LLM API 服务商排行榜——比较 500 多个 AI 模型接入点
比较 OpenAI、Google、DeepSeek 等 API 服务商在 500 多个 AI 模型接入点上的表现,涵盖价格、输出速度、延迟、上下文窗口等关键性能指标。
如需了解包括方法论在内的更多详情,请参阅我们的常见问题。
进一步分析 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Claude Fable 5.1 (max with fallback) | 1M | 专有 | 53 | $7.63 | 65 | 213.23 | 220.92 | -- | ||
Claude Fable 5.1 (xhigh with fallback) | 1M | 专有 | 53 | $5.98 | 60 | 85.78 | 94.16 | -- | ||
GPT-6 Astra (max) | 1M | 专有 | 53 | $3.26 | 58 | 334.04 | 342.65 | -- | ||
GPT-6 Astra (xhigh) | 1M | 专有 | 53 | $2.31 | 55 | 126.39 | 135.51 | -- | ||
Claude Fable 5.1 (high with fallback) | 1M | 专有 | 51 | $3.91 | 55 | 16.16 | 25.26 | -- | ||
GPT-6 Astra (high) | 1M | 专有 | 51 | $1.72 | 52 | 36.95 | 46.49 | -- | ||
Claude Opus 5 (max) | 1M | 专有 | 51 | $5.86 | 53 | 58.38 | 67.84 | -- | ||
Claude Opus 5 (max) | 1M | 专有 | 51 | $5.86 | 52 | 49.69 | 59.36 | -- | ||
Claude Opus 5 (max) | 1M | 专有 | 51 | $9.38 | 52 | 51.15 | 60.73 | -- | ||
Claude Fable 5 (with fallback) | 1M | 专有 | 50 | $8.75 | 61 | 83.53 | 91.78 | -- | ||
Claude Fable 5 (with fallback) | 1M | 专有 | 50 | $9.66 | 59 | 92.67 | 101.17 | -- | ||
Claude Fable 5 (with fallback) | 1M | 专有 | 50 | $43.25 | 57 | 78.66 | 87.46 | -- | ||
GPT-6 Astra (medium) | 1M | 专有 | 50 | $1.54 | 51 | 3.85 | 13.70 | -- | ||
Claude Opus 5 (xhigh) | 1M | 专有 | 50 | $4.88 | 53 | 28.90 | 38.31 | -- | ||
Claude Opus 5 (xhigh) | 1M | 专有 | 50 | $7.75 | 53 | 32.46 | 41.81 | -- | ||
Claude Opus 5 (xhigh) | 1M | 专有 | 50 | $4.88 | 52 | 40.54 | 50.20 | -- | ||
Claude Fable 5.1 (medium with fallback) | 1M | 专有 | 49 | $2.98 | 54 | 11.26 | 20.59 | -- | ||
Claude Opus 5 (high) | 1M | 专有 | 48 | $3.61 | 51 | 11.51 | 21.34 | -- | ||
Claude Opus 5 (high) | 1M | 专有 | 48 | $5.64 | 53 | 12.35 | 21.78 | -- | ||
Claude Opus 5 (high) | 1M | 专有 | 48 | $3.61 | 52 | 17.68 | 27.25 | -- | ||
Muse Spark 1.3 (max) | 1.05M | 专有 | 48 | $1.60 | 230 | 22.41 | 33.28 | 8.70 | ||
GPT-5.6 Sol (max) | 1M | 专有 | 47 | $3.70 | 110 | 89.07 | 93.63 | -- | ||
GPT-5.6 Sol (max) | 1M | 专有 | 47 | $1.99 | 59 | 130.99 | 139.50 | -- | ||
GPT-5.6 Sol (max) | 524k | 专有 | 47 | -- | 98 | 91.90 | 96.99 | -- | ||
Claude Fable 5.1 (low with fallback) | 1M | 专有 | 47 | $2.37 | 53 | 4.72 | 14.16 | -- | ||
GPT-6 Astra (low) | 1M | 专有 | 46 | $0.82 | 51 | 2.42 | 12.18 | -- | ||
Muse Spark 1.3 (xhigh) | 1.05M | 专有 | 45 | $1.37 | 217 | 22.12 | 33.66 | 9.23 | ||
Claude Opus 5 (medium) | 1M | 专有 | 45 | $2.19 | 51 | 3.83 | 13.59 | -- | ||
Claude Opus 5 (medium) | 1M | 专有 | 45 | $2.19 | 51 | 4.39 | 14.18 | -- | ||
Claude Opus 5 (medium) | 1M | 专有 | 45 | $3.32 | 52 | 5.11 | 14.67 | -- | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.01 | 72 | 3.08 | 37.74 | 27.72 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $2.16 | 138 | 1.04 | 19.18 | 14.51 | ||
GLM-5.3 (max) | 164k | 开放 | 45 | $2.05 | 50 | 12.93 | 62.92 | 40.00 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $1.73 | 39 | 1.05 | 65.04 | 51.19 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $1.97 | 114 | 1.13 | 23.06 | 17.54 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $2.58 | 230 | 0.63 | 11.51 | 8.70 | ||
GLM-5.3 (max) (FAST) | 1M | 开放 | 45 | $4.08 | 387 | 0.98 | 7.45 | 5.17 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $8.68 | 79 | 2.26 | 34.05 | 25.43 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $1.43 | 126 | 1.39 | 21.22 | 15.86 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $1.90 | 292 | 1.05 | 9.61 | 6.85 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.01 | 246 | 1.02 | 11.17 | 8.12 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $6.82 | 137 | 0.87 | 19.08 | 14.57 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.01 | 215 | 1.08 | 12.69 | 9.28 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.01 | 202 | 0.84 | 13.19 | 9.88 | ||
GLM-5.3 (max) (FAST) | 1M | 开放 | 45 | $2.15 | 209 | 1.20 | 13.15 | 9.56 | ||
GLM-5.3 (max) (FP4) | 1M | 开放 | 45 | $8.68 | 369 | 1.96 | 8.73 | 5.42 | ||
Grok 4.6 (high) | 500k | 专有 | 44 | $1.86 | 57 | 39.70 | 48.52 | -- | ||
Grok 4.6 (xhigh) | 500k | 专有 | 44 | $2.32 | 55 | 41.74 | 50.90 | -- | ||
GPT-5.6 Sol (xhigh) | 1M | 专有 | 44 | $1.18 | 60 | 49.68 | 58.01 | -- | ||
GPT-5.6 Sol (xhigh) | 524k | 专有 | 44 | $1.26 | 94 | 31.12 | 36.45 | -- | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $1.81 | 114 | 0.81 | 22.72 | 17.52 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $4.34 | 47 | 0.84 | 54.24 | 42.72 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $2.25 | 39 | 1.24 | 65.50 | 51.41 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $2.01 | 95 | 0.78 | 27.18 | 21.12 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $2.42 | 48 | 1.24 | 53.20 | 41.56 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $1.21 | 50 | 3.29 | 53.61 | 40.25 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $9.22 | 186 | 1.57 | 15.00 | 10.75 | ||
Kimi K3 (max) | 205k | 开放 | 44 | $1.85 | 163 | 0.94 | 16.30 | 12.29 | ||
Kimi K3 (max) | 262k | 开放 | 44 | $2.70 | 89 | 1.66 | 29.88 | 22.58 | ||
Kimi K3 (max) (FAST) | 1.05M | 开放 | 44 | $3.77 | 246 | 1.76 | 11.92 | 8.13 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $2.00 | 36 | 4.69 | 74.71 | 56.02 | ||
Grok 4.6 (medium) | 500k | 专有 | 43 | $1.50 | 52 | 37.04 | 46.59 | -- | ||
GPT-5.6 Sol (high) | 1M | 专有 | 42 | $0.81 | 57 | 15.19 | 23.95 | -- | ||
GPT-5.6 Sol (high) | 524k | 专有 | 42 | $0.85 | 85 | 8.26 | 14.11 | -- | ||
GPT-5.6 Terra (max) | 1M | 专有 | 42 | $1.40 | 113 | 162.00 | 166.41 | -- | ||
GPT-5.6 Terra (max) | 1M | 专有 | 42 | $1.95 | 140 | 122.20 | 125.77 | -- | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.25 | 107 | 2.45 | 25.82 | 18.70 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.30 | 181 | 0.73 | 14.53 | 11.04 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.29 | 102 | 1.58 | 26.02 | 19.56 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.43 | 30 | 1.44 | 84.71 | 66.62 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.29 | 107 | 1.41 | 24.88 | 18.77 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.29 | 23 | 1.06 | 110.49 | 87.54 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.36 | 99 | 0.69 | 25.99 | 20.24 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.30 | 179 | 1.53 | 15.46 | 11.15 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.28 | 230 | 0.69 | 11.56 | 8.70 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.42 | 103 | 2.64 | 26.79 | 19.33 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.28 | 110 | 1.14 | 23.93 | 18.23 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.14 | 111 | 8.17 | 30.78 | 18.08 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.28 | 136 | 1.25 | 19.56 | 14.65 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $1.19 | 285 | 0.54 | 9.32 | 7.03 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.33 | 112 | 0.96 | 23.22 | 17.80 | ||
GLM-5.3-Flash (FAST) | 1M | 开放 | 42 | $0.46 | 467 | 5.61 | 10.97 | 4.29 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.56 | 88 | 0.93 | 29.19 | 22.61 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.76 | 153 | 1.48 | 17.78 | 13.04 | ||
Gemini 3.8 Flash (high) AI Studio | 1M | 专有 | 41 | $1.24 | 278 | 13.00 | 14.80 | -- | ||
Qwen3.8 Max | 1M | 专有 | 40 | $2.67 | 41 | 2.74 | 64.18 | 49.15 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 40 | $1.87 | 109 | 1.04 | 23.95 | 18.33 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 40 | $2.77 | 179 | 0.90 | 14.89 | 11.20 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 40 | $2.89 | 89 | 1.43 | 29.63 | 22.56 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 40 | $1.80 | 60 | 2.05 | 43.39 | 33.07 | ||
Qwen3.8 2.4T A95B (FP8) | 262k | 开放 | 40 | $1.54 | 105 | 3.39 | 27.21 | 19.06 | ||
Qwen3.8 2.4T A95B | 984k | 开放 | 40 | $2.16 | 40 | 2.78 | 64.83 | 49.64 | ||
Gemini 3.8 Flash (medium) AI Studio | 1M | 专有 | 40 | $0.93 | -- | -- | -- | -- | ||
Qwen3.8-Flash-Next | 1M | 开放 | 40 | $0.37 | 51 | 2.73 | 51.56 | 39.06 | ||
Qwen3.8-Flash-Next (NVFP4) | 262k | 开放 | 40 | $0.44 | 112 | 1.29 | 23.60 | 17.85 | ||
Muse Spark 1.2 (xhigh) | 1.05M | 专有 | 40 | $0.97 | 178 | 18.48 | 32.54 | 11.25 | ||
Claude Opus 5 (low) | 1M | 专有 | 40 | $1.10 | 53 | 2.47 | 11.90 | -- | ||
Claude Opus 5 (low) | 1M | 专有 | 40 | $1.10 | 52 | 2.69 | 12.27 | -- | ||
Claude Opus 5 (low) | 1M | 专有 | 40 | $1.57 | 51 | 3.22 | 13.04 | -- | ||
Gemini 3.7 Flash (medium) AI Studio | 1M | 专有 | 40* | -- | 279 | 4.96 | 6.75 | -- | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 40 | $0.27 | 214 | 1.17 | 12.83 | 9.33 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 40 | $2.18 | 307 | 0.67 | 8.82 | 6.52 | ||
GPT-5.6 Sol (medium) | 1M | 专有 | 39 | $0.50 | 60 | 3.64 | 12.01 | -- | ||
Gemini 3.7 Flash (high) AI Studio | 1M | 专有 | 39 | $0.93 | 288 | 10.22 | 11.95 | -- | ||
Grok 4.5 (high) | 500k | 专有 | 39 | $1.04 | 60 | 6.84 | 15.24 | -- | ||
Claude Sonnet 5 (max) | 1M | 专有 | 38 | $7.36 | 71 | 183.01 | 190.03 | -- | ||
Claude Sonnet 5 (max) | 1M | 专有 | 38 | $4.75 | 71 | 180.61 | 187.61 | -- | ||
Claude Sonnet 5 (max) | 1M | 专有 | 38 | $5.09 | 76 | 215.96 | 222.57 | -- | ||
Claude Sonnet 5 (max) | 1M | 专有 | 38 | $6.21 | 77 | 201.68 | 208.18 | -- | ||
GPT-5.6 Terra (xhigh) | 1M | 专有 | 38 | $0.63 | 102 | 21.09 | 25.98 | -- | ||
GPT-5.6 Terra (xhigh) | 524k | 专有 | 38 | $0.67 | 106 | 20.29 | 25.00 | -- | ||
GPT-5.6 Luna (max) | 1M | 专有 | 38 | $0.18 | 120 | 124.21 | 128.39 | -- | ||
GPT-5.6 Luna (max) | 1M | 专有 | 38 | $1.02 | 228 | 80.25 | 82.44 | -- | ||
Gemini 3.7 Flash (low) AI Studio | 1M | 专有 | 37* | -- | 298 | 0.81 | 2.48 | -- | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $0.67 | 82 | 1.70 | 32.15 | 24.36 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $1.61 | 67 | 3.14 | 40.29 | 29.72 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $6.15 | 64 | 1.85 | 40.85 | 31.20 | ||
DeepSeek V4 Pro 0813 (max) | 1M | 开放 | 36 | $0.60 | 87 | 1.63 | 30.26 | 22.90 | ||
DeepSeek V4 Pro 0813 (max) | 1M | 开放 | 36 | $6.17 | 162 | 1.04 | 16.43 | 12.32 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $1.65 | 185 | 1.67 | 15.17 | 10.80 | ||
DeepSeek V4 Pro 0813 (max) | 1M | 开放 | 36 | $1.00 | 114 | 0.92 | 22.78 | 17.49 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $0.70 | 70 | 1.87 | 37.42 | 28.44 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $0.83 | 42 | 0.98 | 60.85 | 47.90 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $8.43 | 69 | 2.41 | 38.77 | 29.09 | ||
Agnes 3.0 Flash | 1M | 专有 | 36* | -- | 235 | 1.84 | 12.50 | 8.52 | ||
Grok 4.6 (low) | 500k | 专有 | 35 | $0.48 | 52 | 5.31 | 14.89 | -- | ||
Agnes 2.5 Pro Beta | 1M | 专有 | 35* | -- | -- | -- | -- | -- | ||
DeepSeek V4 Flash Vision (max) | 1M | 专有 | 35 | $0.31 | 213 | 1.30 | 13.03 | 9.38 | ||
DeepSeek V4 Flash Vision (max) | 1M | 专有 | 35 | $0.12 | 143 | 0.91 | 18.39 | 13.99 | ||
GPT-5.6 Luna (xhigh) | 1M | 专有 | 35 | $0.09 | 117 | 52.08 | 56.37 | -- | ||
GPT-5.6 Luna (xhigh) | 524k | 专有 | 35 | $0.09 | 126 | 50.60 | 54.55 | -- | ||
Claude Sonnet 5 (xhigh) | 1M | 专有 | 35 | $2.87 | 66 | 24.85 | 32.45 | -- | ||
DeepSeek V4 Flash 0731 (max) | 262k | 开放 | 35 | $0.38 | 145 | 1.63 | 18.85 | 13.78 | ||
DeepSeek V4 Flash 0731 (max) (FAST) | 1M | 开放 | 35 | $0.90 | 151 | 0.80 | 17.41 | 13.28 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 35 | $0.65 | 307 | 2.07 | 10.21 | 6.51 | ||
DeepSeek V4 Flash 0731 (max) | 1M | 开放 | 35 | $0.22 | 213 | 1.43 | 13.16 | 9.38 | ||
DeepSeek V4 Flash 0731 (max) | 1M | 开放 | 35 | $0.10 | 131 | 1.52 | 20.60 | 15.27 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 35 | $0.41 | 179 | 1.50 | 15.44 | 11.15 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 35 | $0.09 | 256 | 0.62 | 10.39 | 7.81 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 35 | $0.85 | 86 | 2.57 | 31.59 | 23.22 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 35 | $0.44 | 257 | 0.64 | 10.39 | 7.80 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 35 | $0.19 | 318 | 1.00 | 8.86 | 6.29 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 35 | $0.58 | 156 | 2.71 | 18.71 | 12.80 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 35 | $0.26 | 207 | 1.59 | 13.64 | 9.64 | ||
DeepSeek V4 Flash 0731 (max) | 1M | 开放 | 35 | $0.10 | 55 | 0.89 | 46.42 | 36.42 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 35 | $0.33 | 57 | 0.95 | 45.12 | 35.34 | ||
DeepSeek V4 Flash 0731 (max) | 1M | 开放 | 35 | $0.42 | 126 | 0.80 | 20.68 | 15.91 | ||
GPT-5.6 Terra (high) | 1M | 专有 | 34 | $0.34 | 92 | 2.48 | 7.90 | -- | ||
GPT-5.6 Terra (high) | 524k | 专有 | 34 | $0.35 | 108 | 2.44 | 7.09 | -- | ||
Gemini 3.6 Flash AI Studio | 1M | 专有 | 34 | $0.93 | 183 | 17.92 | 20.65 | -- | ||
GLM-5.2 (max) | 1M | 开放 | 34 | $0.87 | 149 | 0.75 | 17.51 | 13.41 | ||
GLM-5.2 (max) (FAST) | 524k | 开放 | 34 | $1.04 | 277 | 1.88 | 10.91 | 7.23 | ||
GLM-5.2 (max) (FP8) | 1.05M | 开放 | 34 | $0.88 | 77 | 1.78 | 34.38 | 26.08 | ||
GLM-5.2 (max) (NVFP4) | 1M | 开放 | 34 | -- | 184 | 1.14 | 14.74 | 10.89 | ||
GLM-5.2 (max) | 262k | 开放 | 34 | $0.96 | 209 | 1.21 | 13.16 | 9.56 | ||
GLM-5.2 (max) | 1M | 开放 | 34 | $2.31 | 91 | 1.05 | 28.41 | 21.89 | ||
GLM-5.2 (max) (FP4) | 1.05M | 开放 | 34 | $0.65 | 66 | 1.04 | 38.79 | 30.20 | ||
GLM-5.2 (max) (FP4) | 432k | 开放 | 34 | $2.94 | 336 | 1.07 | 8.53 | 5.96 | ||
GLM-5.2 (max) | 262k | 开放 | 34 | $1.05 | 238 | 0.69 | 11.20 | 8.41 | ||
GLM-5.2 (max) | 262k | 开放 | 34 | $4.37 | 96 | 1.67 | 27.78 | 20.89 | ||
GLM-5.2 (max) | 1M | 开放 | 34 | $0.87 | 317 | 0.80 | 8.68 | 6.31 | ||
GLM-5.2 (max) (NVFP4) | 1M | 开放 | 34 | $1.01 | 246 | 1.05 | 11.23 | 8.15 | ||
GLM-5.2 (max) | 1M | 开放 | 34 | $0.33 | 56 | 2.30 | 47.27 | 35.98 | ||
GLM-5.2 (max) | 1M | 开放 | 34 | $0.64 | 224 | 1.53 | 12.68 | 8.92 | ||
GLM-5.2 (max) (FP8) | 1.05M | 开放 | 34 | -- | -- | -- | -- | -- | ||
GLM-5.2 (max) | 1.05M | 开放 | 34 | $0.65 | 132 | 1.82 | 20.74 | 15.14 | ||
GLM-5.2 (max) | 164k | 开放 | 34 | $0.88 | 212 | 1.51 | 13.31 | 9.44 | ||
GLM-5.2 (max) | 1M | 开放 | 34 | $0.96 | 78 | 7.77 | 40.01 | 25.79 | ||
GLM-5.2 (max) | 1.05M | 开放 | 34 | $0.76 | 172 | 0.96 | 15.47 | 11.61 | ||
GLM-5.2 (max) (FP8) | 1.05M | 开放 | 34 | $0.85 | 101 | 2.19 | 26.99 | 19.84 | ||
Qwen3.8 27B (xhigh) | 262k | 开放 | 34 | $0.65 | 35 | 1.02 | 72.49 | 57.18 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | 开放 | 34 | $0.92 | 66 | 1.75 | 39.36 | 30.09 | ||
Qwen3.8 27B (xhigh) | 1M | 开放 | 34 | $0.82 | 45 | 3.79 | 59.74 | 44.76 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | 开放 | 34 | $2.29 | 84 | 1.43 | 31.34 | 23.93 | ||
Qwen3.8 27B (xhigh) | 262k | 开放 | 34 | $1.98 | 196 | 0.89 | 13.64 | 10.20 | ||
GPT-5.6 Sol (low) | 1M | 专有 | 34 | $0.26 | 57 | 3.08 | 11.90 | -- | ||
Gemini 3.8 Flash (low) AI Studio | 1M | 专有 | 34 | -- | -- | -- | -- | -- | ||
Gemini 3.5 Flash (medium) | 1M | 专有 | 34* | -- | 227 | 12.19 | 14.39 | -- | ||
GPT-5.3 Codex (xhigh) | 400k | 专有 | 33* | -- | 126 | 43.93 | 47.91 | -- | ||
GPT-5.6 Luna (high) | 1M | 专有 | 32 | $0.04 | 103 | 8.68 | 13.52 | -- | ||
GPT-5.6 Luna (high) | 524k | 专有 | 32 | $0.05 | 121 | 14.43 | 18.58 | -- | ||
Claude Sonnet 5 (high) | 1M | 专有 | 32 | $1.79 | 61 | 2.76 | 10.99 | -- | ||
DeepSeek V4 Pro (max) (FP4) | 1.05M | 开放 | 31 | $1.19 | 52 | 1.13 | 95.65 | 84.83 | ||
DeepSeek V4 Pro (max) | 1M | 开放 | 31 | $9.65 | 93 | 1.69 | 54.21 | 47.14 | ||
DeepSeek V4 Pro (max) | 1.05M | 开放 | 31 | $1.09 | 74 | 1.86 | 68.08 | 59.43 | ||
DeepSeek V4 Pro (max) | 1M | 开放 | 31 | $0.71 | 85 | 1.98 | 59.57 | 51.68 | ||
DeepSeek V4 Pro (max) (FP8) | 1.05M | 开放 | 31 | -- | 51 | 2.20 | 98.10 | 86.06 | ||
DeepSeek V4 Pro (max) | 1.05M | 开放 | 31 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) | 1M | 开放 | 31 | $9.70 | 115 | 1.33 | 43.78 | 38.09 | ||
DeepSeek V4 Pro (max) | 1M | 开放 | 31 | $3.73 | 141 | 0.56 | 35.23 | 31.12 | ||
DeepSeek V4 Pro (max) | 1M | 开放 | 31 | $0.12 | 78 | 1.66 | 63.84 | 55.80 | ||
Kimi K3 (low) | 1.05M | 开放 | 30 | $1.15 | 35 | 3.90 | 74.70 | 56.64 | ||
Kimi K3 (low) | 1M | 开放 | 30 | $1.87 | 89 | 0.79 | 28.93 | 22.52 | ||
Kimi K3 (low) | 1M | 开放 | 30 | $0.88 | 154 | 0.99 | 17.27 | 13.02 | ||
GPT-5.6 Terra (medium) | 1M | 专有 | 30 | $0.18 | 94 | 1.82 | 7.12 | -- | ||
Apodex 1.1 | 256k | 专有 | 30* | -- | -- | -- | -- | -- | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | 专有 | 30 | $0.67 | 112 | 28.27 | 32.73 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | 专有 | 30 | $0.98 | 124 | 23.25 | 27.27 | -- | ||
DeepSeek V4 Pro (high) (FP4) | 65.5k | 开放 | 30* | -- | 55 | 1.47 | 46.40 | 35.92 | ||
DeepSeek V4 Pro (high) | 1M | 开放 | 30* | -- | 88 | 1.61 | 29.81 | 22.54 | ||
DeepSeek V4 Pro (high) | 1M | 开放 | 30* | -- | 82 | 1.75 | 32.19 | 24.33 | ||
DeepSeek V4 Pro (high) | 1M | 开放 | 30* | -- | 77 | 2.27 | 34.43 | 25.71 | ||
DeepSeek V4 Pro (high) (FP8) | 1.05M | 开放 | 30* | -- | 50 | 1.89 | 51.79 | 39.89 | ||
DeepSeek V4 Pro (high) | 1M | 开放 | 30* | -- | 119 | 1.30 | 22.18 | 16.69 | ||
DeepSeek V4 Pro (high) | 1.05M | 开放 | 30* | -- | 73 | 1.75 | 35.91 | 27.31 | ||
DeepSeek V4 Pro (high) | 1M | 开放 | 30* | -- | 144 | 0.58 | 17.87 | 13.82 | ||
MiniMax-M3 (MXFP8) | 1M | 开放 | 30 | $0.46 | 129 | 0.94 | 20.26 | 15.45 | ||
MiniMax-M3 (NVFP4) | 262k | 开放 | 30 | $0.40 | 169 | 1.19 | 15.98 | 11.83 | ||
MiniMax-M3 | 1M | 开放 | 30 | $0.70 | 112 | 0.74 | 23.02 | 17.82 | ||
MiniMax-M3 | 1M | 开放 | 30 | $0.46 | 147 | 1.04 | 18.06 | 13.61 | ||
MiniMax-M3 (FAST) | 1.05M | 开放 | 30 | $1.09 | 426 | 1.59 | 7.45 | 4.69 | ||
MiniMax-M3 | 1M | 开放 | 30 | $0.46 | 198 | 0.61 | 13.27 | 10.13 | ||
MiniMax-M3 (FP8) | 1.05M | 开放 | 30 | $1.91 | 307 | 1.84 | 9.98 | 6.51 | ||
MiniMax-M3 (FP8) | 1M | 开放 | 30 | $0.45 | 130 | 1.26 | 20.53 | 15.41 | ||
MiniMax-M3 | 524k | 开放 | 30 | $0.64 | 179 | 2.86 | 16.85 | 11.20 | ||
MiniMax-M3 | 512k | 开放 | 30 | $0.51 | 103 | 1.32 | 25.61 | 19.43 | ||
MiniMax-M3 | 524k | 开放 | 30 | $0.44 | 24 | 1.00 | 106.63 | 84.50 | ||
MiniMax-M3 | 1.05M | 开放 | 30 | -- | -- | -- | -- | -- | ||
MiniMax-M3 | 1.05M | 开放 | 30 | $3.83 | 247 | 2.52 | 12.64 | 8.10 | ||
MiniMax-M3 | 524k | 开放 | 30 | $0.50 | 182 | 0.95 | 14.72 | 11.01 | ||
Claude Sonnet 5 (Non-reasoning) | 1M | 专有 | 29* | -- | 61 | 0.68 | 8.82 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 1M | 专有 | 29* | -- | 60 | 1.70 | 9.97 | -- | ||
Claude Sonnet 5 (medium) | 1M | 专有 | 28 | $1.00 | 59 | 1.18 | 9.66 | -- | ||
GPT-5.6 Sol (Non-reasoning) | 1M | 专有 | 28* | -- | 61 | 1.15 | 9.34 | -- | ||
GPT-5.6 Sol (Non-reasoning) | 1M | 专有 | 28* | -- | 97 | 0.81 | 5.96 | -- | ||
Nex-N2-Pro (FP8) | 262k | 开放 | 28* | -- | -- | -- | -- | -- | ||
Solar Pro 4 | 512k | 专有 | 28* | -- | 75 | 1.95 | 35.33 | 26.70 | ||
GPT-5.6 Terra (low) | 1M | 专有 | 28 | $0.14 | 93 | 1.61 | 6.99 | -- | ||
Qwen3.8 27B (medium) | 1M | 开放 | 28 | $0.90 | 51 | 3.94 | 52.70 | 39.01 | ||
Qwen3.8 27B (medium) | 262k | 开放 | 28 | $2.36 | 192 | 0.99 | 14.01 | 10.42 | ||
Agnes 2.5 Pro Alpha | 1M | 开放 | 28 | -- | 176 | 4.06 | 18.23 | 11.34 | ||
Quasar 438B (max) | 1M | 专有 | 27 | $2.02 | 174 | 1.00 | 15.37 | 11.49 | ||
GPT-5.5 Instant (June 2026) | 400k | 专有 | 27 | $0.69 | 131 | 1.19 | 20.23 | 15.23 | ||
Qwen3.8 27B (low) | 1M | 开放 | 26 | $0.83 | 50 | 4.04 | 53.90 | 39.89 | ||
Qwen3.8 27B (low) | 262k | 开放 | 26 | $2.19 | 196 | 0.92 | 13.69 | 10.22 | ||
MiMo-V2.5-Pro | 1.05M | 开放 | 26 | $0.07 | 38 | 4.29 | 70.89 | 53.28 | ||
MiMo-V2.5-Pro | 1.05M | 开放 | 26 | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | 开放 | 26 | $0.43 | 36 | 1.11 | 70.05 | 55.15 | ||
MiMo-V2.5-Pro | 1M | 开放 | 26 | $0.05 | 37 | 6.14 | 74.53 | 54.72 | ||
Kimi K2.7 Code (FP4) | 256k | 开放 | 26 | $1.89 | 222 | 1.77 | 14.06 | 10.04 | ||
Kimi K2.7 Code (FP8) | 65.5k | 开放 | 26 | $1.20 | 58 | 5.16 | 51.94 | 38.22 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.89 | 272 | 1.13 | 11.15 | 8.18 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.76 | 219 | 0.48 | 12.97 | 10.20 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $1.69 | 203 | 0.64 | 14.09 | 10.98 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.55 | 53 | 3.94 | 55.88 | 42.43 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.39 | 41 | 0.93 | 67.23 | 54.16 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.52 | 122 | 0.69 | 23.01 | 18.23 | ||
Kimi K2.7 Code | 256k | 开放 | 26 | $0.54 | 49 | 2.82 | 59.01 | 45.89 | ||
Inkling Small | 256k | 开放 | 26 | $0.09 | 178 | 2.12 | 16.14 | 11.22 | ||
Inkling Small | 524k | 开放 | 26 | $0.12 | 244 | 0.98 | 11.24 | 8.21 | ||
Inkling Small | 262k | 开放 | 26 | $0.12 | 323 | 0.51 | 8.24 | 6.18 | ||
Qwen3.7 Plus | 1M | 专有 | 26 | $0.33 | 66 | 2.21 | 40.13 | 30.34 | ||
Hy3 (FP8) | 256k | 开放 | 26 | $0.07 | 96 | 2.93 | 28.94 | 20.81 | ||
Hy3 | 262k | 开放 | 26 | $0.07 | 87 | 2.21 | 31.09 | 23.11 | ||
Hy3 (FP8) | 262k | 开放 | 26 | $0.07 | 56 | 1.01 | 46.04 | 36.03 | ||
Hy3 | 262k | 开放 | 26 | $0.07 | 100 | 2.99 | 27.90 | 19.92 | ||
Inkling (FP8) | 131k | 开放 | 26 | $0.81 | 198 | 0.57 | 13.18 | 10.08 | ||
Inkling | 262k | 开放 | 26 | $0.72 | 209 | 0.64 | 12.63 | 9.59 | ||
Inkling | 524k | 开放 | 26 | $0.91 | 114 | 0.62 | 22.46 | 17.47 | ||
Inkling | 262k | 开放 | 26 | $0.61 | 91 | 2.88 | 30.27 | 21.92 | ||
Inkling | 1M | 开放 | 26 | $0.61 | 212 | 0.99 | 12.80 | 9.45 | ||
GPT-5.6 Luna (medium) | 1M | 专有 | 25 | $0.02 | 107 | 2.86 | 7.52 | -- | ||
Ling 3.0 Flash | 131k | 开放 | 25* | -- | 57 | 0.67 | 44.16 | 34.79 | ||
Ling 3.0 Flash | 262k | 开放 | 25* | -- | 276 | 2.65 | 11.71 | 7.25 | ||
Grok 4.3 (medium) | 524k | 专有 | 25* | -- | 280 | 4.10 | 5.89 | -- | ||
Grok 4.3 (medium) | 200k | 专有 | 25* | -- | 168 | 9.43 | 12.40 | -- | ||
Grok 4.3 (medium) | 1M | 专有 | 25* | -- | 109 | 12.08 | 16.67 | -- | ||
Ling-3.0-flash-VL | 262k | 开放 | 25 | -- | 145 | 2.48 | 19.73 | 13.80 | ||
Claude Sonnet 5 (low) | 1M | 专有 | 25 | $0.51 | 57 | 0.92 | 9.74 | -- | ||
Grok 4.3 (low) | 524k | 专有 | 24* | -- | 259 | 2.58 | 4.51 | -- | ||
Grok 4.3 (low) | 200k | 专有 | 24* | -- | 157 | 4.71 | 7.90 | -- | ||
Grok 4.3 (low) | 1M | 专有 | 24* | -- | 113 | 5.11 | 9.55 | -- | ||
Gemini 3.5 Flash (minimal) AI Studio | 1M | 专有 | 24* | -- | 203 | 0.84 | 3.30 | -- | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | $0.19 | 302 | 1.00 | 10.20 | 7.54 | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | -- | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | $0.47 | 112 | 3.48 | 28.35 | 20.39 | ||
Nemotron 3 Ultra BF16 | 262k | 开放 | 23 | $0.92 | 128 | 3.10 | 24.75 | 17.75 | ||
Nemotron 3 Ultra | 256k | 开放 | 23 | $1.16 | 319 | 2.37 | 11.07 | 7.13 | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | $0.48 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | $0.37 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | $0.22 | 171 | 0.65 | 16.91 | 13.33 | ||
Claude Sonnet 4.6 (Non-reasoning, low) | 1M | 专有 | 23* | -- | 42 | 1.33 | 13.19 | -- | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | 专有 | 23 | $0.12 | 358 | 8.19 | 9.58 | -- | ||
GLM-5.2 (Non-reasoning) (FAST) | 524k | 开放 | 22* | -- | 248 | 1.60 | 3.61 | -- | ||
GLM-5.2 (Non-reasoning) (FP4) | 432k | 开放 | 22* | -- | 261 | 1.04 | 2.95 | -- | ||
GLM-5.2 (Non-reasoning) | 262k | 开放 | 22* | -- | 90 | 1.70 | 7.23 | -- | ||
GLM-5.2 (Non-reasoning) | 1M | 开放 | 22* | -- | 52 | 2.43 | 12.00 | -- | ||
GLM-5.2 (Non-reasoning) (FP8) | 1.05M | 开放 | 22* | -- | 90 | 2.11 | 7.64 | -- | ||
GLM-5.2 (Non-reasoning) | 164k | 开放 | 22* | -- | 176 | 1.42 | 4.27 | -- | ||
GLM-5.2 (Non-reasoning) | 1.05M | 开放 | 22* | -- | 119 | 1.60 | 5.78 | -- | ||
GLM-5.2 (Non-reasoning) | 1M | 开放 | 22* | -- | 273 | 0.87 | 2.70 | -- | ||
Qwen3.8 27B | 1M | 开放 | 22* | -- | 50 | 4.08 | 14.02 | -- | ||
Qwen3.8 27B | 262k | 开放 | 22* | -- | 219 | 0.94 | 3.22 | -- | ||
MiMo-V2.5 | 1.05M | 开放 | 22 | $0.02 | 46 | 4.34 | 58.59 | 43.40 | ||
MiMo-V2.5 | 262k | 开放 | 22 | $0.02 | 29 | 1.43 | 87.16 | 68.58 | ||
MiMo-V2.5 | 1.05M | 开放 | 22 | $0.04 | -- | -- | -- | -- | ||
MiMo-V2.5 | 1M | 开放 | 22 | $0.02 | 44 | 6.11 | 63.32 | 45.77 | ||
GPT-5.6 Terra (Non-reasoning) | 1M | 专有 | 22* | -- | 92 | 0.87 | 6.33 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 1M | 专有 | 22* | -- | 123 | 0.75 | 4.81 | -- | ||
Qwen3.6 27B FP8 | 262k | 开放 | 22 | $0.37 | 65 | 0.94 | 95.81 | 87.19 | ||
Qwen3.6 27B | 131k | 开放 | 22 | $0.60 | 444 | 1.22 | 15.12 | 12.77 | ||
Qwen3.6 27B | 262k | 开放 | 22 | $0.62 | 58 | 2.94 | 110.33 | 98.69 | ||
Qwen3.6 27B | 262k | 开放 | 22 | $0.62 | 57 | 3.66 | 112.46 | 99.99 | ||
Qwen3.6 27B (FP8) | 262k | 开放 | 22 | $0.36 | 43 | 3.32 | 145.88 | 131.01 | ||
G9v3-39A5B | 131k | 开放 | 22* | -- | -- | -- | -- | -- | ||
KAT-Coder-Pro V2 | 256k | 专有 | 22* | -- | -- | -- | -- | -- | ||
GPT-5.6 Luna (low) | 1M | 专有 | 22 | $0.01 | 98 | 2.20 | 7.32 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | 开放 | 21* | -- | 84 | 2.03 | 7.98 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) (FP8) | 262k | 开放 | 21* | -- | 42 | 0.92 | 12.88 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | 开放 | 21* | -- | 86 | 2.14 | 7.98 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) (Base, FP4) | 262k | 开放 | 21* | -- | 139 | 2.06 | 5.65 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | 开放 | 21* | -- | 14 | 1.76 | 37.42 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | 开放 | 21* | -- | 82 | 1.56 | 7.63 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1M | 开放 | 21* | -- | 84 | 1.78 | 7.71 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1M | 开放 | 21* | -- | 78 | 2.02 | 8.44 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1.05M | 开放 | 21* | -- | 107 | 1.31 | 6.00 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1M | 开放 | 21* | -- | 137 | 0.62 | 4.27 | -- | ||
DeepSeek V4 Pro (Non-reasoning) | 1M | 开放 | 21* | -- | 80 | 1.57 | 7.80 | -- | ||
Qwen3.5 Omni Plus | 256k | 专有 | 20* | -- | 95 | 2.14 | 7.41 | -- | ||
o3 | 200k | 专有 | 20* | -- | 106 | 26.44 | 31.17 | -- | ||
o3 | 200k | 专有 | 20* | -- | -- | -- | -- | -- | ||
o3 | 200k | 专有 | 20* | -- | 145 | 4.14 | 7.59 | -- | ||
Qwen3.6 27B (Non-reasoning) | 131k | 开放 | 20* | -- | 452 | 1.20 | 2.30 | -- | ||
Qwen3.6 27B (Non-reasoning) (FP8) | 262k | 开放 | 20* | -- | 70 | 1.79 | 8.94 | -- | ||
Qwen3.6 27B (Non-reasoning) FP8 | 262k | 开放 | 20* | -- | 60 | 0.95 | 9.28 | -- | ||
Qwen3.6 27B (Non-reasoning) | 262k | 开放 | 20* | -- | 58 | 3.62 | 12.31 | -- | ||
Qwen3.6 27B (Non-reasoning) | 262k | 开放 | 20* | -- | 60 | 3.04 | 11.44 | -- | ||
LongCat 2.0 | 1M | 开放 | 20 | $0.06 | -- | -- | -- | -- | ||
LongCat 2.0 (FP8) | 262k | 开放 | 20 | $0.15 | 54 | 3.08 | 49.16 | 36.86 | ||
Step 3.7 Flash | 256k | 开放 | 19* | -- | 111 | 2.67 | 25.26 | 18.07 | ||
Step 3.7 Flash | 256k | 开放 | 19* | -- | 168 | 0.66 | 15.52 | 11.89 | ||
Qwen3.5 397B A17B | 262k | 开放 | 19 | $0.47 | 84 | 2.24 | 45.96 | 37.79 | ||
Qwen3.5 397B A17B | 262k | 开放 | 19 | $0.34 | 85 | 2.15 | 45.65 | 37.60 | ||
Qwen3.5 397B A17B | 262k | 开放 | 19 | $0.30 | 56 | 0.97 | 66.84 | 56.94 | ||
Qwen3.5 397B A17B (FP8) | 262k | 开放 | 19 | $0.31 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (FP8) | 262k | 开放 | 19 | $0.23 | 40 | 0.95 | 92.47 | 79.11 | ||
Qwen3.5 397B A17B | 262k | 开放 | 19 | $0.17 | 14 | 1.31 | 256.54 | 220.60 | ||
Qwen3.5 397B A17B (FP8) | 262k | 开放 | 19 | $0.47 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | 开放 | 19 | $0.47 | 139 | 2.06 | 28.64 | 22.97 | ||
Qwen3.5 397B A17B | 262k | 开放 | 19 | $0.47 | 83 | 1.63 | 45.81 | 38.18 | ||
DeepSeek V4 Flash (Non-reasoning) | 1.05M | 开放 | 19* | -- | -- | -- | -- | -- | ||
DeepSeek V4 Flash (Non-reasoning) | 1M | 开放 | 19* | -- | 121 | 0.74 | 4.86 | -- | ||
DeepSeek V4 Flash (Non-reasoning) | 1M | 开放 | 19* | -- | 78 | 1.56 | 8.00 | -- | ||
Qwen3.6 35B A3B | 229k | 开放 | 19 | $0.48 | 123 | 2.07 | 50.01 | 43.87 | ||
Qwen3.6 35B A3B (FP8) | 262k | 开放 | 19 | $0.27 | 107 | 2.20 | 57.16 | 50.30 | ||
Qwen3.6 35B A3B | 262k | 开放 | 19 | $0.37 | 115 | 0.97 | 52.45 | 47.12 | ||
Qwen3.6 35B A3B (FP8) | 262k | 开放 | 19 | $0.14 | 99 | 0.71 | 60.11 | 54.36 | ||
Qwen3.6 35B A3B FP8 | 262k | 开放 | 19 | $0.31 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | 开放 | 19 | $0.12 | 124 | 0.82 | 48.43 | 43.58 | ||
Qwen3.6 35B A3B | 205k | 开放 | 19 | $0.31 | 124 | 1.35 | 48.71 | 43.34 | ||
MiMo-V2.5-Pro (Non-reasoning) | 1.05M | 开放 | 18* | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro (Non-reasoning) | 65.5k | 开放 | 18* | -- | 29 | 1.09 | 18.58 | -- | ||
MiMo-V2.5-Pro (Non-reasoning) | 131k | 开放 | 18* | -- | 34 | 6.73 | 21.59 | -- | ||
MiMo-V2.5-Pro (Non-reasoning) | 1.05M | 开放 | 18* | -- | 37 | 5.55 | 18.97 | -- | ||
Muse Glimmer (high) | 131k | 开放 | 18 | $0.09 | 91 | 0.80 | 28.40 | 22.08 | ||
Muse Glimmer (high) | 131k | 开放 | 18 | $0.05 | 145 | 0.94 | 18.20 | 13.81 | ||
Muse Glimmer (high) | 131k | 开放 | 18 | $0.06 | 61 | 1.12 | 42.14 | 32.82 | ||
Qwen3.5 122B A10B (Non-reasoning) (FP4) | 262k | 开放 | 18* | -- | 147 | 0.84 | 4.24 | -- | ||
Qwen3.5 122B A10B (Non-reasoning) | 262k | 开放 | 18* | -- | 136 | 2.39 | 6.08 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 18 | $0.20 | 104 | 8.64 | 13.44 | -- | ||
Claude 4.5 Haiku Vertex | 200k | 专有 | 18 | $0.24 | 107 | 16.36 | 21.03 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 18 | $0.21 | 85 | 15.75 | 21.66 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 18 | $0.57 | 85 | 27.56 | 33.43 | -- | ||
Ring-2.6-1T | 262k | 开放 | 17 | $0.29 | 127 | 3.80 | 23.56 | 15.81 | ||
GPT-5.6 Luna (Non-reasoning) | 1M | 专有 | 17* | -- | 109 | 0.90 | 5.49 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 1M | 专有 | 17* | -- | 205 | 0.75 | 3.19 | -- | ||
Gemma 4 26B A4B | 1M | 开放 | 17* | -- | 93 | 1.28 | 28.30 | 21.62 | ||
Gemma 4 26B A4B | 262k | 开放 | 17* | -- | 107 | 1.56 | 24.95 | 18.71 | ||
Gemma 4 26B A4B AI Studio | 262k | 开放 | 17* | -- | 46 | 1.03 | 55.04 | 43.21 | ||
Gemma 4 26B A4B | 256k | 开放 | 17* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | 开放 | 17* | -- | 28 | 0.87 | 88.96 | 70.47 | ||
Gemma 4 26B A4B | 256k | 开放 | 17* | -- | 22 | 1.85 | 117.37 | 92.41 | ||
Gemma 4 26B A4B (FP8) | 1.05M | 开放 | 17* | -- | -- | -- | -- | -- | ||
Qwen3.5 122B A10B (FP8) | 262k | 开放 | 16 | $0.21 | 94 | 1.93 | 28.42 | 21.19 | ||
Qwen3.5 122B A10B (FP4) | 262k | 开放 | 16 | $0.14 | 155 | 0.79 | 16.94 | 12.92 | ||
Qwen3.5 122B A10B | 262k | 开放 | 16 | $0.32 | 128 | 2.33 | 21.80 | 15.57 | ||
Qwen3.5 122B A10B (FP8) | 262k | 开放 | 16 | $0.32 | -- | -- | -- | -- | ||
Qwen3.5 122B A10B | 262k | 开放 | 16 | $0.32 | 113 | 1.91 | 24.05 | 17.71 | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.07 | 64 | 2.23 | 37.37 | 27.29 | ||
Gemma 4 31B (NVFP4) | 262k | 开放 | 15 | -- | 275 | 0.52 | 8.65 | 6.31 | ||
Gemma 4 31B (FP8) | 262k | 开放 | 15 | $0.10 | -- | -- | -- | -- | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.10 | -- | -- | -- | -- | ||
Gemma 4 31B | 131k | 开放 | 15 | $0.71 | -- | -- | -- | -- | ||
Gemma 4 31B (AI Studio) | 262k | 开放 | 15 | $0.00 | 35 | 1.07 | 64.95 | 49.59 | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.05 | 28 | 1.84 | 82.99 | 63.00 | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.02 | 15 | 2.02 | 146.74 | 112.36 | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.10 | 21 | 2.03 | 111.09 | 84.68 | ||
Gemma 4 31B (FP8) | 262k | 开放 | 15 | $0.10 | 52 | 3.62 | 46.39 | 33.21 | ||
Gemma 4 31B | 131k | 开放 | 15 | $0.28 | 198 | 2.98 | 14.29 | 8.78 | ||
Gemma 4 31B | 256k | 开放 | 15 | $0.10 | 100 | 1.95 | 24.32 | 17.37 | ||
Gemma 4 31B | 131k | 开放 | 15 | $0.10 | -- | -- | -- | -- | ||
Gemma 4 31B (FP8) | 262k | 开放 | 15 | $0.29 | 32 | 1.45 | 70.94 | 53.95 | ||
Claude 4.5 Haiku (Non-reasoning) | 200k | 专有 | 15* | -- | 78 | 1.26 | 7.66 | -- | ||
Claude 4.5 Haiku (Non-reasoning) | 200k | 专有 | 15* | -- | 101 | 0.83 | 5.77 | -- | ||
Claude 4.5 Haiku (Non-reasoning) | 200k | 专有 | 15* | -- | 79 | 0.70 | 7.02 | -- | ||
Claude 4.5 Haiku (Non-reasoning) Vertex | 200k | 专有 | 15* | -- | 85 | 0.87 | 6.75 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) | 262k | 开放 | 15* | -- | 140 | 1.00 | 4.56 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) (FP8) | 262k | 开放 | 15* | -- | 108 | 0.69 | 5.33 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) | 205k | 开放 | 15* | -- | 138 | 1.37 | 4.98 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) FP8 | 262k | 开放 | 15* | -- | -- | -- | -- | -- | ||
Qwen3.6 35B A3B (Non-reasoning) (FP8) | 262k | 开放 | 15* | -- | 119 | 0.86 | 5.05 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) | 262k | 开放 | 15* | -- | 134 | 2.08 | 5.80 | -- | ||
Qwen3.5 35B A3B (Non-reasoning) FP8 | 262k | 开放 | 15* | -- | 155 | 0.72 | 3.95 | -- | ||
Qwen3.5 35B A3B (Non-reasoning) | 262k | 开放 | 15* | -- | 165 | 2.07 | 5.10 | -- | ||
Qwen3.5 35B A3B (Non-reasoning) (FP8) | 262k | 开放 | 15* | -- | 229 | 1.03 | 3.20 | -- | ||
Mistral Medium 3.5 | 262k | 开放 | 15 | $0.44 | 148 | 2.25 | 19.08 | 13.47 | ||
Granite 4.2 30B | 131k | 开放 | 15* | -- | 77 | 0.82 | 33.09 | 25.81 | ||
Grok 4.3 (Non-reasoning) | 524k | 专有 | 15 | $0.28 | 242 | 0.67 | 2.74 | -- | ||
Grok 4.3 (Non-reasoning) | 1M | 专有 | 15 | $0.14 | 115 | 0.75 | 5.09 | -- | ||
Gemma 4 12B | 262k | 开放 | 14* | -- | 109 | 2.42 | 25.32 | 18.32 | ||
Nova 2.0 Pro Preview (medium) | 256k | 专有 | 14* | -- | 115 | 12.43 | 34.26 | 17.46 | ||
Command A+ | 200k | 开放 | 14 | $0.00 | 240 | 0.38 | 10.80 | 8.34 | ||
Gemma 4 31B (Non-reasoning) (NVFP4) | 262k | 开放 | 14* | -- | 195 | 0.43 | 3.00 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | 开放 | 14* | -- | 32 | 1.42 | 17.06 | -- | ||
Gemma 4 31B (Non-reasoning) | 131k | 开放 | 14* | -- | -- | -- | -- | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | 开放 | 14* | -- | 103 | 2.05 | 6.92 | -- | ||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | 开放 | 14* | -- | 14 | 1.46 | 36.16 | -- | ||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | 开放 | 14* | -- | 47 | 3.45 | 14.14 | -- | ||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | 开放 | 14* | -- | 25 | 1.47 | 21.14 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | 开放 | 14* | -- | 59 | 2.10 | 10.52 | -- | ||
Gemma 4 31B (Non-reasoning) | 131k | 开放 | 14* | -- | 201 | 3.11 | 5.59 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | 开放 | 14* | -- | 16 | 1.15 | 32.23 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | 开放 | 14* | -- | 16 | 1.76 | 33.55 | -- | ||
Qwen3.5 9B (FP8) | 262k | 开放 | 14* | -- | 65 | 2.38 | 41.00 | 30.90 | ||
Qwen3.5 9B (FP8) | 262k | 开放 | 14* | -- | 94 | 0.78 | 27.52 | 21.39 | ||
Nova 2.0 Omni (medium) | 1M | 专有 | 14* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (medium) | 1M | 专有 | 14* | -- | -- | -- | -- | -- | ||
Nemotron 3.5 Lightning (NVFP4) | 262k | 开放 | 14 | $0.12 | -- | -- | -- | -- | ||
Nemotron 3.5 Lightning (BF16) | 1.05M | 开放 | 14 | $0.09 | 266 | 1.11 | 10.50 | 7.51 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 14 | $0.10 | 288 | 0.55 | 9.22 | 6.94 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 14 | $0.12 | 149 | 3.94 | 20.77 | 13.46 | ||
Nemotron 3.5 Lightning (BF16) | 65.5k | 开放 | 14 | $0.00 | 294 | 1.72 | 10.23 | 6.81 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 14 | $0.02 | 491 | 0.46 | 5.56 | 4.07 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 14 | $0.08 | 306 | 0.43 | 8.60 | 6.54 | ||
Nemotron 3 Super | 256k | 开放 | 14 | $1.64 | 383 | 1.82 | 8.35 | 5.22 | ||
Nemotron 3 Super | 262k | 开放 | 14 | $0.48 | 77 | 14.99 | 47.29 | 25.84 | ||
Apriel-v1.6-15B-Thinker | 131k | 开放 | 13* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | 专有 | 13* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | 专有 | 13* | -- | 173 | 14.98 | 29.40 | 11.54 | ||
Qwen3.5 9B (Non-reasoning) (FP8) | 262k | 开放 | 13* | -- | 94 | 0.77 | 6.08 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 1M | 开放 | 13* | -- | 76 | 1.38 | 7.97 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 262k | 开放 | 13* | -- | 19 | 1.57 | 28.03 | -- | ||
Gemma 4 26B A4B (Non-reasoning) (FP8) | 1.05M | 开放 | 13* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (Non-reasoning) (FP8) | 262k | 开放 | 13* | -- | 50 | 2.64 | 12.66 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 262k | 开放 | 13* | -- | 171 | 0.90 | 3.82 | -- | ||
Gemma 4 26B A4B (Non-reasoning) (FP8) | 262k | 开放 | 13* | -- | 25 | 0.77 | 20.79 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 262k | 开放 | 13* | -- | 36 | 1.26 | 15.00 | -- | ||
Qwen3.5 4B (FP8) | 262k | 开放 | 13* | -- | 36 | 0.70 | 70.28 | 55.66 | ||
North Mini Code | 256k | 开放 | 13* | -- | 77 | 0.41 | 32.71 | 25.84 | ||
Nova 2.0 Pro Preview (low) | 256k | 专有 | 13* | -- | 114 | 10.88 | 32.87 | 17.59 | ||
Nova 2.0 Lite (medium) | 1M | 专有 | 12* | -- | 166 | 10.55 | 25.58 | 12.02 | ||
Qwen3.5 Omni Flash | 256k | 专有 | 12* | -- | 221 | 1.89 | 4.15 | -- | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.08 | 474 | 0.72 | 5.99 | 4.22 | ||
gpt-oss-120b (high) | 116k | 开放 | 12 | $0.23 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | 开放 | 12 | $0.12 | 125 | 1.28 | 21.23 | 15.96 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.02 | 53 | 1.35 | 48.47 | 37.70 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.11 | 313 | 0.73 | 8.70 | 6.38 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.04 | 105 | 1.15 | 25.02 | 19.09 | ||
gpt-oss-120b (high) (Turbo) | 131k | 开放 | 12 | $0.11 | 230 | 0.76 | 11.61 | 8.68 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.04 | 268 | 0.37 | 9.68 | 7.45 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.03 | 48 | 0.62 | 52.46 | 41.48 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.23 | 1,765 | 0.53 | 1.95 | 1.13 | ||
gpt-oss-120b (high) Vertex | 131k | 开放 | 12 | $0.06 | 218 | 0.41 | 11.87 | 9.17 | ||
gpt-oss-120b (high) | 128k | 开放 | 12 | $0.07 | 285 | 0.25 | 9.02 | 7.02 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.15 | 700 | 1.27 | 4.84 | 2.86 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.06 | 183 | 0.75 | 14.43 | 10.95 | ||
gpt-oss-120b (high) (Base) | 128k | 开放 | 12 | $0.11 | 297 | 1.02 | 9.44 | 6.74 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.19 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.11 | 73 | 0.96 | 35.37 | 27.53 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.11 | 185 | 0.48 | 14.02 | 10.83 | ||
Ling 3.0 Tiny | 262k | 开放 | 12 | $0.00 | 171 | 2.63 | 17.27 | 11.71 | ||
Granite 4.2 8B | 131k | 开放 | 12 | $0.06 | 105 | 0.75 | 24.66 | 19.13 | ||
Granite 4.2 8B | 131k | 开放 | 12 | $0.02 | 78 | 0.61 | 32.68 | 25.65 | ||
Nova 2.0 Lite (low) | 1M | 专有 | 12* | -- | 171 | 8.28 | 22.90 | 11.70 | ||
HyperNova 60B 2605 (high) | 131k | 开放 | 12* | -- | 349 | 0.58 | 7.75 | 5.74 | ||
Mercury 2 | 128k | 专有 | 12 | $0.07 | 820 | 4.60 | 5.21 | -- | ||
Mistral Small 4 | 256k | 开放 | 11 | $0.05 | 168 | 0.73 | 15.60 | 11.90 | ||
Qwen3 Next 80B A3B (Reasoning) | 262k | 开放 | 11* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B (Reasoning) Vertex | 262k | 开放 | 11* | -- | 161 | 0.71 | 16.24 | 12.42 | ||
Qwen3 Next 80B A3B (Reasoning) | 262k | 开放 | 11* | -- | 195 | 2.37 | 15.19 | 10.25 | ||
Qwen3 Next 80B A3B (Reasoning) | 262k | 开放 | 11* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (low) | 1M | 专有 | 11* | -- | -- | -- | -- | -- | ||
Trinity Large Thinking | 262k | 开放 | 11 | $0.35 | 319 | 1.33 | 9.16 | 6.27 | ||
G9v3-3B | 131k | 开放 | 11* | -- | -- | -- | -- | -- | ||
Qwen3.5 4B (Non-reasoning) FP8 | 262k | 开放 | 11* | -- | 25 | 0.69 | 20.50 | -- | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) Base | 128k | 开放 | 10* | -- | 290 | 1.01 | 9.63 | 6.89 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 269 | 0.35 | 9.63 | 7.43 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 735 | 1.42 | 4.82 | 2.72 | ||
gpt-oss-120b (low) Vertex | 131k | 开放 | 10* | -- | 212 | 0.36 | 12.17 | 9.45 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 53 | 0.65 | 48.12 | 37.98 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 57 | 1.34 | 45.25 | 35.13 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 1,768 | 0.51 | 1.92 | 1.13 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 334 | 0.81 | 8.31 | 5.99 | ||
gpt-oss-120b (low) | 128k | 开放 | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 128k | 开放 | 10* | -- | 296 | 0.23 | 8.68 | 6.76 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 73 | 0.97 | 35.14 | 27.34 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 159 | 0.80 | 16.48 | 12.54 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 148 | 0.54 | 17.44 | 13.52 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 473 | 0.69 | 5.98 | 4.23 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 110 | 0.98 | 23.81 | 18.26 | ||
Qwen3 Coder Next | 128k | 开放 | 10 | $0.78 | 113 | 1.01 | 5.45 | -- | ||
Qwen3 Coder Next (FP8) | 262k | 开放 | 10 | $0.12 | 71 | 1.04 | 8.13 | -- | ||
Qwen3 Coder Next (FP8) | 262k | 开放 | 10 | $0.78 | -- | -- | -- | -- | ||
Qwen3 Coder Next (FP8) | 262k | 开放 | 10 | $0.33 | 166 | 2.48 | 5.50 | -- | ||
Nova 2.0 Pro Preview (Non-reasoning) | 256k | 专有 | 10* | -- | 113 | 1.03 | 5.46 | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | 931 | 0.84 | 3.53 | 2.15 | ||
gpt-oss-20b (low) | 128k | 开放 | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | 256 | 0.58 | 10.34 | 7.80 | ||
gpt-oss-20b (low) | 128k | 开放 | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | 187 | 6.94 | 20.33 | 10.72 | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | 231 | 1.10 | 11.90 | 8.64 | ||
gpt-oss-20b (low) Vertex | 131k | 开放 | 10* | -- | 404 | 0.31 | 6.50 | 4.95 | ||
Mistral Large 3 | 256k | 开放 | 10 | $0.10 | 204 | 1.09 | 3.55 | -- | ||
Mistral Large 3 | 256k | 开放 | 10 | $0.10 | 93 | 1.43 | 6.79 | -- | ||
Mistral Large 3 | 262k | 开放 | 10 | $0.10 | 74 | 1.07 | 7.81 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 10* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | 开放 | 10* | -- | 308 | 0.64 | 2.26 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 10* | -- | 102 | 0.92 | 5.83 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 10* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 10* | -- | 145 | 0.66 | 4.10 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 10* | -- | 173 | 1.55 | 4.45 | -- | ||
Qwen3 Next 80B A3B | 131k | 开放 | 10* | -- | 185 | 1.80 | 4.50 | -- | ||
Qwen3 Next 80B A3B | 131k | 开放 | 10* | -- | 180 | 2.21 | 4.98 | -- | ||
Devstral 2 | 262k | 开放 | 9 | $0.00 | 141 | 2.25 | 5.80 | -- | ||
Gemma 4 12B (Non-reasoning) | 262k | 开放 | 9* | -- | 104 | 2.34 | 7.13 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | 开放 | 9 | $0.04 | 80 | 0.78 | 7.01 | -- | ||
Llama 4 Maverick (FP8) | 128k | 开放 | 9 | $0.04 | 391 | 1.27 | 2.55 | -- | ||
Llama 4 Maverick | 128k | 开放 | 9 | $0.04 | 220 | 0.75 | 3.02 | -- | ||
Llama 4 Maverick | 1.05M | 开放 | 9 | $0.04 | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | 开放 | 9 | $0.03 | 74 | 0.51 | 7.25 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | 开放 | 9 | $0.03 | 56 | 0.95 | 9.92 | -- | ||
Nova Premier | 1M | 专有 | 9* | -- | 33 | 2.82 | 17.89 | -- | ||
Granite 4.2 3B | 131k | 开放 | 9 | $0.01 | 217 | 0.41 | 11.94 | 9.22 | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.01 | 223 | 0.59 | 11.78 | 8.95 | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.01 | 233 | 27.06 | 37.78 | 8.57 | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.01 | 119 | 0.44 | 21.40 | 16.77 | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | 开放 | 9 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | 开放 | 9 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.01 | 209 | 1.17 | 13.12 | 9.56 | ||
gpt-oss-20b (high) Vertex | 131k | 开放 | 9 | $0.01 | 409 | 0.34 | 6.45 | 4.89 | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.02 | 960 | 0.78 | 3.39 | 2.08 | ||
Llama Nemotron Super 49B v1.5 | 131k | 开放 | 9* | -- | 92 | 4.27 | 31.39 | 21.70 | ||
Mistral Small 4 (Non-reasoning) | 262k | 开放 | 9* | -- | 153 | 0.75 | 4.00 | -- | ||
Gemma 4 E4B | 262k | 开放 | 9* | -- | 43 | 0.83 | 58.62 | 46.24 | ||
Nemotron 3 Nano | 262k | 开放 | 9 | $0.02 | 232 | 1.11 | 11.88 | 8.61 | ||
Nemotron 3 Nano (FP4) | 262k | 开放 | 9 | $0.02 | 310 | 0.99 | 9.07 | 6.46 | ||
Nemotron 3 Nano | 262k | 开放 | 9 | $0.02 | 95 | 5.80 | 32.06 | 21.01 | ||
Sarvam 105B (high) | 128k | 开放 | 9* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (Non-reasoning) | 1M | 专有 | 9* | -- | 153 | 1.06 | 4.32 | -- | ||
Magistral Small 1.2 | 128k | 开放 | 9* | -- | 71 | 1.60 | 36.71 | 28.09 | ||
LFM2.5-2.6B | 32.8k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Devstral Small 2 | 256k | 开放 | 8 | $0.00 | 138 | 2.23 | 5.87 | -- | ||
Nova 2.0 Omni (Non-reasoning) | 1M | 专有 | 8* | -- | -- | -- | -- | -- | ||
Solar Pro 3 | 131k | 专有 | 8 | $0.08 | 155 | 2.66 | 18.84 | 12.94 | ||
Qwen3 Omni 30B A3B (Reasoning) | 65.5k | 开放 | 8* | -- | 101 | 1.91 | 26.62 | 19.76 | ||
Llama 3.3 70B | 131k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B Vertex | 128k | 开放 | 8* | -- | 157 | 0.64 | 3.83 | -- | ||
Llama 3.3 70B | 131k | 开放 | 8* | -- | 299 | 0.81 | 2.49 | -- | ||
Llama 3.3 70B | 131k | 开放 | 8* | -- | 43 | 1.72 | 13.30 | -- | ||
Llama 3.3 70B (FP8) | 131k | 开放 | 8* | -- | 85 | 2.60 | 8.47 | -- | ||
Llama 3.3 70B | 128k | 开放 | 8* | -- | 277 | 2.38 | 4.19 | -- | ||
Llama 3.3 70B Base | 128k | 开放 | 8* | -- | 4 | 16.43 | 142.22 | -- | ||
Llama 3.3 70B | 128k | 开放 | 8* | -- | 80 | 0.88 | 7.10 | -- | ||
Llama 3.3 70B Turbo | 131k | 开放 | 8* | -- | 79 | 1.36 | 7.69 | -- | ||
Llama 3.3 70B | 128k | 开放 | 8* | -- | 116 | 2.21 | 6.53 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | 开放 | 8* | -- | 16 | 2.07 | 34.14 | -- | ||
Llama 3.3 70B | 24k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B | 128k | 开放 | 8* | -- | 149 | 1.11 | 4.46 | -- | ||
Llama 3.3 70B | 100k | 开放 | 8* | -- | 80 | 1.39 | 7.64 | -- | ||
ERNIE 4.5 300B A47B | 131k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Hermes 4 405B (FP8) | 128k | 开放 | 7* | -- | 44 | 2.52 | 59.94 | 45.93 | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | 开放 | 7* | -- | 122 | 4.49 | 25.04 | 16.45 | ||
Gemma 4 E4B (Non-reasoning) | 262k | 开放 | 7* | -- | 45 | 0.77 | 11.83 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | 开放 | 7* | -- | 91 | 7.88 | 35.38 | 22.00 | ||
Hermes 4 405B (Non-reasoning) (FP8) | 128k | 开放 | 7* | -- | 43 | 2.39 | 13.95 | -- | ||
Llama Nemotron Super 49B v1.5 (Non-reasoning) | 131k | 开放 | 7* | -- | 144 | 3.57 | 7.04 | -- | ||
LFM2.5-8B-A1B | 32.8k | 开放 | 7* | -- | -- | -- | -- | -- | ||
Ring-flash-2.0 | 131k | 开放 | 7* | -- | -- | -- | -- | -- | ||
Olmo 3.1 32B Think | 65.5k | 开放 | 7* | -- | -- | -- | -- | -- | ||
Command A | 288k | 开放 | 7* | -- | 55 | 1.63 | 10.64 | -- | ||
Command A | 256k | 开放 | 7* | -- | 42 | 3.00 | 15.01 | -- | ||
Llama 3.1 Nemotron 70B | 131k | 开放 | 7* | -- | 124 | 3.27 | 7.30 | -- | ||
Nemotron 3 Nano (Non-reasoning) (FP4) | 262k | 开放 | 7* | -- | 288 | 0.99 | 2.73 | -- | ||
Nemotron 3 Nano (Non-reasoning) | 262k | 开放 | 7* | -- | 102 | 0.65 | 5.57 | -- | ||
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 131k | 开放 | 7* | -- | 97 | 7.90 | 13.04 | -- | ||
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 131k | 开放 | 7* | -- | 167 | 1.11 | 4.10 | -- | ||
Granite 4.1 8B | 131k | 开放 | 7* | -- | 126 | 0.74 | 4.70 | -- | ||
Sarvam 30B (high) | 64k | 开放 | 7* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 328k | 开放 | 6 | $0.06 | 22 | 0.88 | 23.53 | -- | ||
Llama 4 Scout | 128k | 开放 | 6 | $0.12 | 133 | 0.87 | 4.63 | -- | ||
Llama 4 Scout Vertex | 1.31M | 开放 | 6 | $0.16 | 154 | 0.70 | 3.95 | -- | ||
Llama 4 Scout | 131k | 开放 | 6 | $0.17 | -- | -- | -- | -- | ||
Llama 4 Scout | 128k | 开放 | 6 | $0.11 | 167 | 0.77 | 3.77 | -- | ||
Llama 4 Scout | 131k | 开放 | 6 | $0.11 | 22 | 1.73 | 24.97 | -- | ||
Celeris-1 | 131k | 专有 | 6 | $0.05 | 1,416 | 0.60 | 0.95 | -- | ||
Phi-4 Mini | 128k | 开放 | 6* | -- | 45 | 0.86 | 12.05 | -- | ||
Granite 4.0 H Small | 128k | 开放 | 6* | -- | 15 | 29.59 | 63.25 | -- | ||
Ministral 3 14B | 262k | 开放 | 6 | $0.14 | 85 | 0.92 | 6.82 | -- | ||
Ministral 3 14B | 256k | 开放 | 6 | $0.14 | 240 | 0.92 | 3.00 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | 开放 | 6* | -- | 96 | 1.92 | 7.12 | -- | ||
Phi-4 | 16.4k | 开放 | 6* | -- | 40 | 2.58 | 15.11 | -- | ||
Phi-4 | 16.4k | 开放 | 6* | -- | 58 | 0.93 | 9.61 | -- | ||
Nova Micro | 130k | 专有 | 6* | -- | 278 | 0.89 | 2.69 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | 128k | 开放 | 6* | -- | 199 | 1.08 | 3.59 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) (FP8) | 131k | 开放 | 6* | -- | 128 | 4.58 | 8.48 | -- | ||
Phi-4 Multimodal | 128k | 开放 | 6* | -- | 17 | 0.87 | 30.16 | -- | ||
Reka Flash 3 | 54k | 开放 | 6* | -- | -- | -- | -- | -- | ||
Ministral 3 8B | 256k | 开放 | 5 | $0.07 | 243 | 1.02 | 3.08 | -- | ||
Ministral 3 8B | 262k | 开放 | 5 | $0.07 | 89 | 0.73 | 6.34 | -- | ||
Llama 3.2 11B (Vision) | 131k | 开放 | 5* | -- | 23 | 1.27 | 23.15 | -- | ||
Olmo 3 7B | 65.5k | 开放 | 5* | -- | -- | -- | -- | -- | ||
Apertus 70B Instruct | 64k | 开放 | 5* | -- | -- | -- | -- | -- | ||
Ministral 3 3B | 256k | 开放 | 5 | $0.04 | 526 | 0.89 | 1.84 | -- | ||
Ministral 3 3B | 131k | 开放 | 5 | $0.04 | 213 | 0.61 | 2.96 | -- | ||
LFM2.5-VL-1.6B | 32.8k | 开放 | 5* | -- | -- | -- | -- | -- | ||
Tiny Aya Global | 8.19k | 开放 | 5* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | 开放 | 5* | -- | -- | -- | -- | -- | ||
Cogito v2.1 | 164k | 开放 | -- | -- | -- | -- | -- | -- | ||