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 Opus 5 (max) | 1M | 专有 | 63 | $2.34 | 55 | 92.49 | 101.65 | -- | ||
Claude Opus 5 (max) | 1M | 专有 | 63 | $2.34 | 58 | 57.93 | 66.59 | -- | ||
Claude Opus 5 (max) | 1M | 专有 | 63 | $3.31 | 55 | 67.28 | 76.40 | -- | ||
Claude Opus 5 (xhigh) | 1M | 专有 | 63 | $1.80 | 53 | 38.79 | 48.17 | -- | ||
Claude Opus 5 (xhigh) | 1M | 专有 | 63 | $2.51 | 55 | 34.74 | 43.81 | -- | ||
Claude Opus 5 (xhigh) | 1M | 专有 | 63 | $1.80 | 57 | 41.09 | 49.89 | -- | ||
Claude Fable 5 (with fallback) | 1M | 专有 | 62 | $3.14 | 71 | 134.59 | 141.63 | -- | ||
Claude Fable 5 (with fallback) | 1M | 专有 | 62 | $3.32 | 71 | 112.71 | 119.73 | -- | ||
Claude Fable 5 (with fallback) | 1M | 专有 | 62 | $10.16 | 71 | 109.99 | 117.04 | -- | ||
Claude Opus 5 (high) | 1M | 专有 | 61 | $1.23 | 56 | 25.94 | 34.85 | -- | ||
Claude Opus 5 (high) | 1M | 专有 | 61 | $1.67 | 56 | 24.04 | 33.04 | -- | ||
Claude Opus 5 (high) | 1M | 专有 | 61 | $1.23 | 55 | 25.45 | 34.48 | -- | ||
GPT-5.6 Sol (max) | 1M | 专有 | 61 | $1.66 | 120 | 132.61 | 136.78 | -- | ||
GPT-5.6 Sol (max) | 1M | 专有 | 61 | $0.96 | 73 | 135.70 | 142.56 | -- | ||
Grok 4.6 (high) | 500k | 专有 | 61 | $0.84 | 55 | 44.82 | 53.91 | -- | ||
Grok 4.6 (xhigh) | 500k | 专有 | 60 | $1.04 | 60 | 48.14 | 56.50 | -- | ||
Kimi K3 (max) | 1.05M | 开放 | 60 | $0.84 | 36 | 4.11 | 74.44 | 56.27 | ||
Kimi K3 (max) | 1.05M | 开放 | 60 | $0.89 | 54 | 1.48 | 48.07 | 37.27 | ||
Kimi K3 (max) (FAST) | 1.05M | 开放 | 60 | $1.34 | 112 | 1.03 | 23.40 | 17.89 | ||
Kimi K3 (max) | 1.05M | 开放 | 60 | $1.24 | 143 | 2.05 | 19.50 | 13.96 | ||
Kimi K3 (max) | 1.05M | 开放 | 60 | $1.43 | 47 | 0.94 | 53.89 | 42.36 | ||
Kimi K3 (max) | 1.05M | 开放 | 60 | $0.96 | 33 | 1.20 | 77.70 | 61.20 | ||
Kimi K3 (max) | 1.05M | 开放 | 60 | $1.26 | 113 | 0.92 | 22.98 | 17.65 | ||
Kimi K3 (max) | 1.05M | 开放 | 60 | $0.78 | 162 | 1.87 | 17.26 | 12.31 | ||
Kimi K3 (max) | 1.05M | 开放 | 60 | $0.56 | 180 | 1.17 | 15.03 | 11.09 | ||
Kimi K3 (max) | 1.05M | 开放 | 60 | $3.11 | 138 | 1.59 | 19.68 | 14.47 | ||
Kimi K3 (max) | 205k | 开放 | 60 | $0.79 | 103 | 0.88 | 25.14 | 19.41 | ||
Kimi K3 (max) | 262k | 开放 | 60 | $1.19 | 16 | 2.97 | 159.05 | 124.86 | ||
GLM-5.3 (max) | 1M | 专有 | 60 | $0.68 | 59 | 3.30 | 45.45 | 33.72 | ||
GPT-5.6 Sol (xhigh) | 1M | 专有 | 59 | $0.64 | 68 | 68.57 | 75.96 | -- | ||
Grok 4.6 (medium) | 500k | 专有 | 59 | $0.67 | 59 | 38.64 | 47.09 | -- | ||
Claude Opus 5 (medium) | 1M | 专有 | 59 | $0.72 | 54 | 6.41 | 15.74 | -- | ||
Claude Opus 5 (medium) | 1M | 专有 | 59 | $0.72 | 55 | 15.57 | 24.71 | -- | ||
Claude Opus 5 (medium) | 1M | 专有 | 59 | $0.95 | 54 | 6.81 | 16.03 | -- | ||
Qwen3.8 Max | 1M | 专有 | 58 | $1.13 | 19 | 2.51 | 134.08 | 105.25 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 58 | $0.72 | 72 | 1.11 | 35.82 | 27.76 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 58 | $1.74 | 186 | 1.08 | 14.54 | 10.77 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 58 | $1.03 | 62 | 1.34 | 41.65 | 32.25 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 58 | $0.70 | 56 | 2.63 | 47.02 | 35.51 | ||
Qwen3.8 2.4T A95B (FP8) | 262k | 开放 | 58 | $0.61 | 65 | 5.12 | 43.80 | 30.94 | ||
Qwen3.8 2.4T A95B | 984k | 开放 | 58 | $1.09 | 21 | 2.62 | 123.79 | 96.93 | ||
GPT-5.6 Sol (high) | 1M | 专有 | 57 | $0.43 | 67 | 19.96 | 27.40 | -- | ||
Muse Spark 1.2 (xhigh) | 1.05M | 专有 | 57 | $0.40 | -- | -- | -- | -- | ||
GPT-5.6 Terra (max) | 1M | 专有 | 57 | $0.51 | 121 | 217.51 | 221.65 | -- | ||
GPT-5.6 Terra (max) | 1M | 专有 | 57 | $0.97 | 161 | 148.43 | 151.54 | -- | ||
Gemini 3.7 Flash (high) AI Studio | 1M | 专有 | 56 | $0.40 | 362 | 12.45 | 13.83 | -- | ||
Grok 4.5 (high) | 500k | 专有 | 56 | $0.36 | 56 | 14.06 | 22.97 | -- | ||
GPT-5.6 Sol (medium) | 1M | 专有 | 56 | $0.30 | 69 | 5.40 | 12.68 | -- | ||
Claude Sonnet 5 (max) | 1M | 专有 | 55 | $2.22 | 76 | 202.33 | 208.88 | -- | ||
Claude Sonnet 5 (max) | 1M | 专有 | 55 | $1.64 | 71 | 181.78 | 188.83 | -- | ||
Claude Sonnet 5 (max) | 1M | 专有 | 55 | $1.72 | 77 | 161.41 | 167.88 | -- | ||
Claude Sonnet 5 (max) | 1M | 专有 | 55 | $1.96 | 83 | 202.30 | 208.30 | -- | ||
Gemini 3.7 Flash (medium) AI Studio | 1M | 专有 | 53 | $0.26 | 365 | 5.88 | 7.25 | -- | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 53 | $0.25 | 65 | 1.57 | 40.15 | 30.86 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 53 | $0.53 | 63 | 3.51 | 42.91 | 31.52 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 53 | $0.52 | 74 | 3.36 | 37.21 | 27.08 | ||
DeepSeek V4 Pro 0813 (max) | 1M | 开放 | 53 | $0.66 | 107 | 1.58 | 24.84 | 18.61 | ||
DeepSeek V4 Pro 0813 (max) | 1M | 开放 | 53 | $1.12 | 179 | 1.03 | 15.02 | 11.19 | ||
DeepSeek V4 Pro 0813 (max) | 1M | 开放 | 53 | $0.47 | 60 | 1.63 | 43.53 | 33.52 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 53 | $0.35 | 65 | 1.90 | 40.25 | 30.68 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 53 | $0.39 | 66 | 2.78 | 40.58 | 30.24 | ||
GPT-5.6 Terra (xhigh) | 1M | 专有 | 53 | $0.31 | 106 | 37.12 | 41.82 | -- | ||
GLM-5.2 (max) | 205k | 开放 | 53 | $0.36 | 61 | 2.86 | 43.96 | 32.88 | ||
GLM-5.2 (max) | 1M | 开放 | 53 | $0.42 | 194 | 1.30 | 14.21 | 10.33 | ||
GLM-5.2 (max) (NVFP4) | 1M | 开放 | 53 | $0.34 | 294 | 0.86 | 9.37 | 6.80 | ||
GLM-5.2 (max) (FAST) | 524k | 开放 | 53 | $0.54 | 291 | 1.64 | 10.21 | 6.86 | ||
GLM-5.2 (max) (FP8) | 1.05M | 开放 | 53 | $0.42 | 78 | 1.58 | 33.72 | 25.71 | ||
GLM-5.2 (max) (NVFP4) | 1M | 开放 | 53 | -- | 175 | 0.92 | 15.19 | 11.41 | ||
GLM-5.2 (max) | 262k | 开放 | 53 | $0.38 | 178 | 1.24 | 15.29 | 11.24 | ||
GLM-5.2 (max) (FP4) | 1.05M | 开放 | 53 | $0.25 | 69 | 1.09 | 37.45 | 29.09 | ||
GLM-5.2 (max) (FP4) | 432k | 开放 | 53 | $1.06 | 173 | 1.14 | 15.61 | 11.58 | ||
GLM-5.2 (max) | 262k | 开放 | 53 | $0.67 | 166 | 0.78 | 15.80 | 12.02 | ||
GLM-5.2 (max) | 262k | 开放 | 53 | $1.57 | 92 | 1.72 | 28.81 | 21.67 | ||
GLM-5.2 (max) | 1M | 开放 | 53 | -- | 331 | 0.85 | 8.40 | 6.04 | ||
GLM-5.2 (max) (NVFP4) | 1M | 开放 | 53 | $0.42 | 192 | 0.97 | 14.03 | 10.44 | ||
GLM-5.2 (max) | 1M | 开放 | 53 | $0.17 | 150 | 8.12 | 24.79 | 13.34 | ||
GLM-5.2 (max) | 1M | 开放 | 53 | $0.48 | 73 | 1.52 | 35.68 | 27.33 | ||
GLM-5.2 (max) (FP8) | 1.05M | 开放 | 53 | -- | -- | -- | -- | -- | ||
GLM-5.2 (max) | 261k | 开放 | 53 | $0.46 | 113 | 1.65 | 23.74 | 17.67 | ||
GLM-5.2 (max) | 164k | 开放 | 53 | $0.51 | 226 | 1.22 | 12.28 | 8.85 | ||
GLM-5.2 (max) | 1M | 开放 | 53 | $0.44 | 69 | 1.54 | 37.61 | 28.85 | ||
GLM-5.2 (max) | 1.05M | 开放 | 53 | $0.38 | 197 | 1.05 | 13.74 | 10.16 | ||
GLM-5.2 (max) (FP8) | 1.05M | 开放 | 53 | $0.62 | 99 | 1.90 | 27.11 | 20.16 | ||
Claude Opus 5 (low) | 1M | 专有 | 52 | $0.43 | 54 | 3.55 | 12.75 | -- | ||
Claude Opus 5 (low) | 1M | 专有 | 52 | $0.43 | 54 | 3.11 | 12.32 | -- | ||
Claude Opus 5 (low) | 1M | 专有 | 52 | $0.55 | 55 | 3.01 | 12.08 | -- | ||
GPT-5.6 Luna (max) | 1M | 专有 | 52 | $0.05 | 131 | 150.68 | 154.49 | -- | ||
GPT-5.6 Luna (max) | 1M | 专有 | 52 | $0.34 | 237 | 85.43 | 87.54 | -- | ||
Qwen3.8 27B (xhigh) | 262k | 开放 | 52 | $0.31 | 47 | 0.97 | 54.04 | 42.45 | ||
Qwen3.8 27B (xhigh) | 1M | 开放 | 52 | $0.25 | 53 | 3.04 | 50.28 | 37.79 | ||
DeepSeek V4 Flash 0731 (max) | 262k | 开放 | 52 | $0.12 | 175 | 1.66 | 15.93 | 11.42 | ||
DeepSeek V4 Flash 0731 (max) (FAST) | 1M | 开放 | 52 | $0.17 | 291 | 2.17 | 10.75 | 6.86 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 52 | $0.20 | 80 | 2.06 | 33.41 | 25.07 | ||
DeepSeek V4 Flash 0731 (max) | 1M | 开放 | 52 | $0.11 | 120 | 1.06 | 21.86 | 16.64 | ||
DeepSeek V4 Flash 0731 (max) | 1M | 开放 | 52 | $0.02 | 113 | 4.08 | 26.28 | 17.76 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 52 | $0.13 | 58 | 1.63 | 44.53 | 34.32 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 52 | $0.11 | 104 | 0.90 | 25.05 | 19.32 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 52 | $0.09 | 67 | 1.66 | 39.13 | 29.97 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 52 | $0.14 | 169 | 0.85 | 15.61 | 11.80 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 52 | $0.12 | 124 | 2.39 | 22.53 | 16.11 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 52 | $0.20 | 113 | 1.57 | 23.60 | 17.63 | ||
DeepSeek V4 Flash 0731 (max) | 1M | 开放 | 52 | $0.05 | 78 | 0.81 | 32.68 | 25.50 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | 开放 | 52 | $0.06 | 82 | 0.56 | 31.19 | 24.50 | ||
DeepSeek V4 Flash 0731 (max) | 1M | 开放 | 52 | $0.13 | 295 | 0.71 | 9.18 | 6.78 | ||
Grok 4.6 (low) | 500k | 专有 | 52 | $0.22 | 58 | 7.74 | 16.34 | -- | ||
Gemini 3.6 Flash AI Studio | 1M | 专有 | 52 | $0.34 | 202 | 15.46 | 17.93 | -- | ||
DeepSeek V4 Flash Vision (max) | 1M | 专有 | 51 | $0.12 | 120 | 1.13 | 21.96 | 16.67 | ||
Gemini 3.7 Flash (low) AI Studio | 1M | 专有 | 51 | $0.16 | 333 | 1.23 | 2.74 | -- | ||
GPT-5.6 Sol (low) | 1M | 专有 | 51 | $0.19 | 72 | 3.21 | 10.20 | -- | ||
GPT-5.6 Terra (high) | 1M | 专有 | 50 | $0.22 | 108 | 3.10 | 7.75 | -- | ||
GPT-5.6 Luna (xhigh) | 1M | 专有 | 50 | $0.03 | 123 | 69.73 | 73.80 | -- | ||
Kimi K3 (low) | 1.05M | 开放 | 48 | $0.24 | 36 | 3.99 | 73.81 | 55.86 | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | 专有 | 48 | $0.33 | 118 | 27.39 | 31.63 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | 专有 | 48 | $0.43 | 134 | 27.31 | 31.05 | -- | ||
GPT-5.6 Luna (high) | 1M | 专有 | 47 | $0.02 | 129 | 16.96 | 20.85 | -- | ||
GPT-5.6 Terra (medium) | 1M | 专有 | 47 | $0.12 | 100 | 1.85 | 6.86 | -- | ||
Gemini 3.5 Flash (medium) | 1M | 专有 | 47* | -- | 205 | 15.42 | 17.86 | -- | ||
GPT-5.3 Codex (xhigh) | 400k | 专有 | 46* | -- | 146 | 68.34 | 71.76 | -- | ||
MiniMax-M3 (MXFP8) | 1M | 开放 | 45 | $0.18 | 82 | 1.25 | 31.66 | 24.33 | ||
MiniMax-M3 | 262k | 开放 | 45 | $0.11 | 189 | 1.24 | 14.44 | 10.56 | ||
MiniMax-M3 | 1M | 开放 | 45 | $0.21 | 134 | 0.68 | 19.36 | 14.95 | ||
MiniMax-M3 | 1M | 开放 | 45 | $0.13 | 137 | 1.49 | 19.67 | 14.55 | ||
MiniMax-M3 | 1M | 开放 | 45 | $0.18 | 214 | 0.54 | 12.25 | 9.37 | ||
MiniMax-M3 (FP8) | 1.05M | 开放 | 45 | $0.45 | 258 | 1.87 | 11.57 | 7.76 | ||
MiniMax-M3 (FP8) | 1M | 开放 | 45 | $0.12 | 112 | 1.34 | 23.56 | 17.78 | ||
MiniMax-M3 | 524k | 开放 | 45 | $0.12 | 40 | 8.02 | 70.56 | 50.04 | ||
MiniMax-M3 | 512k | 开放 | 45 | $0.14 | 126 | 1.38 | 21.29 | 15.93 | ||
MiniMax-M3 | 524k | 开放 | 45 | $0.12 | 31 | 1.34 | 81.75 | 64.32 | ||
MiniMax-M3 | 1.05M | 开放 | 45 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) (FP4) | 1.05M | 开放 | 45 | $0.27 | 60 | 1.29 | 82.50 | 72.88 | ||
DeepSeek V4 Pro (max) | 1M | 开放 | 45 | $0.89 | 80 | 1.70 | 62.54 | 54.60 | ||
DeepSeek V4 Pro (max) | 1.05M | 开放 | 45 | $0.23 | 66 | 1.65 | 75.05 | 65.87 | ||
DeepSeek V4 Pro (max) | 1M | 开放 | 45 | $0.21 | 31 | 2.02 | 159.75 | 141.55 | ||
DeepSeek V4 Pro (max) (FP8) | 1.05M | 开放 | 45 | $0.31 | 48 | 2.08 | 103.29 | 90.83 | ||
DeepSeek V4 Pro (max) | 1.05M | 开放 | 45 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) | 1M | 开放 | 45 | $0.90 | 130 | 1.31 | 38.80 | 33.64 | ||
DeepSeek V4 Pro (max) | 1.05M | 开放 | 45 | $0.38 | 75 | 1.56 | 66.30 | 58.10 | ||
DeepSeek V4 Pro (max) | 131k | 开放 | 45 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) | 1M | 开放 | 45 | $0.05 | 71 | 1.72 | 70.75 | 61.95 | ||
Qwen3.8 27B (medium) | 1M | 开放 | 44 | $0.19 | 59 | 3.05 | 45.31 | 33.81 | ||
DeepSeek V4 Pro (high) (FP4) | 65.5k | 开放 | 44 | $0.26 | 60 | 1.22 | 42.87 | 33.29 | ||
DeepSeek V4 Pro (high) | 1.05M | 开放 | 44 | $0.36 | 70 | 1.55 | 37.13 | 28.44 | ||
DeepSeek V4 Pro (high) | 1M | 开放 | 44 | $0.94 | 92 | 1.51 | 28.52 | 21.59 | ||
DeepSeek V4 Pro (high) | 1M | 开放 | 44 | $0.04 | 70 | 1.65 | 37.26 | 28.47 | ||
DeepSeek V4 Pro (high) | 1M | 开放 | 44 | $0.18 | 38 | 4.32 | 70.32 | 52.76 | ||
DeepSeek V4 Pro (high) (FP8) | 1.05M | 开放 | 44 | $0.29 | 50 | 2.52 | 51.94 | 39.50 | ||
DeepSeek V4 Pro (high) | 1M | 开放 | 44 | $0.94 | 127 | 1.32 | 20.94 | 15.68 | ||
DeepSeek V4 Pro (high) | 1.05M | 开放 | 44 | $0.20 | 67 | 1.73 | 38.75 | 29.60 | ||
DeepSeek V4 Pro (high) | 131k | 开放 | 44 | $0.68 | 159 | 0.70 | 16.33 | 12.49 | ||
Kimi K2.7 Code (FP4) | 256k | 开放 | 43 | $0.64 | 218 | 1.82 | 14.37 | 10.25 | ||
Kimi K2.7 Code (FP8) | 65.5k | 开放 | 43 | $0.46 | 62 | 4.25 | 47.94 | 35.68 | ||
Kimi K2.7 Code | 262k | 开放 | 43 | $0.28 | 318 | 1.11 | 9.69 | 7.01 | ||
Kimi K2.7 Code | 262k | 开放 | 43 | $0.18 | 77 | 1.30 | 36.97 | 29.14 | ||
Kimi K2.7 Code | 262k | 开放 | 43 | $0.30 | 170 | 0.44 | 16.49 | 13.11 | ||
Kimi K2.7 Code | 262k | 开放 | 43 | $0.29 | -- | -- | -- | -- | ||
Kimi K2.7 Code | 262k | 开放 | 43 | $0.57 | 139 | 0.59 | 20.28 | 16.09 | ||
Kimi K2.7 Code | 262k | 开放 | 43 | $0.23 | 46 | 3.70 | 63.62 | 48.95 | ||
Kimi K2.7 Code | 262k | 开放 | 43 | $0.16 | 47 | 0.60 | 59.01 | 47.71 | ||
Kimi K2.7 Code | 256k | 开放 | 43 | $0.22 | 47 | 2.89 | 60.39 | 46.96 | ||
MiMo-V2.5-Pro | 1.05M | 开放 | 43 | $0.04 | 52 | 3.35 | 51.22 | 38.29 | ||
MiMo-V2.5-Pro | 1.05M | 开放 | 43 | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | 开放 | 43 | $0.18 | 130 | 0.76 | 19.97 | 15.37 | ||
MiMo-V2.5-Pro | 1M | 开放 | 43 | $0.03 | 49 | 3.42 | 54.86 | 41.15 | ||
Qwen3.8 27B (low) | 1M | 开放 | 43 | $0.17 | 64 | 3.00 | 42.33 | 31.46 | ||
Claude Sonnet 5 (Non-reasoning) | 1M | 专有 | 43 | $0.42 | 70 | 1.78 | 8.94 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 1M | 专有 | 43 | $0.61 | 66 | 1.70 | 9.31 | -- | ||
Inkling (FP8) | 131k | 开放 | 42 | $0.43 | 191 | 0.55 | 13.63 | 10.46 | ||
Inkling | 262k | 开放 | 42 | $0.34 | 264 | 0.61 | 10.07 | 7.57 | ||
Inkling | 524k | 开放 | 42 | $0.62 | 146 | 0.85 | 17.99 | 13.71 | ||
Inkling | 262k | 开放 | 42 | $0.34 | 50 | 2.83 | 53.31 | 40.38 | ||
Hy3 (FP8) | 256k | 开放 | 42 | $0.03 | 84 | 2.88 | 32.64 | 23.81 | ||
Hy3 | 262k | 开放 | 42 | $0.04 | 79 | 2.95 | 34.53 | 25.26 | ||
Hy3 (FP8) | 262k | 开放 | 42 | $0.04 | 75 | 1.03 | 34.18 | 26.52 | ||
Hy3 | 262k | 开放 | 42 | $0.03 | 80 | 3.29 | 34.41 | 24.89 | ||
GPT-5.6 Sol (Non-reasoning) | 1M | 专有 | 42 | $0.19 | 64 | 1.33 | 9.19 | -- | ||
GPT-5.6 Sol (Non-reasoning) | 1M | 专有 | 42 | $0.30 | 99 | 1.25 | 6.31 | -- | ||
Nex-N2-Pro (FP8) | 262k | 开放 | 42 | -- | 130 | 1.62 | 20.84 | 15.38 | ||
Solar Pro 4 | 512k | 专有 | 42 | $0.22 | 59 | 2.16 | 44.52 | 33.89 | ||
GPT-5.6 Terra (low) | 1M | 专有 | 41 | $0.09 | 105 | 1.48 | 6.22 | -- | ||
Inkling Small | 256k | 开放 | 41 | $0.07 | 133 | 2.00 | 20.85 | 15.08 | ||
Inkling Small | 524k | 开放 | 41 | $0.13 | 240 | 0.73 | 11.14 | 8.33 | ||
Inkling Small | 262k | 开放 | 41 | $0.13 | 346 | 0.46 | 7.69 | 5.78 | ||
Agnes 2.5 Pro Alpha | 1M | 专有 | 40 | -- | 130 | 2.22 | 21.50 | 15.42 | ||
Qwen3.7 Plus | 1M | 专有 | 39 | $0.24 | 56 | 2.16 | 46.96 | 35.84 | ||
GPT-5.6 Luna (medium) | 1M | 专有 | 39 | $0.01 | 130 | 2.53 | 6.36 | -- | ||
Nemotron 3 Ultra | 262k | 开放 | 38 | $0.16 | 294 | 1.10 | 10.53 | 7.73 | ||
Nemotron 3 Ultra | 262k | 开放 | 38 | -- | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 512k | 开放 | 38 | $0.40 | 178 | 0.67 | 16.30 | 12.81 | ||
Nemotron 3 Ultra | 262k | 开放 | 38 | $0.23 | 92 | 6.04 | 36.24 | 24.75 | ||
Nemotron 3 Ultra BF16 | 262k | 开放 | 38 | -- | 86 | 7.16 | 39.40 | 26.43 | ||
Nemotron 3 Ultra | 256k | 开放 | 38 | $0.60 | 380 | 2.30 | 9.61 | 5.99 | ||
Nemotron 3 Ultra | 262k | 开放 | 38 | $0.25 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | 开放 | 38 | $0.19 | -- | -- | -- | -- | ||
MiMo-V2.5 | 1.05M | 开放 | 38 | $0.01 | 66 | 2.41 | 40.38 | 30.38 | ||
MiMo-V2.5 | 1M | 开放 | 38 | $0.04 | 72 | 1.18 | 36.12 | 27.95 | ||
MiMo-V2.5 | 262k | 开放 | 38 | $0.08 | 55 | 0.75 | 46.51 | 36.61 | ||
MiMo-V2.5 | 1.05M | 开放 | 38 | $0.02 | -- | -- | -- | -- | ||
MiMo-V2.5 | 1M | 开放 | 38 | $0.01 | 69 | 3.87 | 39.90 | 28.82 | ||
Ling 3.0 Flash | 131k | 开放 | 38 | $0.03 | 109 | 0.81 | 23.72 | 18.33 | ||
Ling 3.0 Flash | 262k | 开放 | 38 | $0.04 | 387 | 2.44 | 8.90 | 5.17 | ||
Qwen3.6 27B FP8 | 262k | 开放 | 38 | $0.19 | 32 | 1.22 | 194.19 | 177.34 | ||
Qwen3.6 27B | 131k | 开放 | 38 | $0.27 | 445 | 1.32 | 15.20 | 12.76 | ||
Qwen3.6 27B | 262k | 开放 | 38 | $0.29 | 57 | 3.09 | 112.23 | 100.31 | ||
Qwen3.6 27B | 262k | 开放 | 38 | $0.29 | 56 | 3.74 | 114.26 | 101.58 | ||
Qwen3.6 27B | 262k | 开放 | 38 | $0.07 | 175 | 1.30 | 36.69 | 32.52 | ||
Qwen3.6 27B (FP8) | 262k | 开放 | 38 | $0.19 | 36 | 3.38 | 173.73 | 156.55 | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | 专有 | 37 | $0.10 | 366 | 8.60 | 9.96 | -- | ||
Grok 4.3 (medium) | 524k | 专有 | 37* | -- | 281 | 6.10 | 7.88 | -- | ||
Grok 4.3 (medium) | 200k | 专有 | 37* | -- | 159 | 10.58 | 13.72 | -- | ||
Grok 4.3 (medium) | 1M | 专有 | 37* | -- | 133 | 11.47 | 15.22 | -- | ||
Grok 4.3 (low) | 524k | 专有 | 36* | -- | 248 | 2.89 | 4.91 | -- | ||
Grok 4.3 (low) | 200k | 专有 | 36* | -- | 149 | 5.52 | 8.87 | -- | ||
Grok 4.3 (low) | 1M | 专有 | 36* | -- | 135 | 5.77 | 9.46 | -- | ||
Gemini 3.5 Flash (minimal) AI Studio | 1M | 专有 | 36* | -- | 184 | 0.79 | 3.51 | -- | ||
Claude Sonnet 4.6 (Non-reasoning, Low Effort) | 1M | 专有 | 35* | -- | 48 | 1.50 | 12.01 | -- | ||
Muse Glimmer (high) | 131k | 开放 | 35 | $0.08 | 91 | 0.83 | 28.25 | 21.94 | ||
Muse Glimmer (high) | 131k | 开放 | 35 | $0.07 | 160 | 0.76 | 16.42 | 12.53 | ||
GLM-5.2 (FAST) | 524k | 开放 | 35 | -- | 224 | 1.48 | 3.71 | -- | ||
GLM-5.2 (FP4) | 432k | 开放 | 35 | -- | 145 | 1.14 | 4.58 | -- | ||
GLM-5.2 | 262k | 开放 | 35 | -- | 87 | 1.64 | 7.37 | -- | ||
GLM-5.2 | 205k | 开放 | 35 | -- | 61 | 2.92 | 11.08 | -- | ||
GLM-5.2 | 1M | 开放 | 35 | -- | 148 | 5.27 | 8.66 | -- | ||
GLM-5.2 (FP8) | 1.05M | 开放 | 35 | -- | 87 | 1.93 | 7.70 | -- | ||
GLM-5.2 | 164k | 开放 | 35 | -- | 196 | 1.07 | 3.63 | -- | ||
Qwen3.8 27B | 1M | 开放 | 35 | $0.21 | 64 | 3.03 | 10.80 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 1M | 专有 | 35 | $0.10 | 107 | 0.87 | 5.56 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 1M | 专有 | 35 | $0.20 | 144 | 0.59 | 4.07 | -- | ||
Qwen3.5 397B A17B | 262k | 开放 | 34 | $0.36 | 81 | 2.24 | 47.65 | 39.26 | ||
Qwen3.5 397B A17B | 262k | 开放 | 34 | $0.12 | 75 | 3.38 | 52.49 | 42.46 | ||
Qwen3.5 397B A17B | 262k | 开放 | 34 | $0.23 | 79 | 1.00 | 47.45 | 40.15 | ||
Qwen3.5 397B A17B (FP8) | 262k | 开放 | 34 | $0.23 | 88 | 2.15 | 43.97 | 36.14 | ||
Qwen3.5 397B A17B (FP8) | 262k | 开放 | 34 | $0.19 | 40 | 1.12 | 93.10 | 79.50 | ||
Qwen3.5 397B A17B | 262k | 开放 | 34 | $0.15 | 13 | 1.33 | 288.16 | 247.92 | ||
Qwen3.5 397B A17B (FP8) | 262k | 开放 | 34 | $0.36 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | 开放 | 34 | $0.36 | 135 | 2.00 | 29.40 | 23.68 | ||
Qwen3.5 397B A17B | 262k | 开放 | 34 | $0.36 | 79 | 1.81 | 48.40 | 40.27 | ||
G9v3-39A5B | 131k | 开放 | 34 | $0.00 | -- | -- | -- | -- | ||
LongCat 2.0 (FP8) | 1M | 开放 | 34 | $0.12 | 42 | 2.74 | 62.61 | 47.89 | ||
GPT-5.6 Luna (low) | 1M | 专有 | 34 | $0.01 | 123 | 1.46 | 5.54 | -- | ||
KAT-Coder-Pro V2 | 256k | 专有 | 34 | -- | 102 | 1.41 | 6.31 | -- | ||
KAT-Coder-Pro V2 | 256k | 专有 | 34 | -- | -- | -- | -- | -- | ||
Qwen3.5 122B A10B (FP8) | 262k | 开放 | 33 | $0.16 | 40 | 1.98 | 64.51 | 50.03 | ||
Qwen3.5 122B A10B (FP4) | 262k | 开放 | 33 | $0.12 | 147 | 0.81 | 17.83 | 13.61 | ||
Qwen3.5 122B A10B | 262k | 开放 | 33 | $0.25 | 131 | 2.34 | 21.35 | 15.21 | ||
Qwen3.5 122B A10B (FP8) | 262k | 开放 | 33 | $0.25 | -- | -- | -- | -- | ||
Qwen3.5 122B A10B | 262k | 开放 | 33 | $0.25 | 115 | 1.76 | 23.57 | 17.45 | ||
Qwen3.5 397B A17B | 262k | 开放 | 33* | -- | 76 | 3.61 | 10.16 | -- | ||
Qwen3.5 397B A17B (FP8) | 262k | 开放 | 33* | -- | 40 | 1.17 | 13.79 | -- | ||
Qwen3.5 397B A17B | 262k | 开放 | 33* | -- | 77 | 2.20 | 8.68 | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | 开放 | 33* | -- | 136 | 2.05 | 5.71 | -- | ||
Qwen3.5 397B A17B | 262k | 开放 | 33* | -- | 21 | 1.24 | 25.36 | -- | ||
Qwen3.5 397B A17B | 262k | 开放 | 33* | -- | 77 | 1.51 | 8.00 | -- | ||
Qwen3.6 35B A3B | 229k | 开放 | 32 | $0.29 | 122 | 2.12 | 50.46 | 44.24 | ||
Qwen3.6 35B A3B (FP8) | 262k | 开放 | 32 | $0.17 | 77 | 2.09 | 78.64 | 70.06 | ||
Qwen3.6 35B A3B | 262k | 开放 | 32 | $0.23 | 185 | 0.90 | 32.72 | 29.12 | ||
Qwen3.6 35B A3B (FP8) | 262k | 开放 | 32 | $0.09 | 65 | 0.76 | 91.19 | 82.76 | ||
Qwen3.6 35B A3B FP8 | 262k | 开放 | 32 | $0.19 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | 开放 | 32 | $0.08 | 106 | 0.85 | 56.68 | 51.10 | ||
Qwen3.6 35B A3B | 205k | 开放 | 32 | $0.19 | 130 | 1.44 | 46.95 | 41.65 | ||
DeepSeek V4 Pro | 1M | 开放 | 32* | -- | 99 | 1.70 | 6.77 | -- | ||
DeepSeek V4 Pro | 1M | 开放 | 32* | -- | 36 | 3.18 | 17.14 | -- | ||
DeepSeek V4 Pro | 1.05M | 开放 | 32* | -- | 117 | 1.51 | 5.78 | -- | ||
DeepSeek V4 Pro | 1M | 开放 | 32* | -- | 70 | 1.80 | 8.98 | -- | ||
Ring-2.6-1T | 262k | 开放 | 32 | $0.36 | 129 | 4.44 | 23.87 | 15.54 | ||
Qwen3.5 Omni Plus | 256k | 专有 | 31* | -- | 56 | 2.38 | 11.29 | -- | ||
Qwen3.6 27B | 131k | 开放 | 31 | $0.39 | 460 | 1.11 | 2.20 | -- | ||
Qwen3.6 27B | 262k | 开放 | 31 | $0.10 | 154 | 0.85 | 4.10 | -- | ||
Qwen3.6 27B FP8 | 262k | 开放 | 31 | $0.23 | 45 | 1.13 | 12.16 | -- | ||
Qwen3.6 27B | 262k | 开放 | 31 | $0.40 | 58 | 3.83 | 12.51 | -- | ||
Qwen3.6 27B | 262k | 开放 | 31 | $0.40 | 60 | 3.06 | 11.34 | -- | ||
o3 | 200k | 专有 | 31* | -- | 119 | 23.97 | 28.18 | -- | ||
o3 | 200k | 专有 | 31* | -- | -- | -- | -- | -- | ||
o3 | 200k | 专有 | 31* | -- | 135 | 8.49 | 12.20 | -- | ||
Step 3.7 Flash | 256k | 开放 | 31 | $0.09 | 109 | 2.82 | 25.85 | 18.42 | ||
Step 3.7 Flash | 256k | 开放 | 31 | -- | 172 | 0.65 | 15.19 | 11.63 | ||
Mistral Medium 3.5 | 262k | 开放 | 30 | $0.46 | 144 | 2.20 | 19.57 | 13.89 | ||
Claude 4.5 Haiku | 200k | 专有 | 30 | $0.24 | 122 | 13.02 | 17.11 | -- | ||
Claude 4.5 Haiku Vertex | 200k | 专有 | 30 | $0.25 | 122 | 30.56 | 34.67 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 30 | $0.22 | 118 | 21.43 | 25.67 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 30 | $0.54 | 103 | 22.54 | 27.40 | -- | ||
Gemma 4 31B | 262k | 开放 | 30 | -- | 35 | 1.96 | 66.61 | 50.19 | ||
Gemma 4 31B (NVFP4) | 262k | 开放 | 30 | -- | 233 | 0.47 | 10.07 | 7.45 | ||
Gemma 4 31B (FP8) | 262k | 开放 | 30 | $0.04 | -- | -- | -- | -- | ||
Gemma 4 31B | 262k | 开放 | 30 | $0.04 | -- | -- | -- | -- | ||
Gemma 4 31B | 131k | 开放 | 30 | $0.24 | 1,496 | 0.54 | 2.04 | 1.16 | ||
Gemma 4 31B (AI Studio) | 262k | 开放 | 30 | $0.00 | 35 | 1.08 | 64.84 | 49.51 | ||
Gemma 4 31B | 262k | 开放 | 30 | $0.02 | 68 | 1.46 | 34.40 | 25.57 | ||
Gemma 4 31B | 262k | 开放 | 30 | $0.01 | 55 | 1.28 | 42.06 | 31.66 | ||
Gemma 4 31B (FP8) | 262k | 开放 | 30 | $0.03 | 55 | 3.45 | 44.29 | 31.71 | ||
Gemma 4 31B | 131k | 开放 | 30 | $0.10 | 196 | 2.53 | 13.93 | 8.85 | ||
Gemma 4 31B | 256k | 开放 | 30 | $0.04 | 168 | 1.28 | 14.55 | 10.30 | ||
Gemma 4 31B | 131k | 开放 | 30 | $0.04 | 152 | 0.81 | 15.54 | 11.43 | ||
Gemma 4 31B (FP8) | 262k | 开放 | 30 | $0.10 | 56 | 1.41 | 41.23 | 30.91 | ||
DeepSeek V4 Flash | 1.05M | 开放 | 29* | -- | -- | -- | -- | -- | ||
DeepSeek V4 Flash | 1M | 开放 | 29* | -- | 317 | 0.78 | 2.35 | -- | ||
DeepSeek V4 Flash | 1M | 开放 | 29* | -- | 66 | 1.56 | 9.11 | -- | ||
GPT-5.5 Instant (June 2026) | 400k | 专有 | 29 | $0.54 | 132 | 1.06 | 20.00 | 15.15 | ||
MiMo-V2.5-Pro | 1.05M | 开放 | 28* | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | 开放 | 28* | -- | 117 | 0.72 | 4.98 | -- | ||
MiMo-V2.5-Pro | 131k | 开放 | 28* | -- | 42 | 5.74 | 17.52 | -- | ||
MiMo-V2.5-Pro | 1.05M | 开放 | 28* | -- | 47 | 3.25 | 13.90 | -- | ||
Qwen3.5 122B A10B (FP4) | 262k | 开放 | 28 | $0.10 | 154 | 0.89 | 4.13 | -- | ||
Qwen3.5 122B A10B | 262k | 开放 | 28 | $0.20 | 146 | 2.31 | 5.74 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 1M | 专有 | 27 | $0.01 | 125 | 0.68 | 4.68 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 1M | 专有 | 27 | $0.09 | 211 | 0.60 | 2.97 | -- | ||
Gemma 4 26B A4B | 1M | 开放 | 26 | $0.02 | 171 | 1.00 | 15.59 | 11.67 | ||
Gemma 4 26B A4B | 262k | 开放 | 26 | $0.04 | 40 | 1.67 | 63.67 | 49.60 | ||
Gemma 4 26B A4B AI Studio | 262k | 开放 | 26 | $0.00 | 47 | 1.05 | 54.56 | 42.81 | ||
Gemma 4 26B A4B | 256k | 开放 | 26 | $0.03 | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | 开放 | 26 | $0.03 | 28 | 0.74 | 89.08 | 70.67 | ||
Gemma 4 26B A4B | 256k | 开放 | 26 | $0.03 | 51 | 1.45 | 50.05 | 38.88 | ||
Gemma 4 26B A4B (FP8) | 1.05M | 开放 | 26 | $0.04 | -- | -- | -- | -- | ||
Nemotron 3 Super | 262k | 开放 | 26 | $0.23 | 142 | 0.94 | 18.59 | 14.12 | ||
Nemotron 3 Super | 256k | 开放 | 26 | $0.33 | 374 | 1.81 | 8.49 | 5.35 | ||
Nemotron 3 Super | 262k | 开放 | 26 | $0.10 | 60 | 29.84 | 71.28 | 33.15 | ||
Grok 4.3 (Non-reasoning) | 524k | 专有 | 25 | $0.91 | 248 | 0.73 | 2.74 | -- | ||
Grok 4.3 (Non-reasoning) | 1M | 专有 | 25 | $0.29 | 131 | 0.71 | 4.51 | -- | ||
Qwen3.6 35B A3B | 262k | 开放 | 25 | $0.49 | 187 | 0.99 | 3.67 | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | 开放 | 25 | $0.29 | 65 | 0.74 | 8.42 | -- | ||
Qwen3.6 35B A3B | 205k | 开放 | 25 | $0.42 | 141 | 1.23 | 4.77 | -- | ||
Qwen3.6 35B A3B FP8 | 262k | 开放 | 25 | $0.42 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | 开放 | 25 | $0.15 | 104 | 0.87 | 5.69 | -- | ||
Qwen3.6 35B A3B | 262k | 开放 | 25 | $0.63 | 140 | 1.97 | 5.55 | -- | ||
Ling 3.0 Tiny | 262k | 开放 | 25 | $0.00 | -- | -- | -- | -- | ||
Ling 3.0 Tiny | 262k | 开放 | 25 | $0.00 | 156 | 2.64 | 18.64 | 12.81 | ||
Qwen3.5 35B A3B FP8 | 262k | 开放 | 24 | $0.07 | 116 | 0.51 | 4.81 | -- | ||
Qwen3.5 35B A3B | 262k | 开放 | 24 | $0.24 | 169 | 2.03 | 4.99 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 24* | -- | 94 | 1.14 | 6.45 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 24* | -- | 109 | 1.02 | 5.61 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 24* | -- | 94 | 0.77 | 6.07 | -- | ||
Claude 4.5 Haiku Vertex | 200k | 专有 | 24* | -- | 100 | 0.64 | 5.66 | -- | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.06 | 475 | 0.74 | 6.00 | 4.21 | ||
gpt-oss-120b (high) | 116k | 开放 | 24 | $0.15 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | 开放 | 24 | $0.08 | 154 | 1.21 | 17.41 | 12.95 | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.02 | 48 | 1.31 | 53.06 | 41.39 | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.07 | 325 | 0.69 | 8.39 | 6.16 | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.03 | 100 | 0.94 | 25.85 | 19.93 | ||
gpt-oss-120b (high) (Turbo) | 131k | 开放 | 24 | $0.07 | 233 | 0.76 | 11.49 | 8.58 | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.02 | 44 | 0.60 | 57.54 | 45.55 | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.15 | 1,685 | 0.47 | 1.95 | 1.19 | ||
gpt-oss-120b (high) Vertex | 131k | 开放 | 24 | $0.04 | 77 | 0.93 | 33.60 | 26.14 | ||
gpt-oss-120b (high) | 128k | 开放 | 24 | $0.05 | 344 | 0.24 | 7.50 | 5.81 | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.10 | 700 | 0.88 | 4.45 | 2.86 | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | -- | 135 | 0.69 | 19.27 | 14.86 | ||
gpt-oss-120b (high) (Base) | 128k | 开放 | 24 | $0.07 | 327 | 0.98 | 8.64 | 6.13 | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.11 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.07 | 92 | 0.97 | 28.02 | 21.64 | ||
gpt-oss-120b (high) | 131k | 开放 | 24 | $0.07 | 147 | 0.55 | 17.59 | 13.63 | ||
Nemotron 3.5 Lightning (NVFP4) | 28.7k | 开放 | 24 | $0.10 | 416 | 0.42 | 6.43 | 4.80 | ||
Nemotron 3.5 Lightning (BF16) | 1.05M | 开放 | 24 | $0.07 | 190 | 1.81 | 14.96 | 10.52 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 24 | $0.08 | 344 | 0.84 | 8.12 | 5.82 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 24 | $0.10 | 350 | 1.65 | 8.79 | 5.71 | ||
Nemotron 3.5 Lightning (BF16) | 65.5k | 开放 | 24 | $0.00 | 307 | 2.01 | 10.16 | 6.52 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 24 | $0.03 | 554 | 0.50 | 5.01 | 3.61 | ||
Command A+ | 200k | 开放 | 23 | $0.00 | 259 | 0.38 | 10.03 | 7.72 | ||
Gemma 4 31B (NVFP4) | 262k | 开放 | 22 | -- | 242 | 0.46 | 2.53 | -- | ||
Gemma 4 31B | 262k | 开放 | 22 | $0.03 | 54 | 1.46 | 10.66 | -- | ||
Gemma 4 31B | 131k | 开放 | 22 | $0.28 | 1,360 | 0.53 | 0.90 | -- | ||
Gemma 4 31B | 262k | 开放 | 22 | $0.04 | 179 | 1.63 | 4.42 | -- | ||
Gemma 4 31B (FP8) | 262k | 开放 | 22 | $0.11 | 62 | 1.19 | 9.24 | -- | ||
Gemma 4 31B (FP8) | 262k | 开放 | 22 | $0.04 | 54 | 3.42 | 12.63 | -- | ||
Gemma 4 31B (FP8) | 262k | 开放 | 22 | $0.04 | 60 | 1.07 | 9.38 | -- | ||
Gemma 4 31B | 131k | 开放 | 22 | $0.11 | 202 | 2.59 | 5.06 | -- | ||
Gemma 4 31B | 262k | 开放 | 22 | $0.04 | 51 | 1.41 | 11.20 | -- | ||
Gemma 4 12B | 262k | 开放 | 22* | -- | 110 | 2.30 | 24.94 | 18.11 | ||
Nova 2.0 Pro Preview (medium) | 256k | 专有 | 22* | -- | 122 | 15.20 | 35.67 | 16.38 | ||
Mercury 2 | 128k | 专有 | 22 | $0.08 | 950 | 4.04 | 4.56 | -- | ||
Qwen3.5 9B (FP8) | 262k | 开放 | 22 | $0.18 | 66 | 2.47 | 40.28 | 30.25 | ||
Qwen3.5 9B (FP8) | 262k | 开放 | 22 | $0.30 | 81 | 0.73 | 31.73 | 24.80 | ||
Qwen3 Coder Next | 128k | 开放 | 21 | $0.47 | 121 | 0.96 | 5.08 | -- | ||
Qwen3 Coder Next (FP8) | 262k | 开放 | 21 | $0.08 | 88 | 0.89 | 6.58 | -- | ||
Qwen3 Coder Next (FP8) | 262k | 开放 | 21 | $0.47 | -- | -- | -- | -- | ||
Qwen3 Coder Next (FP8) | 262k | 开放 | 21 | $0.21 | 176 | 2.38 | 5.23 | -- | ||
Nova 2.0 Omni (medium) | 1M | 专有 | 21* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (medium) | 1M | 专有 | 21* | -- | -- | -- | -- | -- | ||
Apriel-v1.6-15B-Thinker | 131k | 开放 | 21* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | 专有 | 21* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | 专有 | 21* | -- | 178 | 17.42 | 31.46 | 11.23 | ||
Qwen3.5 9B (FP8) | 262k | 开放 | 21* | -- | 88 | 0.82 | 6.51 | -- | ||
Gemma 4 26B A4B | 1M | 开放 | 20* | -- | 163 | 0.94 | 4.02 | -- | ||
Gemma 4 26B A4B | 262k | 开放 | 20* | -- | 44 | 1.49 | 12.74 | -- | ||
Gemma 4 26B A4B (FP8) | 1.05M | 开放 | 20* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | 开放 | 20* | -- | 106 | 2.16 | 6.87 | -- | ||
Gemma 4 26B A4B | 262k | 开放 | 20* | -- | 133 | 1.01 | 4.77 | -- | ||
Gemma 4 26B A4B (FP8) | 262k | 开放 | 20* | -- | 30 | 0.76 | 17.34 | -- | ||
Gemma 4 26B A4B | 262k | 开放 | 20* | -- | 31 | 1.30 | 17.43 | -- | ||
Qwen3.5 4B (FP8) | 262k | 开放 | 20* | -- | 26 | 0.77 | 97.51 | 77.39 | ||
North Mini Code | 256k | 开放 | 20 | $0.00 | 25 | 0.50 | 100.07 | 79.66 | ||
Nova 2.0 Pro Preview (low) | 256k | 专有 | 20* | -- | 129 | 10.84 | 30.16 | 15.46 | ||
Mistral Small 4 | 256k | 开放 | 20 | $0.10 | 174 | 0.76 | 15.10 | 11.47 | ||
Devstral 2 | 262k | 开放 | 19 | $0.00 | 49 | 1.53 | 11.64 | -- | ||
Nova 2.0 Lite (medium) | 1M | 专有 | 19* | -- | 191 | 18.04 | 31.11 | 10.45 | ||
Qwen3.5 Omni Flash | 256k | 专有 | 19* | -- | 247 | 1.80 | 3.82 | -- | ||
Trinity Large Thinking | 262k | 开放 | 19 | $0.20 | 196 | 1.30 | 14.04 | 10.19 | ||
Trinity Large Thinking (FP8) | 262k | 开放 | 19 | $0.08 | 165 | 0.61 | 15.74 | 12.10 | ||
HyperNova 60B 2605 | 131k | 开放 | 18 | $0.02 | 366 | 0.84 | 7.68 | 5.47 | ||
Nova 2.0 Lite (low) | 1M | 专有 | 18* | -- | 177 | 9.06 | 23.18 | 11.29 | ||
Devstral Small 2 | 256k | 开放 | 18 | $0.00 | 138 | 2.21 | 5.83 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 17 | $0.05 | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | 开放 | 17 | $0.04 | 165 | 0.72 | 15.89 | 12.14 | ||
Qwen3 Next 80B A3B | 262k | 开放 | 17 | $0.04 | 202 | 2.31 | 14.66 | 9.88 | ||
Qwen3 Next 80B A3B (FP8) | 262k | 开放 | 17 | $0.04 | 96 | 1.13 | 27.27 | 20.91 | ||
Qwen3 Next 80B A3B | 262k | 开放 | 17 | $0.03 | -- | -- | -- | -- | ||
Nova 2.0 Omni (low) | 1M | 专有 | 17* | -- | -- | -- | -- | -- | ||
G9v3-3B | 131k | 开放 | 16* | -- | -- | -- | -- | -- | ||
Qwen3.5 4B FP8 | 262k | 开放 | 16* | -- | 19 | 0.81 | 27.68 | -- | ||
Mistral Large 3 | 256k | 开放 | 16 | $0.08 | 207 | 1.18 | 3.60 | -- | ||
Mistral Large 3 | 256k | 开放 | 16 | $0.08 | 78 | 1.74 | 8.19 | -- | ||
Mistral Large 3 | 262k | 开放 | 16 | $0.08 | 49 | 1.17 | 11.31 | -- | ||
gpt-oss-20b (high) | 131k | 开放 | 15 | $0.01 | 95 | 0.90 | 27.08 | 20.95 | ||
gpt-oss-20b (high) | 131k | 开放 | 15 | $0.03 | 192 | 37.19 | 50.19 | 10.40 | ||
gpt-oss-20b (high) | 131k | 开放 | 15 | $0.01 | 98 | 0.41 | 26.01 | 20.47 | ||
gpt-oss-20b (high) | 131k | 开放 | 15 | $0.04 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | 开放 | 15 | $0.02 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | 开放 | 15 | $0.08 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 131k | 开放 | 15 | $0.02 | 126 | 1.22 | 21.06 | 15.88 | ||
gpt-oss-20b (high) Vertex | 131k | 开放 | 15 | $0.03 | 148 | 13.86 | 30.73 | 13.49 | ||
gpt-oss-20b (high) | 131k | 开放 | 15 | $0.03 | 951 | 0.81 | 3.44 | 2.10 | ||
Nemotron 3 Nano Omni 30B A3B (FP8) | 65.5k | 开放 | 15* | -- | 324 | 0.98 | 8.69 | 6.17 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.04 | -- | -- | -- | -- | ||
gpt-oss-120b (low) Base | 128k | 开放 | 15 | $0.02 | 343 | 0.99 | 8.28 | 5.83 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.03 | 730 | 0.89 | 4.31 | 2.74 | ||
gpt-oss-120b (low) Vertex | 131k | 开放 | 15 | $0.01 | 63 | 0.82 | 40.67 | 31.88 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.01 | 42 | 0.61 | 60.73 | 48.10 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.0042 | 45 | 1.39 | 56.98 | 44.48 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.05 | 1,728 | 0.49 | 1.94 | 1.16 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.02 | 341 | 0.76 | 8.09 | 5.86 | ||
gpt-oss-120b (low) | 128k | 开放 | 15 | $0.05 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 128k | 开放 | 15 | $0.01 | 343 | 0.22 | 7.51 | 5.83 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.02 | 86 | 1.06 | 30.24 | 23.34 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | -- | 125 | 0.70 | 20.68 | 15.98 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.02 | 130 | 0.64 | 19.91 | 15.41 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.02 | 476 | 0.75 | 6.00 | 4.20 | ||
gpt-oss-120b (low) | 131k | 开放 | 15 | $0.01 | 104 | 0.92 | 25.02 | 19.28 | ||
Nemotron 3 Nano | 262k | 开放 | 15 | $0.03 | 308 | 1.08 | 9.21 | 6.50 | ||
Nemotron 3 Nano (FP4) | 262k | 开放 | 15 | $0.02 | 243 | 0.98 | 11.28 | 8.24 | ||
Nemotron 3 Nano | 262k | 开放 | 15 | $0.02 | 224 | 3.12 | 14.30 | 8.95 | ||
Solar Pro 3 | 131k | 专有 | 14 | $0.15 | 153 | 2.29 | 18.67 | 13.10 | ||
Llama 4 Maverick (FP8) | 1.05M | 开放 | 14 | $0.04 | 77 | 0.79 | 7.31 | -- | ||
Llama 4 Maverick (FP8) | 128k | 开放 | 14 | $0.03 | 468 | 1.24 | 2.31 | -- | ||
Llama 4 Maverick | 128k | 开放 | 14 | $0.03 | 233 | 0.78 | 2.93 | -- | ||
Llama 4 Maverick | 1.05M | 开放 | 14 | $0.04 | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | 开放 | 14 | $0.03 | 76 | 0.50 | 7.11 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | 开放 | 14 | $0.03 | 101 | 1.11 | 6.05 | -- | ||
Nova 2.0 Pro Preview | 256k | 专有 | 14* | -- | 113 | 1.09 | 5.50 | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 14* | -- | 936 | 0.82 | 3.49 | 2.14 | ||
gpt-oss-20b (low) | 128k | 开放 | 14* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 14* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 14* | -- | 95 | 0.94 | 27.35 | 21.13 | ||
gpt-oss-20b (low) | 128k | 开放 | 14* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 14* | -- | 98 | 17.20 | 42.68 | 20.39 | ||
gpt-oss-20b (low) | 131k | 开放 | 14* | -- | 134 | 1.16 | 19.78 | 14.90 | ||
gpt-oss-20b (low) Vertex | 131k | 开放 | 14* | -- | 96 | 15.70 | 41.68 | 20.78 | ||
Qwen3 Next 80B A3B | 262k | 开放 | 14* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | 开放 | 14* | -- | 107 | 0.62 | 5.31 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 14* | -- | 188 | 2.16 | 4.82 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 14* | -- | 185 | 0.67 | 3.36 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 14* | -- | 130 | 1.42 | 5.28 | -- | ||
Qwen3 Next 80B A3B | 131k | 开放 | 14* | -- | 192 | 1.56 | 4.17 | -- | ||
Qwen3 Next 80B A3B | 131k | 开放 | 14* | -- | 194 | 2.13 | 4.70 | -- | ||
Gemma 4 12B (Non-reasoning) | 262k | 开放 | 13* | -- | 114 | 2.23 | 6.62 | -- | ||
Nova Premier | 1M | 专有 | 13* | -- | 33 | 2.87 | 18.22 | -- | ||
Llama Nemotron Super 49B v1.5 | 131k | 开放 | 12* | -- | 89 | 9.11 | 37.12 | 22.40 | ||
Celeris-1 | 131k | 专有 | 12 | $0.26 | 1,597 | 0.55 | 0.86 | -- | ||
Mistral Small 4 | 262k | 开放 | 12* | -- | 168 | 0.87 | 3.84 | -- | ||
Gemma 4 E4B | 262k | 开放 | 12* | -- | 46 | 0.79 | 54.93 | 43.31 | ||
Sarvam 105B (high) | 128k | 开放 | 12* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite | 1M | 专有 | 12* | -- | 184 | 1.07 | 3.79 | -- | ||
Magistral Small 1.2 | 128k | 开放 | 11 | $0.30 | 75 | 1.57 | 34.87 | 26.63 | ||
Ministral 3 14B | 262k | 开放 | 11 | $0.16 | 99 | 0.93 | 5.98 | -- | ||
Ministral 3 14B | 256k | 开放 | 11 | $0.16 | 235 | 0.96 | 3.08 | -- | ||
LFM2.5-2.6B | 32.8k | 开放 | 11 | $0.00 | -- | -- | -- | -- | ||
Nova 2.0 Omni | 1M | 专有 | 10* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 328k | 开放 | 10 | $0.01 | 60 | 0.50 | 8.78 | -- | ||
Llama 4 Scout | 128k | 开放 | 10 | $0.01 | 133 | 0.82 | 4.59 | -- | ||
Llama 4 Scout Vertex | 1.31M | 开放 | 10 | $0.01 | 153 | 0.68 | 3.95 | -- | ||
Llama 4 Scout | 131k | 开放 | 10 | $0.02 | -- | -- | -- | -- | ||
Llama 4 Scout | 128k | 开放 | 10 | $0.01 | 180 | 0.80 | 3.58 | -- | ||
Llama 4 Scout | 131k | 开放 | 10 | $0.01 | 57 | 0.82 | 9.62 | -- | ||
Llama 4 Scout | 131k | 开放 | 10 | $0.01 | 447 | 0.68 | 1.80 | -- | ||
Hermes 4 70B (FP8) | 128k | 开放 | 10* | -- | 85 | 1.45 | 30.73 | 23.42 | ||
Qwen3 Omni 30B A3B | 65.5k | 开放 | 10* | -- | 101 | 1.90 | 26.65 | 19.80 | ||
Llama 3.3 70B | 131k | 开放 | 9* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B Vertex | 128k | 开放 | 9* | -- | 147 | 0.64 | 4.04 | -- | ||
Llama 3.3 70B | 131k | 开放 | 9* | -- | 325 | 0.91 | 2.44 | -- | ||
Llama 3.3 70B | 131k | 开放 | 9* | -- | 38 | 1.72 | 14.74 | -- | ||
Llama 3.3 70B (FP8) | 131k | 开放 | 9* | -- | 80 | 2.46 | 8.73 | -- | ||
Llama 3.3 70B | 128k | 开放 | 9* | -- | 295 | 1.74 | 3.43 | -- | ||
Llama 3.3 70B Base | 128k | 开放 | 9* | -- | 7 | 6.26 | 73.92 | -- | ||
Llama 3.3 70B | 128k | 开放 | 9* | -- | 79 | 0.90 | 7.24 | -- | ||
Llama 3.3 70B Turbo | 131k | 开放 | 9* | -- | 61 | 1.48 | 9.67 | -- | ||
Llama 3.3 70B | 128k | 开放 | 9* | -- | 130 | 2.10 | 5.95 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | 开放 | 9* | -- | 15 | 2.18 | 35.69 | -- | ||
Llama 3.3 70B | 24k | 开放 | 9* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B | 128k | 开放 | 9* | -- | 154 | 1.13 | 4.39 | -- | ||
Llama 3.3 70B | 100k | 开放 | 9* | -- | 84 | 1.28 | 7.21 | -- | ||
Ministral 3 8B | 256k | 开放 | 9 | $0.18 | 252 | 1.01 | 2.99 | -- | ||
Ministral 3 8B | 262k | 开放 | 9 | $0.18 | 126 | 0.76 | 4.74 | -- | ||
Llama Nemotron Ultra Base | 131k | 开放 | 9* | -- | 53 | 2.39 | 49.95 | 38.05 | ||
ERNIE 4.5 300B A47B | 131k | 开放 | 9* | -- | -- | -- | -- | -- | ||
Hermes 4 405B (FP8) | 128k | 开放 | 9* | -- | 38 | 2.52 | 68.10 | 52.46 | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | 开放 | 9* | -- | 135 | 5.69 | 24.26 | 14.86 | ||
Gemma 4 E4B | 262k | 开放 | 9* | -- | 47 | 0.76 | 11.43 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | 开放 | 9* | -- | 218 | 3.29 | 14.78 | 9.19 | ||
Hermes 4 405B (FP8) | 128k | 开放 | 9* | -- | 36 | 2.37 | 16.10 | -- | ||
Llama Nemotron Super 49B v1.5 | 131k | 开放 | 9* | -- | 81 | 10.07 | 16.25 | -- | ||
LFM2.5-8B-A1B | 32.8k | 开放 | 8* | -- | 340 | 1.51 | 8.86 | 5.88 | ||
Ring-flash-2.0 | 131k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Olmo 3.1 32B Think | 65.5k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Command A | 288k | 开放 | 7* | -- | 75 | 1.57 | 8.26 | -- | ||
Command A | 256k | 开放 | 7* | -- | 43 | 3.02 | 14.55 | -- | ||
Llama 3.1 Nemotron 70B | 131k | 开放 | 7* | -- | 102 | 6.55 | 11.48 | -- | ||
Nemotron 3 Nano (FP4) | 262k | 开放 | 7* | -- | 261 | 0.99 | 2.90 | -- | ||
Nemotron 3 Nano | 262k | 开放 | 7* | -- | 226 | 0.60 | 2.81 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | 开放 | 7* | -- | 230 | 2.56 | 4.73 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | 开放 | 7* | -- | 165 | 1.11 | 4.13 | -- | ||
Ministral 3 3B | 256k | 开放 | 7 | $0.13 | 377 | 0.95 | 2.27 | -- | ||
Ministral 3 3B | 131k | 开放 | 7 | $0.13 | 204 | 0.60 | 3.05 | -- | ||
Hermes 4 70B (FP8) | 128k | 开放 | 7* | -- | 84 | 1.37 | 7.33 | -- | ||
Granite 4.1 8B | 131k | 开放 | 6* | -- | 124 | 0.76 | 4.78 | -- | ||
Sarvam 30B (high) | 64k | 开放 | 6* | -- | -- | -- | -- | -- | ||
Phi-4 Mini | 128k | 开放 | 6* | -- | 44 | 0.83 | 12.26 | -- | ||
Granite 4.0 H Small | 128k | 开放 | 5* | -- | 21 | 24.33 | 48.09 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | 开放 | 5* | -- | 95 | 1.94 | 7.22 | -- | ||
Phi-4 | 16.4k | 开放 | 5* | -- | 42 | 2.45 | 14.38 | -- | ||
Phi-4 | 16.4k | 开放 | 5* | -- | 74 | 0.87 | 7.63 | -- | ||
Nova Micro | 130k | 专有 | 4* | -- | 301 | 0.86 | 2.52 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL | 128k | 开放 | 4* | -- | 181 | 1.15 | 3.92 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | 开放 | 4* | -- | 138 | 7.15 | 10.78 | -- | ||
Phi-4 Multimodal | 128k | 开放 | 4* | -- | 18 | 0.82 | 29.20 | -- | ||
Reka Flash 3 | 54k | 开放 | 4* | -- | -- | -- | -- | -- | ||
Llama 3.2 11B (Vision) | 131k | 开放 | 3* | -- | 65 | 0.98 | 8.73 | -- | ||
Olmo 3 7B | 65.5k | 开放 | 2* | -- | -- | -- | -- | -- | ||
Apertus 70B Instruct | 64k | 开放 | 2* | -- | -- | -- | -- | -- | ||
LFM2.5-VL-1.6B | 32.8k | 开放 | 1* | -- | 383 | 1.30 | 2.60 | -- | ||
Tiny Aya Global | 8.19k | 开放 | 1* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | 开放 | 1* | -- | -- | -- | -- | -- | ||
Claude Sonnet 5 (low) | 1M | 专有 | -- | -- | 65 | 2.00 | 9.70 | -- | ||
Claude Sonnet 5 (xhigh) | 1M | 专有 | -- | -- | 70 | 26.25 | 33.40 | -- | ||
Claude Sonnet 5 (high) | 1M | 专有 | -- | -- | 66 | 14.70 | 22.29 | -- | ||
Cogito v2.1 | 164k | 开放 | -- | -- | -- | -- | -- | -- | ||
Claude Sonnet 5 (medium) | 1M | 专有 | -- | -- | 69 | 2.71 | 9.96 | -- | ||