback) | 1M | Proprietär | 42 | $0.55 | 82 | 4.28 | 10.39 | -- | ||
Claude Opus 5.5 (low with fallback) | 1M | Proprietär | 42 | $0.68 | 82 | 5.36 | 11.46 | -- | ||
Claude Opus 5.5 (low with fallback) | 1M | Proprietär | 42 | $0.59 | 82 | 3.47 | 9.61 | -- | ||
Grok 4.7 (low) | 500k | Proprietär | 42 | $1.25 | 78 | 4.77 | 11.17 | -- | ||
GPT-6.1 Sol (low) | 1M | Proprietär | 42 | $0.13 | 48 | 1.78 | 12.24 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietär | 42 | $1.40 | 126 | 101.00 | 104.98 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietär | 42 | $1.41 | 138 | 75.69 | 79.32 | -- | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.88 | 98 | 0.84 | 26.37 | 20.42 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.28 | 69 | 3.29 | 39.60 | 29.04 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.60 | 153 | 0.39 | 16.70 | 13.05 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.34 | 53 | 0.87 | 48.41 | 38.04 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.29 | 79 | 3.14 | 34.92 | 25.42 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.37 | 175 | 3.13 | 17.40 | 11.42 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.28 | 124 | 0.91 | 21.09 | 16.14 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.50 | 60 | 1.87 | 43.39 | 33.22 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.31 | 50 | 4.02 | 53.56 | 39.63 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.24 | 235 | 1.42 | 12.05 | 8.51 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.45 | 162 | 0.77 | 16.17 | 12.32 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.47 | 173 | 0.73 | 15.19 | 11.57 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.67 | 112 | 1.43 | 23.77 | 17.88 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.51 | 322 | 0.62 | 8.38 | 6.21 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $1.19 | 144 | 1.56 | 18.90 | 13.88 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.42 | 265 | 0.69 | 10.14 | 7.56 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.54 | 146 | 2.15 | 19.25 | 13.68 | ||
GLM-5.3-Flash | 1M | Offen | 42 | $0.65 | 281 | 1.25 | 10.15 | 7.12 | ||
GLM-5.3-Flash (FP4) | 1.05M | Offen | 42 | $0.81 | 133 | 1.17 | 20.01 | 15.08 | ||
GLM-5.3-Flash (FAST) | 1M | Offen | 42 | $0.56 | 1,385 | 3.41 | 5.22 | 1.44 | ||
GLM-5.3-Flash (FP4) | 1.05M | Offen | 42 | $0.29 | 378 | 0.95 | 7.57 | 5.30 | ||
GLM-5.3-Flash (FP4, ULTRA CHAT) | 1.05M | Offen | 42 | $0.56 | 1,469 | 0.42 | 2.12 | 1.36 | ||
GLM-5.3-Flash | 1.05M | Offen | 42 | $0.44 | 281 | 0.65 | 9.55 | 7.12 | ||
GLM-5.3-Flash (FP4, ULTRA) | 1.05M | Offen | 42 | $0.57 | 533 | 0.86 | 5.55 | 3.75 | ||
Claude Haiku 5.5 (xhigh) | 1M | Proprietär | 41 | $0.12 | 190 | 55.53 | 58.16 | -- | ||
Ling 3.1 Flash | 262k | Offen | 41 | $1.01 | 11 | 0.92 | 227.37 | 181.16 | ||
Ling 3.1 Flash | 1M | Offen | 41 | $1.01 | 219 | 1.91 | 13.33 | 9.13 | ||
Gemini 3.8 Flash (high) AI Studio | 1M | Proprietär | 41 | $1.24 | 141 | 25.70 | 29.24 | -- | ||
Claude Sonnet 5.5 (medium with fallback) | 1M | Proprietär | 41 | $0.48 | 104 | 1.39 | 6.20 | -- | ||
Qwen3.8 2.4T A95B | 262k | Offen | 40 | $1.87 | 163 | 0.89 | 16.19 | 12.24 | ||
Qwen3.8 2.4T A95B | 262k | Offen | 40 | $2.09 | 135 | 1.13 | 19.63 | 14.80 | ||
Qwen3.8 2.4T A95B | 262k | Offen | 40 | $1.80 | 54 | 0.88 | 46.82 | 36.75 | ||
Qwen3.8 2.4T A95B | 1M | Offen | 40 | $1.96 | 247 | 0.78 | 10.90 | 8.10 | ||
Qwen3.8 2.4T A95B | 262k | Offen | 40 | $2.89 | 83 | 1.11 | 31.35 | 24.19 | ||
Qwen3.8 2.4T A95B | 262k | Offen | 40 | $2.16 | 43 | 2.94 | 61.07 | 46.50 | ||
Qwen3.8-Flash-Next | 1M | Offen | 40 | $0.37 | 52 | 2.16 | 50.69 | 38.82 | ||
Gemini 3.8 Flash (medium) AI Studio | 1M | Proprietär | 40 | $0.93 | -- | -- | -- | -- | ||
Muse Spark Open (xhigh) | 1.05M | Offen | 39 | $0.84 | 91 | 0.77 | 28.18 | 21.93 | ||
Muse Spark Open (xhigh) | 1.05M | Offen | 39 | $0.84 | 234 | 0.24 | 10.94 | 8.56 | ||
Muse Spark Open (xhigh) (FP4) | 1.05M | Offen | 39 | $0.70 | 130 | 1.39 | 20.69 | 15.44 | ||
Muse Spark Open (xhigh) | 1.05M | Offen | 39 | $0.84 | 205 | 0.66 | 12.83 | 9.73 | ||
Muse Spark Open (xhigh) (NVFP4) | 1.05M | Offen | 39 | $0.72 | 379 | 0.83 | 7.43 | 5.27 | ||
Mistral Large 4 Preview | 524k | Proprietär | 38 | $1.13 | 95 | 3.14 | 29.59 | 21.16 | ||
GPT-6 Luna (max) | 1M | Proprietär | 38 | $0.07 | 137 | 64.91 | 68.56 | -- | ||
GPT-6 Luna (max) | 524k | Proprietär | 38 | $0.07 | 162 | 55.27 | 58.36 | -- | ||
GPT-6 Luna (max) (Flex) | 1M | Proprietär | 38 | $0.03 | 52 | 137.23 | 146.84 | -- | ||
GPT-5.6 Terra (xhigh) | 1M | Proprietär | 38 | $0.63 | 112 | 7.25 | 11.72 | -- | ||
GPT-5.6 Terra (xhigh) | 524k | Proprietär | 38 | $0.71 | 134 | 10.49 | 14.21 | -- | ||
MiMo-V2.6-Flash | 1M | Offen | 38 | $0.06 | 59 | 4.12 | 46.19 | 33.66 | ||
MiMo-V2.6-Flash | 1M | Offen | 38 | $0.42 | 49 | 1.97 | 52.48 | 40.41 | ||
MiMo-V2.6-Flash (BF16) | 524k | Offen | 38 | $0.06 | 45 | 3.66 | 59.74 | 44.87 | ||
MiMo-V2.6-Flash | 1.05M | Offen | 38 | $0.22 | 148 | 0.98 | 17.89 | 13.53 | ||
Claude Haiku 5.5 (high) | 1M | Proprietär | 38 | $0.08 | 189 | 17.81 | 20.45 | -- | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $1.76 | 73 | 2.90 | 37.13 | 27.38 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $1.65 | 191 | 1.47 | 14.55 | 10.46 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $0.67 | 97 | 1.65 | 27.41 | 20.61 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $1.45 | 64 | 1.46 | 40.34 | 31.11 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Offen | 36 | $5.51 | 137 | 1.63 | 19.86 | 14.58 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $0.70 | 72 | 2.44 | 37.13 | 27.75 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $1.61 | 57 | 0.83 | 44.59 | 35.01 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Offen | 36 | $1.00 | 81 | 1.16 | 31.92 | 24.61 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $0.51 | 309 | 1.59 | 9.68 | 6.48 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Offen | 36 | $3.63 | 187 | 1.60 | 14.97 | 10.70 | ||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietär | 36 | -- | 106 | 1.25 | 5.97 | -- | ||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietär | 36 | $0.35 | 104 | 1.40 | 6.21 | -- | ||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietär | 36 | -- | 104 | 1.77 | 6.57 | -- | ||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietär | 36 | $0.33 | 106 | 0.87 | 5.58 | -- | ||
Agnes 2.5 Pro Beta | 1M | Proprietär | 35* | -- | 113 | 1.40 | 23.51 | 17.69 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietär | 35 | $0.51 | 181 | 0.80 | 14.61 | 11.05 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietär | 35 | $0.28 | 201 | 2.38 | 14.82 | 9.95 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietär | 35 | $2.51 | 195 | 1.41 | 14.20 | 10.23 | ||
GPT-6 Luna (xhigh) | 1M | Proprietär | 35 | $0.04 | 126 | 15.29 | 19.26 | -- | ||
Claude Haiku 5.5 (medium) | 1M | Proprietär | 34 | $0.05 | 180 | 7.71 | 10.49 | -- | ||
GLM-5.3 (low) | 1M | Offen | 34 | $0.85 | 89 | 3.10 | 31.14 | 22.44 | ||
GLM-5.3 (low) (FP4) | 1M | Offen | 34 | $0.50 | 230 | 1.91 | 12.79 | 8.70 | ||
GLM-5.3 (low) (FP4, FAST) | 1M | Offen | 34 | $2.24 | 607 | 1.62 | 5.73 | 3.29 | ||
GLM-5.3 (low) | 1M | Offen | 34 | $2.11 | 134 | 1.61 | 20.21 | 14.88 | ||
GLM-5.3 (low) | 1.05M | Offen | 34 | $0.84 | 56 | 0.82 | 45.41 | 35.67 | ||
GLM-5.3 (low) | 262k | Offen | 34 | $5.46 | 204 | 1.31 | 13.58 | 9.81 | ||
GLM-5.3 (low) | 164k | Offen | 34 | $0.87 | 101 | 3.20 | 28.00 | 19.84 | ||
GLM-5.3 (low) (FAST) | 1M | Offen | 34 | $1.73 | 775 | 0.85 | 4.07 | 2.58 | ||
GPT-5.6 Terra (high) | 1M | Proprietär | 34 | $0.34 | 116 | 2.15 | 6.48 | -- | ||
GPT-5.6 Terra (high) | 524k | Proprietär | 34 | $0.37 | 129 | 2.25 | 6.13 | -- | ||
Qwen3.8 27B (xhigh) | 262k | Offen | 34 | $0.52 | 35 | 1.18 | 72.42 | 56.99 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | Offen | 34 | $0.92 | 56 | 1.83 | 46.69 | 35.89 | ||
Qwen3.8 27B (xhigh) | 1M | Offen | 34 | $1.01 | 44 | 3.88 | 61.31 | 45.94 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | Offen | 34 | $0.60 | 72 | 1.41 | 36.02 | 27.69 | ||
Qwen3.8 27B (xhigh) | 262k | Offen | 34 | -- | 189 | 0.82 | 14.08 | 10.61 | ||
Qwen3.8 27B (xhigh) | 262k | Offen | 34 | $0.61 | 90 | 1.10 | 28.90 | 22.24 | ||
Qwen3.8 27B (xhigh) | 262k | Offen | 34 | $0.84 | 204 | 0.90 | 13.15 | 9.80 | ||
Qwen3.8 27B (xhigh) (FP4) | 262k | Offen | 34 | $0.70 | 414 | 1.36 | 7.41 | 4.83 | ||
Qwen3.8 27B (xhigh) (NVFP4) | 262k | Offen | 34 | $0.00 | 210 | 0.59 | 12.47 | 9.50 | ||
Gemini 3.8 Flash (low) AI Studio | 1M | Proprietär | 33 | -- | -- | -- | -- | -- | ||
GPT-6 Luna (high) | 1M | Proprietär | 33 | $0.03 | 123 | 6.11 | 10.17 | -- | ||
GPT-6 Luna (high) | 524k | Proprietär | 33 | $0.03 | -- | -- | -- | -- | ||
GPT-5.3 Codex (xhigh) | 400k | Proprietär | 33* | -- | 87 | 60.62 | 66.39 | -- | ||
K2 Horizon 375B A23B | 524k | Offen | 31 | $0.00 | 909 | 2.09 | 4.84 | 2.20 | ||
Beam 1.0 (NVFP4) | 1.05M | Offen | 30 | $0.40 | 514 | 0.45 | 5.32 | 3.89 | ||
Beam 1.0 (NVFP4) | 1.05M | Offen | 30 | $0.92 | 361 | 0.97 | 7.89 | 5.53 | ||
Beam 1.0 (NVFP4) | 1.05M | Offen | 30 | $0.21 | 305 | 0.53 | 8.73 | 6.56 | ||
Beam 1.0 | 1.05M | Offen | 30 | $0.12 | 235 | 0.55 | 11.21 | 8.53 | ||
Beam 1.0 (FP8) | 1.05M | Offen | 30 | $0.30 | 310 | 1.29 | 9.35 | 6.45 | ||
GPT-5.6 Terra (medium) | 1M | Proprietär | 30 | $0.18 | 109 | 1.60 | 6.18 | -- | ||
GPT-6 Luna (medium) | 1M | Proprietär | 30 | $0.02 | 92 | 2.79 | 8.25 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | Proprietär | 30 | $1.31 | 97 | 25.64 | 30.80 | -- | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | Proprietär | 30 | $1.30 | 132 | 21.06 | 24.85 | -- | ||
Claude Haiku 5.5 (low) | 1M | Proprietär | 29 | $0.02 | 176 | 6.68 | 9.52 | -- | ||
MiniMax-M3 (MXFP8) | 1M | Offen | 29 | $0.46 | 143 | 1.09 | 18.57 | 13.98 | ||
MiniMax-M3 (NVFP4) | 262k | Offen | 29 | -- | 185 | 1.08 | 14.58 | 10.80 | ||
MiniMax-M3 | 1M | Offen | 29 | $0.58 | 85 | 0.87 | 30.23 | 23.49 | ||
MiniMax-M3 | 1M | Offen | 29 | $0.46 | 99 | 2.09 | 27.32 | 20.18 | ||
MiniMax-M3 | 1M | Offen | 29 | $0.46 | 148 | 1.14 | 18.01 | 13.49 | ||
MiniMax-M3 (FP8) | 1.05M | Offen | 29 | $0.51 | 346 | 1.45 | 8.67 | 5.78 | ||
MiniMax-M3 (FP8) | 1M | Offen | 29 | $0.45 | 84 | 1.52 | 31.22 | 23.76 | ||
MiniMax-M3 | 512k | Offen | 29 | $0.51 | 89 | 1.30 | 29.48 | 22.54 | ||
MiniMax-M3 | 524k | Offen | 29 | $0.44 | 22 | 0.93 | 116.73 | 92.64 | ||
MiniMax-M3 | 1.05M | Offen | 29 | -- | 93 | 1.33 | 28.12 | 21.43 | ||
MiniMax-M3 | 1.05M | Offen | 29 | $3.83 | 132 | 3.33 | 22.33 | 15.20 | ||
MiniMax-M3 | 524k | Offen | 29 | $0.50 | 173 | 0.93 | 15.37 | 11.55 | ||
Qwen3.8 27B (medium) | 1M | Offen | 28 | $1.13 | 50 | 3.94 | 54.17 | 40.19 | ||
GPT-5.6 Terra (low) | 1M | Proprietär | 27 | $0.14 | 114 | 1.39 | 5.76 | -- | ||
Quasar 438B (max) | 1M | Proprietär | 27 | -- | 172 | 1.29 | 15.86 | 11.66 | ||
Solar Pro 4 | 512k | Proprietär | 27 | $0.71 | -- | -- | -- | -- | ||
Nemotron 3.5 Super VL (NVFP4) | 1.05M | Offen | 26 | $0.18 | 608 | 0.85 | 4.96 | 3.29 | ||
Nemotron 3.5 Super VL | 1M | Offen | 26 | $0.11 | 557 | 0.29 | 4.78 | 3.59 | ||
Nemotron 3.5 Super VL | 1.05M | Offen | 26 | $0.44 | 421 | 1.30 | 7.25 | 4.76 | ||
Nemotron 3.5 Super VL (NVFP4) | 1M | Offen | 26 | $0.24 | 522 | 1.38 | 6.17 | 3.83 | ||
Nemotron 3.5 Super VL | 131k | Offen | 26 | $0.35 | 182 | 0.65 | 14.42 | 11.01 | ||
Nemotron 3.5 Super VL | 262k | Offen | 26 | $0.16 | 297 | 0.60 | 9.02 | 6.74 | ||
Nemotron 3.5 Super VL (NVFP4) | 262k | Offen | 26 | $0.26 | 408 | 0.64 | 6.77 | 4.91 | ||
Apodex 1.1 | 256k | Proprietär | 26 | $0.46 | -- | -- | -- | -- | ||
Qwen3.8 27B (low) | 1M | Offen | 26 | $1.05 | 51 | 3.97 | 52.75 | 39.02 | ||
GPT-5.5 Instant (June 2026) | 400k | Proprietär | 26 | $0.69 | 155 | 0.89 | 17.04 | 12.92 | ||
Kimi K2.7 Code (FP4) | 256k | Offen | 26 | $0.46 | 36 | 1.50 | 76.48 | 61.25 | ||
Kimi K2.7 Code (FP8) | 65.5k | Offen | 26 | $1.37 | 59 | 5.96 | 52.37 | 37.91 | ||
Kimi K2.7 Code | 262k | Offen | 26 | $0.83 | 91 | 1.35 | 31.33 | 24.49 | ||
Kimi K2.7 Code | 262k | Offen | 26 | $0.55 | 59 | 4.43 | 50.88 | 37.94 | ||
Kimi K2.7 Code | 262k | Offen | 26 | $0.39 | 48 | 1.29 | 57.77 | 46.13 | ||
Kimi K2.7 Code | 256k | Offen | 26 | $0.54 | 60 | 2.84 | 48.35 | 37.18 | ||
Inkling Small | 524k | Offen | 26 | -- | 209 | 0.88 | 12.87 | 9.59 | ||
Inkling Small | 256k | Offen | 26 | $0.09 | 224 | 1.62 | 12.78 | 8.93 | ||
Hy3 (FP8) | 256k | Offen | 25 | $0.07 | 92 | 3.00 | 30.09 | 21.67 | ||
Hy3 | 262k | Offen | 25 | $0.07 | 83 | 2.65 | 32.77 | 24.09 | ||
Hy3 (FP8) | 262k | Offen | 25 | $0.07 | 51 | 1.90 | 50.74 | 39.07 | ||
Hy3 | 262k | Offen | 25 | $0.07 | 96 | 2.86 | 28.93 | 20.86 | ||
Qwen3.7 Plus | 1M | Proprietär | 25 | $0.22 | 59 | 2.28 | 44.50 | 33.77 | ||
Inkling (xhigh) (FP8) | 131k | Offen | 25 | -- | 273 | 0.62 | 9.79 | 7.33 | ||
Inkling (xhigh) | 524k | Offen | 25 | $0.91 | 104 | 0.67 | 24.73 | 19.25 | ||
Inkling (xhigh) (NVFP4) | 1.05M | Offen | 25 | $0.86 | 192 | 1.13 | 14.18 | 10.44 | ||
Inkling (xhigh) | 262k | Offen | 25 | -- | 194 | 1.77 | 14.63 | 10.29 | ||
Inkling (xhigh) | 1M | Offen | 25 | $0.61 | 235 | 1.27 | 11.93 | 8.52 | ||
Inkling (xhigh) | 1.05M | Offen | 25 | $0.63 | 184 | 0.51 | 14.12 | 10.89 | ||
Solar Mini 4 | 524k | Proprietär | 24 | $0.37 | 95 | 1.85 | 28.10 | 21.00 | ||
Nemotron 3 Ultra | 262k | Offen | 23 | $0.51 | 376 | 0.99 | 8.36 | 6.04 | ||
Nemotron 3 Ultra | 262k | Offen | 23 | $0.39 | 65 | 1.24 | 44.11 | 35.15 | ||
Nemotron 3 Ultra BF16 | 262k | Offen | 23 | $0.99 | 89 | 1.55 | 32.90 | 25.70 | ||
Nemotron 3 Ultra | 256k | Offen | 23 | $0.59 | 370 | 2.17 | 9.68 | 6.15 | ||
Nemotron 3 Ultra | 262k | Offen | 23 | $0.32 | 136 | 0.73 | 21.13 | 16.72 | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | Proprietär | 22 | $0.19 | 430 | 6.94 | 8.10 | -- | ||
GPT-6 Luna (low) | 1M | Proprietär | 22 | $0.0045 | 111 | 2.14 | 6.63 | -- | ||
Qwen3.5 397B A17B (non-reasoning) (FP8) | 262k | Offen | 21* | -- | 46 | 1.24 | 12.06 | -- | ||
Qwen3.5 397B A17B (non-reasoning) | 262k | Offen | 21* | -- | 59 | 2.11 | 10.56 | -- | ||
Qwen3.5 397B A17B (non-reasoning) (Base, FP4) | 262k | Offen | 21* | -- | 143 | 1.63 | 5.13 | -- | ||
Qwen3.5 397B A17B (non-reasoning) | 131k | Offen | 21* | -- | 14 | 1.57 | 37.85 | -- | ||
Qwen3.5 397B A17B (non-reasoning) | 262k | Offen | 21* | -- | 59 | 2.26 | 10.77 | -- | ||
GPT-5.6 Terra (non-reasoning) | 1M | Proprietär | 21 | $0.14 | 115 | 0.73 | 5.08 | -- | ||
GPT-5.6 Terra (non-reasoning) | 1M | Proprietär | 21 | $0.14 | 123 | 0.51 | 4.56 | -- | ||
Qwen3.5 Omni Plus | 256k | Proprietär | 20* | -- | 112 | 1.99 | 6.44 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1.05M | Offen | 20 | $0.26 | 307 | 1.49 | 3.12 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1M | Offen | 20 | $0.36 | 96 | 1.71 | 6.90 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1.05M | Offen | 20 | $1.85 | 175 | 1.61 | 4.47 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1.05M | Offen | 20 | $0.43 | 57 | 0.87 | 9.58 | -- | ||
o3 | 200k | Proprietär | 20* | -- | 100 | 23.14 | 28.13 | -- | ||
o3 | 200k | Proprietär | 20* | -- | 134 | 7.39 | 11.12 | -- | ||
Qwen3.8 27B (non-reasoning) | 1M | Offen | 20 | $2.49 | 48 | 3.83 | 14.30 | -- | ||
Qwen3.8 27B (non-reasoning) | 262k | Offen | 20 | -- | 217 | 0.87 | 3.17 | -- | ||
Qwen3.8 27B (non-reasoning) | 262k | Offen | 20 | $1.34 | 97 | 1.15 | 6.33 | -- | ||
Qwen3.8 27B (non-reasoning) | 262k | Offen | 20 | $2.18 | 241 | 0.89 | 2.96 | -- | ||
Qwen3.8 27B (non-reasoning) (NVFP4) | 262k | Offen | 20 | $0.00 | 260 | 0.57 | 2.50 | -- | ||
Qwen3.8 27B (non-reasoning) (FP4) | 262k | Offen | 20 | $1.54 | 441 | 1.37 | 2.51 | -- | ||
LongCat 2.0 (FP8) | 262k | Offen | 19 | $0.15 | 77 | 2.72 | 35.27 | 26.05 | ||
GPT-6 Luna (non-reasoning) | 1M | Proprietär | 18 | $0.01 | 111 | 0.89 | 5.39 | -- | ||
GPT-6 Luna (non-reasoning) | 524k | Proprietär | 18 | $0.01 | 152 | 1.08 | 4.37 | -- | ||
Qwen3.5 397B A17B | 262k | Offen | 18 | $0.47 | 58 | 2.11 | 65.33 | 54.64 | ||
Qwen3.5 397B A17B | 262k | Offen | 18 | $0.29 | 87 | 1.19 | 43.45 | 36.52 | ||
Qwen3.5 397B A17B (FP8) | 262k | Offen | 18 | -- | 49 | 1.17 | 76.80 | 65.37 | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Offen | 18 | $0.17 | 136 | 1.62 | 28.73 | 23.43 | ||
Qwen3.5 397B A17B | 262k | Offen | 18 | $0.47 | 59 | 2.34 | 65.05 | 54.20 | ||
Qwen3.5 397B A17B | 131k | Offen | 18 | $0.17 | 17 | 1.38 | 220.65 | 189.53 | ||
Qwen3.6 35B A3B | 229k | Offen | 18 | $0.48 | 136 | 1.98 | 45.20 | 39.55 | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 18 | $0.32 | 136 | 1.20 | 44.58 | 39.69 | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 18 | $0.14 | 100 | 0.79 | 59.87 | 54.07 | ||
Qwen3.6 35B A3B (FP8) | 262k | Offen | 18 | $0.31 | 167 | 1.03 | 36.38 | 32.35 | ||
Qwen3.6 35B A3B FP8 | 262k | Offen | 18 | $0.31 | 116 | 1.86 | 52.58 | 46.41 | ||
Qwen3.6 35B A3B | 262k | Offen | 18 | $0.12 | 115 | 0.98 | 52.33 | 46.99 | ||
Qwen3.6 35B A3B | 205k | Offen | 18 | $0.31 | 135 | 1.95 | 45.71 | 40.05 | ||
Qwen3.6 35B A3B | 262k | Offen | 18 | $0.37 | 120 | 1.19 | 50.29 | 44.93 | ||
Qwen3.5 122B A10B (non-reasoning) (FP4) | 262k | Offen | 18* | -- | 47 | 1.17 | 11.85 | -- | ||
Qwen3.5 122B A10B (non-reasoning) | 262k | Offen | 18* | -- | 142 | 2.25 | 5.76 | -- | ||
Muse Glimmer (high) | 131k | Offen | 17 | $0.08 | 92 | 0.70 | 27.80 | 21.68 | ||
Muse Glimmer (high) | 131k | Offen | 17 | $0.05 | 122 | 0.93 | 21.38 | 16.36 | ||
Muse Glimmer (high) | 131k | Offen | 17 | $0.03 | 188 | 1.50 | 14.76 | 10.61 | ||
Gemma 4 26B A4B | 262k | Offen | 17* | -- | 90 | 1.36 | 29.28 | 22.33 | ||
Gemma 4 26B A4B AI Studio | 262k | Offen | 17* | -- | 47 | 0.96 | 54.18 | 42.58 | ||
Gemma 4 26B A4B | 131k | Offen | 17* | -- | 516 | 0.98 | 5.83 | 3.87 | ||
Gemma 4 26B A4B | 262k | Offen | 17* | -- | 48 | 0.79 | 53.09 | 41.84 | ||
Gemma 4 26B A4B (FP8) | 262k | Offen | 17* | -- | 83 | 0.71 | 30.85 | 24.11 | ||
Gemma 4 26B A4B | 256k | Offen | 17* | -- | 60 | 1.57 | 43.43 | 33.49 | ||
Gemma 4 26B A4B | 1M | Offen | 17* | -- | 148 | 0.65 | 17.52 | 13.49 | ||
Ring-2.6-1T | 262k | Offen | 17 | $0.29 | 121 | 3.76 | 24.47 | 16.57 | ||
Qwen3.5 122B A10B (FP8) | 262k | Offen | 16 | $0.21 | 72 | 1.70 | 36.23 | 27.62 | ||
Qwen3.5 122B A10B (FP4) | 262k | Offen | 16 | $0.24 | 47 | 1.15 | 54.54 | 42.71 | ||
Qwen3.5 122B A10B | 262k | Offen | 16 | $0.32 | 131 | 2.25 | 21.38 | 15.31 | ||
Qwen3.5 122B A10B | 262k | Offen | 16 | $0.32 | 120 | 2.40 | 23.30 | 16.72 | ||
Qwen3.6 35B A3B (non-reasoning) | 262k | Offen | 15* | -- | 134 | 1.13 | 4.87 | -- | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | 262k | Offen | 15* | -- | 160 | 1.04 | 4.18 | -- | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | 262k | Offen | 15* | -- | 82 | 0.77 | 6.84 | -- | ||
Qwen3.6 35B A3B (non-reasoning) | 205k | Offen | 15* | -- | 156 | 1.89 | 5.10 | -- | ||
Qwen3.6 35B A3B (non-reasoning) FP8 | 262k | Offen | 15* | -- | 91 | 1.87 | 7.36 | -- | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | 262k | Offen | 15* | -- | 114 | 1.01 | 5.41 | -- | ||
Qwen3.6 35B A3B (non-reasoning) | 262k | Offen | 15* | -- | 156 | 1.97 | 5.18 | -- | ||
Gemma 4 31B | 262k | Offen | 15 | $0.07 | 65 | 2.00 | 36.64 | 26.89 | ||
Gemma 4 31B (NVFP4) | 262k | Offen | 15 | $0.10 | 282 | 0.46 | 8.40 | 6.16 | ||
Gemma 4 31B | 262k | Offen | 15 | $0.10 | 22 | 2.38 | 102.75 | 77.93 | ||
Gemma 4 31B (AI Studio) | 262k | Offen | 15 | $0.00 | 36 | 1.08 | 63.28 | 48.29 | ||
Gemma 4 31B | 262k | Offen | 15 | $0.07 | 59 | 1.48 | 39.44 | 29.47 | ||
Gemma 4 31B | 262k | Offen | 15 | $0.15 | 23 | 1.69 | 101.02 | 77.12 | ||
Gemma 4 31B | 262k | Offen | 15 | $0.10 | 60 | 0.94 | 37.98 | 28.76 | ||
Gemma 4 31B (FP8) | 262k | Offen | 15 | $0.54 | 9 | 3.32 | 258.42 | 198.05 | ||
Gemma 4 31B | 131k | Offen | 15 | $0.28 | 543 | 3.41 | 7.53 | 3.20 | ||
Gemma 4 31B | 256k | Offen | 15 | $0.10 | 134 | 0.76 | 17.40 | 12.92 | ||
Gemma 4 31B | 262k | Offen | 15 | $0.05 | 45 | 2.05 | 52.08 | 38.84 | ||
Mistral Medium 3.5 | 262k | Offen | 14 | $0.50 | 159 | 2.25 | 17.96 | 12.57 | ||
Gemma 4 12B | 262k | Offen | 14* | -- | 120 | 2.24 | 23.12 | 16.70 | ||
Nova 2.0 Pro Preview (medium) | 256k | Proprietär | 14* | -- | 125 | 11.38 | 31.40 | 16.02 | ||
Gemma 4 31B (non-reasoning) (NVFP4) | 262k | Offen | 14* | -- | 277 | 0.39 | 2.19 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Offen | 14* | -- | 70 | 1.36 | 8.48 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Offen | 14* | -- | 143 | 0.72 | 4.21 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Offen | 14* | -- | 45 | 1.94 | 12.97 | -- | ||
Gemma 4 31B (non-reasoning) (FP8) | 262k | Offen | 14* | -- | 8 | 3.32 | 64.74 | -- | ||
Gemma 4 31B (non-reasoning) | 131k | Offen | 14* | -- | 206 | 3.06 | 5.49 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Offen | 14* | -- | 48 | 0.86 | 11.24 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Offen | 14* | -- | 21 | 2.38 | 26.59 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Offen | 14* | -- | 46 | 2.06 | 12.98 | -- | ||
Gemma 4 31B (non-reasoning) (FP8) | 262k | Offen | 14* | -- | 25 | 1.39 | 21.39 | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietär | 13* | -- | 182 | 16.05 | 29.78 | 10.98 | ||
Qwen3.5 9B (non-reasoning) (FP8) | 262k | Offen | 13* | -- | 78 | 0.81 | 7.20 | -- | ||
Command A+ | 200k | Offen | 13 | $0.00 | 149 | 0.53 | 17.34 | 13.44 | ||
Gemma 4 26B A4B (non-reasoning) | 262k | Offen | 13* | -- | 75 | 1.31 | 7.95 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 131k | Offen | 13* | -- | 531 | 0.95 | 1.89 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | Offen | 13* | -- | 186 | 0.82 | 3.52 | -- | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | 262k | Offen | 13* | -- | 16 | 2.18 | 32.68 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | Offen | 13* | -- | 63 | 0.77 | 8.67 | -- | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | 262k | Offen | 13* | -- | 78 | 0.78 | 7.22 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | Offen | 13* | -- | 96 | 1.10 | 6.32 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 1M | Offen | 13* | -- | 127 | 0.87 | 4.81 | -- | ||
Qwen3.5 4B (FP8) | 262k | Offen | 13* | -- | 17 | 0.86 | 149.52 | 118.93 | ||
Nemotron 3.5 Lightning (NVFP4) | 262k | Offen | 13 | $0.09 | 98 | 0.71 | 26.24 | 20.42 | ||
Nemotron 3.5 Lightning (BF16) | 1.05M | Offen | 13 | $0.09 | 247 | 1.02 | 11.16 | 8.11 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Offen | 13 | $0.07 | 354 | 0.58 | 7.63 | 5.64 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Offen | 13 | $0.02 | 408 | 0.47 | 6.59 | 4.90 | ||
Nemotron 3.5 Lightning (NVFP4) | 1.05M | Offen | 13 | $0.07 | 635 | 0.74 | 4.67 | 3.15 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Offen | 13 | $0.08 | 285 | 0.48 | 9.24 | 7.01 | ||
Nova 2.0 Pro Preview (low) | 256k | Proprietär | 13* | -- | 119 | 10.64 | 31.60 | 16.77 | ||
Granite 4.2 30B | 131k | Offen | 13 | $0.07 | 75 | 0.67 | 34.22 | 26.84 | ||
Nova 2.0 Lite (medium) | 1M | Proprietär | 12* | -- | 177 | 11.87 | 26.02 | 11.32 | ||
Qwen3.5 Omni Flash | 256k | Proprietär | 12* | -- | 234 | 1.79 | 3.92 | -- | ||
Mercury 2.5 | 256k | Proprietär | 12 | $0.12 | 689 | 3.71 | 4.43 | -- | ||
Nova 2.0 Lite (low) | 1M | Proprietär | 12* | -- | 175 | 8.89 | 23.18 | 11.43 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | -- | 472 | 0.67 | 5.97 | 4.24 | ||
gpt-oss-120b (high) | 128k | Offen | 12 | $0.12 | 82 | 1.37 | 31.81 | 24.35 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.02 | 99 | 1.28 | 26.49 | 20.17 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.04 | 205 | 1.02 | 13.24 | 9.78 | ||
gpt-oss-120b (high) (Turbo) | 131k | Offen | 12 | $0.11 | 50 | 0.69 | 50.34 | 39.72 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.11 | 369 | 0.74 | 7.51 | 5.42 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.03 | 54 | 0.66 | 46.85 | 36.95 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.23 | 1,748 | 0.39 | 1.82 | 1.14 | ||
gpt-oss-120b (high) Vertex | 131k | Offen | 12 | $0.06 | 148 | 1.23 | 18.07 | 13.47 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.11 | 100 | 0.57 | 25.58 | 20.01 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.04 | 307 | 0.44 | 8.58 | 6.51 | ||
gpt-oss-120b (high) | 128k | Offen | 12 | $0.07 | 206 | 0.18 | 12.31 | 9.70 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.15 | 707 | 1.14 | 4.68 | 2.83 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.06 | 297 | 0.81 | 9.22 | 6.73 | ||
gpt-oss-120b (high) (Base) | 128k | Offen | 12 | $0.11 | 359 | 0.95 | 7.90 | 5.57 | ||
gpt-oss-120b (high) | 131k | Offen | 12 | $0.11 | 96 | 1.04 | 26.95 | 20.73 | ||
Mistral Small 4 | 256k | Offen | 11 | $0.02 | 183 | 0.90 | 14.55 | 10.92 | ||
Qwen3.5 9B (FP8) | 262k | Offen | 11 | $0.16 | 25 | 2.43 | 102.93 | 80.39 | ||
Qwen3.5 9B (FP8) | 262k | Offen | 11 | $0.27 | 79 | 0.77 | 32.33 | 25.25 | ||
Granite 4.2 8B | 131k | Offen | 11 | $0.05 | 89 | 0.74 | 28.75 | 22.40 | ||
Granite 4.2 8B | 131k | Offen | 11 | $0.02 | 87 | 0.72 | 29.58 | 23.09 | ||
Ling 3.0 Tiny | 262k | Offen | 11 | $0.00 | 57 | 2.53 | 46.17 | 34.92 | ||
Trinity Large Thinking | 262k | Offen | 11 | $0.12 | 357 | 1.25 | 8.25 | 5.60 | ||
Qwen3.5 4B (non-reasoning) FP8 | 262k | Offen | 11* | -- | 11 | 1.05 | 46.01 | -- | ||
Nemotron 3 Nano Omni 30B A3B | 262k | Offen | 10* | -- | 237 | 0.35 | 10.92 | 8.45 | ||
Nemotron 3 Nano Omni 30B A3B | 65.5k | Offen | 10* | -- | 234 | 1.04 | 11.74 | 8.56 | ||
gpt-oss-120b (low) Base | 128k | Offen | 10* | -- | 368 | 0.90 | 7.69 | 5.43 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 740 | 1.10 | 4.47 | 2.70 | ||
gpt-oss-120b (low) Vertex | 131k | Offen | 10* | -- | 118 | 1.03 | 22.25 | 16.97 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 469 | 0.71 | 6.05 | 4.27 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 284 | 0.46 | 9.25 | 7.03 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 49 | 0.64 | 51.69 | 40.84 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 81 | 1.25 | 32.28 | 24.82 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 1,833 | 0.38 | 1.75 | 1.09 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 418 | 0.73 | 6.71 | 4.78 | ||
gpt-oss-120b (low) | 128k | Offen | 10* | -- | 189 | 0.19 | 13.42 | 10.58 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 105 | 1.05 | 24.88 | 19.07 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 293 | 0.84 | 9.36 | 6.82 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 106 | 0.50 | 24.00 | 18.80 | ||
gpt-oss-120b (low) | 131k | Offen | 10* | -- | 238 | 0.92 | 11.41 | 8.39 | ||
Nova 2.0 Pro Preview (non-reasoning) | 256k | Proprietär | 10* | -- | 111 | 0.98 | 5.48 | -- | ||
gpt-oss-20b (low) | 131k | Offen | 10* | -- | 870 | 0.81 | 3.69 | 2.30 | ||
gpt-oss-20b (low) | 131k | Offen | 10* | -- | 121 | 0.58 | 21.18 | 16.49 | ||
gpt-oss-20b (low) | 131k | Offen | 10* | -- | 155 | 9.32 | 25.49 | 12.94 | ||
North Mini Code | 256k | Offen | 10 | $0.00 | 60 | 0.45 | 41.94 | 33.19 | ||
Qwen3 Next 80B A3B | 262k | Offen | 10* | -- | 50 | 0.96 | 11.00 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 10* | -- | 106 | 0.72 | 5.43 | -- | ||
Qwen3 Next 80B A3B | 262k | Offen | 10* | -- | 152 | 0.85 | 4.15 | -- | ||
Gemma 4 12B (non-reasoning) | 262k | Offen | 9* | -- | 127 | 2.22 | 6.14 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Offen | 9 | $0.04 | 44 | 1.04 | 12.34 | -- | ||
Llama 4 Maverick (FP8) | 128k | Offen | 9 | $0.04 | 230 | 1.49 | 3.67 | -- | ||
Llama 4 Maverick | 128k | Offen | 9 | $0.04 | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Offen | 9 | $0.03 | 42 | 0.78 | 12.60 | -- | ||
Llama 4 Maverick | 128k | Offen | 9 | $0.01 | 16 | 1.00 | 32.67 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Offen | 9 | $0.03 | 85 | 1.06 | 6.91 | -- | ||
Qwen3 Coder Next | 128k | Offen | 9 | $0.78 | 109 | 1.14 | 5.72 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Offen | 9 | $0.12 | 80 | 0.96 | 7.19 | -- | ||
Granite 4.2 3B | 131k | Offen | 9 | $0.01 | 99 | 0.77 | 25.92 | 20.12 | ||
Mistral Small 4 (non-reasoning) | 262k | Offen | 9* | -- | 171 | 0.92 | 3.84 | -- | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.01 | 142 | 0.58 | 18.16 | 14.06 | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.01 | 159 | 30.93 | 46.64 | 12.57 | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.01 | 119 | 0.52 | 21.55 | 16.83 | ||
gpt-oss-20b (high) | 131k | Offen | 9 | $0.02 | 863 | 0.78 | 3.68 | 2.32 | ||
Gemma 4 E4B | 131k | Offen | 9 | $0.01 | 41 | 0.94 | 62.58 | 49.31 | ||
Nemotron 3 Nano | 262k | Offen | 9 | $0.02 | 191 | 1.01 | 14.08 | 10.45 | ||
Nemotron 3 Nano (FP4) | 262k | Offen | 9 | $0.02 | 241 | 0.99 | 11.38 | 8.31 | ||
Nemotron 3 Nano | 262k | Offen | 9 | $0.02 | 95 | 0.77 | 27.02 | 21.01 | ||
Nemotron 3 Nano (FP8) | 262k | Offen | 9 | $0.01 | 285 | 0.37 | 9.15 | 7.02 | ||
Sarvam 105B (high) | 128k | Offen | 9* | -- | 192 | 1.59 | 14.60 | 10.41 | ||
Nova 2.0 Lite (non-reasoning) | 1M | Proprietär | 9* | -- | 176 | 1.05 | 3.90 | -- | ||
Magistral Small 1.2 | 128k | Offen | 9* | -- | 78 | 1.48 | 33.45 | 25.58 | ||
Qwen3 Omni 30B A3B | 65.5k | Offen | 8* | -- | 102 | 1.84 | 26.24 | 19.52 | ||
Llama 3.3 70B | 131k | Offen | 8* | -- | 314 | 0.90 | 2.50 | -- | ||
Llama 3.3 70B | 131k | Offen | 8* | -- | 45 | 1.70 | 12.93 | -- | ||
Llama 3.3 70B | 128k | Offen | 8* | -- | 305 | 1.95 | 3.59 | -- | ||
Llama 3.3 70B (FP8) | 131k | Offen | 8* | -- | 78 | 2.35 | 8.77 | -- | ||
Llama 3.3 70B | 128k | Offen | 8* | -- | 93 | 0.84 | 6.20 | -- | ||
Llama 3.3 70B Turbo | 131k | Offen | 8* | -- | 64 | 1.83 | 9.66 | -- | ||
Llama 3.3 70B | 128k | Offen | 8* | -- | 131 | 2.11 | 5.91 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | Offen | 8* | -- | 17 | 2.15 | 32.03 | -- | ||
Llama 3.3 70B | 128k | Offen | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B | 100k | Offen | 8* | -- | 80 | 1.29 | 7.58 | -- | ||
Hermes 4 405B (FP8) | 128k | Offen | 7* | -- | 41 | 2.30 | 63.34 | 48.83 | ||
Gemma 4 E4B (non-reasoning) | 131k | Offen | 7* | -- | 49 | 0.83 | 11.03 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Offen | 7* | -- | 95 | 0.79 | 27.08 | 21.04 | ||
Hermes 4 405B (non-reasoning) (FP8) | 128k | Offen | 7* | -- | 40 | 2.28 | 14.72 | -- | ||
Command A | 288k | Offen | 7* | -- | 51 | 1.72 | 11.62 | -- | ||
Command A | 256k | Offen | 7* | -- | 42 | 3.04 | 14.96 | -- | ||
Nemotron 3 Nano (non-reasoning) (FP4) | 262k | Offen | 7* | -- | 266 | 1.01 | 2.89 | -- | ||
Nemotron 3 Nano (non-reasoning) | 262k | Offen | 7* | -- | 92 | 0.77 | 6.21 | -- | ||
Nemotron 3 Nano (non-reasoning) (FP8) | 262k | Offen | 7* | -- | 287 | 0.37 | 2.12 | -- | ||
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | 131k | Offen | 7* | -- | 103 | 0.57 | 5.42 | -- | ||
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | 131k | Offen | 7* | -- | 169 | 1.13 | 4.08 | -- | ||
Llama 4 Scout | 128k | Offen | 6 | $0.12 | 130 | 0.83 | 4.67 | -- | ||
Llama 4 Scout Vertex | 1.31M | Offen | 6 | $0.16 | 156 | 0.71 | 3.90 | -- | ||
Llama 4 Scout | 131k | Offen | 6 | $0.06 | 24 | 1.26 | 21.87 | -- | ||
Llama 4 Scout | 128k | Offen | 6 | $0.11 | -- | -- | -- | -- | ||
Llama 4 Scout | 131k | Offen | 6 | $0.11 | 20 | 1.08 | 25.96 | -- | ||
Celeris-1 | 131k | Proprietär | 6 | $0.05 | 1,581 | 0.55 | 0.87 | -- | ||
Phi-4 Mini | 128k | Offen | 6* | -- | 46 | 0.82 | 11.78 | -- | ||
Ministral 3 14B | 262k | Offen | 6 | $0.02 | 83 | 0.95 | 6.98 | -- | ||
Ministral 3 14B | 256k | Offen | 6 | $0.14 | 192 | 1.05 | 3.65 | -- | ||
Ministral 3 14B | 262k | Offen | 6 | $0.03 | 38 | 1.04 | 14.36 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | Offen | 6* | -- | 96 | 1.78 | 6.97 | -- | ||
Phi-4 | 16.4k | Offen | 6* | -- | 38 | 2.67 | 15.83 | -- | ||
Phi-4 | 16.4k | Offen | 6* | -- | 90 | 1.11 | 6.68 | -- | ||
Nova Micro | 130k | Proprietär | 6* | -- | 280 | 0.86 | 2.65 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (non-reasoning) | 128k | Offen | 6* | -- | 202 | 1.12 | 3.59 | -- | ||
Phi-4 Multimodal | 4.1k | Offen | 6* | -- | -- | -- | -- | -- | ||
Reka Flash 3 | 54k | Offen | 6* | -- | 88 | 1.43 | 29.84 | 22.72 | ||
Ministral 3 8B | 256k | Offen | 5 | $0.07 | 247 | 1.07 | 3.10 | -- | ||
Ministral 3 8B | 262k | Offen | 5 | $0.01 | 113 | 0.86 | 5.28 | -- | ||
Llama 3.2 11B (Vision) | 131k | Offen | 5* | -- | 23 | 1.28 | 23.14 | -- | ||
Ministral 3 3B | 256k | Offen | 5 | $0.04 | 430 | 0.96 | 2.12 | -- | ||
Ministral 3 3B | 131k | Offen | 5 | $0.01 | 207 | 0.68 | 3.09 | -- | ||
Tiny Aya Global | 8.19k | Offen | 5* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | Offen | 5* | -- | 131 | 3.22 | 7.04 | -- | ||
GPT-6 Sol (Daybreak Blue, max) | 1.05M | Proprietär | -- | -- | -- | -- | -- | -- | ||