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 5.5 (max with fallback) | 1M | 专有 | 58 | $5.98 | 92 | 704.69 | 710.10 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | 专有 | 56 | $7.67 | 132 | 428.36 | 432.14 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | 专有 | 56 | -- | 130 | 341.05 | 344.91 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | 专有 | 56 | -- | 134 | 435.41 | 439.15 | -- | ||
Claude Opus 5.5 (xhigh with fallback) | 1M | 专有 | 56 | $3.46 | 80 | 141.03 | 147.31 | -- | ||
Claude Opus 5.5 (high with fallback) | 1M | 专有 | 54 | $1.82 | 73 | 38.91 | 45.72 | -- | ||
Claude Fable 5.1 (max with fallback) | 1M | 专有 | 53 | $7.63 | 68 | 238.66 | 246.00 | -- | ||
Claude Fable 5.1 (xhigh with fallback) | 1M | 专有 | 53 | $5.98 | 59 | 106.70 | 115.14 | -- | ||
GPT-6 Astra (max) | 524k | 专有 | 53 | $3.19 | 69 | 343.27 | 350.48 | -- | ||
GPT-6 Astra (max) | 1M | 专有 | 53 | $3.26 | 52 | 320.14 | 329.84 | -- | ||
GPT-6 Astra (max) | 524k | 专有 | 53 | $3.26 | 79 | 346.83 | 353.12 | -- | ||
Gemini 4 Argon (high) AI Studio (1M output) | 1M | 专有 | 53 | $1.99 | -- | -- | -- | -- | ||
GPT-6 Astra (xhigh) | 1M | 专有 | 52 | $2.31 | 49 | 181.00 | 191.14 | -- | ||
Claude Sonnet 5.5 (xhigh with fallback) | 1M | 专有 | 52 | $2.75 | 101 | 34.69 | 39.63 | -- | ||
GPT-6.1 Sol (max) | 1M | 专有 | 52 | $0.72 | 52 | 269.34 | 278.94 | -- | ||
Claude Opus 5.5 (medium with fallback) | 1M | 专有 | 51 | $1.34 | 73 | 25.75 | 32.62 | -- | ||
Claude Fable 5.1 (high with fallback) | 1M | 专有 | 51 | $3.91 | 53 | 25.00 | 34.41 | -- | ||
GPT-6.1 Sol (xhigh) | 1M | 专有 | 51 | $0.39 | 53 | 110.28 | 119.63 | -- | ||
GPT-6 Astra (high) | 1M | 专有 | 51 | $1.73 | 45 | 65.56 | 76.57 | -- | ||
GPT-6.1 Sol (high) | 1M | 专有 | 50 | $0.32 | 58 | 57.61 | 66.20 | -- | ||
GPT-6 Astra (medium) | 1M | 专有 | 50 | $1.54 | 45 | 6.21 | 17.34 | -- | ||
Claude Fable 5.1 (medium with fallback) | 1M | 专有 | 49 | $2.98 | 51 | 8.79 | 18.51 | -- | ||
Muse Spark 1.3 (max) | 1.05M | 专有 | 48 | $1.60 | 129 | 53.10 | 72.48 | 15.50 | ||
GPT-6.1 Sol (medium) | 1M | 专有 | 48 | $0.21 | 45 | 5.59 | 16.59 | -- | ||
Claude Fable 5.1 (low with fallback) | 1M | 专有 | 47 | $2.37 | 49 | 4.49 | 14.78 | -- | ||
Claude Sonnet 5.5 (high with fallback) | 1M | 专有 | 47 | $1.08 | 101 | 12.20 | 17.15 | -- | ||
Grok 4.7 (xhigh) | 500k | 专有 | 46 | $3.74 | 79 | 49.32 | 55.65 | -- | ||
Grok 4.7 (high) | 500k | 专有 | 46 | $2.73 | 78 | 30.21 | 36.64 | -- | ||
MiMo-V2.6-Pro | 1M | 开放 | 46 | $0.13 | 44 | 4.20 | 61.39 | 45.75 | ||
MiMo-V2.6-Pro | 1M | 开放 | 46 | $0.12 | 23 | 2.24 | 108.63 | 85.11 | ||
MiMo-V2.6-Pro | 1.05M | 开放 | 46 | $0.14 | 310 | 0.67 | 8.73 | 6.44 | ||
MiMo-V2.6-Pro | 1M | 开放 | 46 | $0.13 | 44 | 3.51 | 60.51 | 45.60 | ||
GPT-6 Astra (low) | 524k | 专有 | 46 | $0.79 | 55 | 3.16 | 12.27 | -- | ||
GPT-6 Astra (low) | 1M | 专有 | 46 | $0.82 | 51 | 2.65 | 12.52 | -- | ||
Qwen3.8 Max (0902) | 984k | 专有 | 45 | $5.41 | 37 | 2.64 | 69.35 | 53.37 | ||
Muse Spark 1.3 (xhigh) | 1.05M | 专有 | 45 | $1.37 | 142 | 39.81 | 57.36 | 14.04 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.44 | 259 | 0.86 | 10.49 | 7.71 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.01 | 72 | 3.14 | 37.93 | 27.83 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $2.15 | 319 | 1.67 | 9.52 | 6.28 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $1.39 | 76 | 1.13 | 33.91 | 26.22 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $2.96 | 185 | 0.67 | 14.17 | 10.80 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $1.97 | 137 | 1.01 | 19.30 | 14.63 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $1.97 | 228 | 0.55 | 11.50 | 8.76 | ||
GLM-5.3 (max) (FAST) | 1M | 开放 | 45 | $4.08 | 429 | 0.78 | 6.61 | 4.66 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.00 | 83 | 1.95 | 31.94 | 23.99 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $1.43 | 129 | 1.91 | 21.25 | 15.47 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $1.97 | 59 | 0.79 | 43.23 | 33.95 | ||
GLM-5.3 (max) | 1.05M | 开放 | 45 | $1.90 | 230 | 0.83 | 11.72 | 8.71 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.73 | 202 | 0.94 | 13.31 | 9.89 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $6.82 | 151 | 1.43 | 17.98 | 13.24 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.01 | 161 | 0.80 | 16.35 | 12.44 | ||
GLM-5.3 (max) (FAST) | 1M | 开放 | 45 | $2.15 | 273 | 0.50 | 9.67 | 7.33 | ||
GLM-5.3 (max) (FP4) | 1.05M | 开放 | 45 | $2.35 | 461 | 0.78 | 6.19 | 4.33 | ||
GLM-5.3 (max) (FP4 ULTRA CHAT) | 1.05M | 开放 | 45 | $5.14 | 463 | 0.81 | 6.21 | 4.32 | ||
GLM-5.3 (max) | 164k | 开放 | 45 | $2.04 | 142 | 1.71 | 19.37 | 14.13 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $4.99 | 139 | 1.74 | 19.76 | 14.42 | ||
GLM-5.3 (max) (FP4) | 786k | 开放 | 45 | $3.36 | 214 | 0.86 | 12.52 | 9.33 | ||
GLM-5.3 (max) (FP4) | 1M | 开放 | 45 | $1.19 | 228 | 1.78 | 12.74 | 8.77 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $1.81 | 208 | 1.00 | 13.04 | 9.63 | ||
GLM-5.3 (max) (FP4, FAST) | 1M | 开放 | 45 | $5.29 | 559 | 157.91 | 162.39 | 3.58 | ||
GLM-5.3 (max) | 1M | 开放 | 45 | $2.02 | 94 | 1.91 | 28.59 | 21.34 | ||
Step 5 Preview | 1M | 专有 | 44 | $0.72 | 85 | 3.12 | 32.49 | 23.50 | ||
Kimi K3 (max) | 205k | 开放 | 44 | $1.85 | 120 | 0.91 | 21.73 | 16.65 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $1.91 | 110 | 1.38 | 24.12 | 18.19 | ||
Kimi K3 (max) (FAST) | 1.05M | 开放 | 44 | $2.72 | 111 | 1.05 | 23.55 | 18.00 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $3.48 | 84 | 1.43 | 31.09 | 23.73 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $2.40 | 86 | 1.00 | 30.14 | 23.31 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $1.90 | 33 | 1.20 | 76.69 | 60.39 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $2.42 | 163 | 0.75 | 16.05 | 12.23 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $4.14 | 92 | 1.48 | 28.73 | 21.80 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $1.21 | 46 | 1.19 | 55.47 | 43.43 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $9.22 | 233 | 1.08 | 11.80 | 8.58 | ||
Kimi K3 (max) | 262k | 开放 | 44 | $1.77 | 89 | 2.14 | 30.27 | 22.50 | ||
Kimi K3 (max) (ULTRA CHAT) | 1.05M | 开放 | 44 | $3.93 | 300 | 0.74 | 9.07 | 6.67 | ||
Kimi K3 (max) (FAST) | 1.05M | 开放 | 44 | $3.77 | 253 | 2.17 | 12.06 | 7.91 | ||
Kimi K3 (max) | 1M | 开放 | 44 | $3.58 | 172 | 1.33 | 15.89 | 11.65 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $2.00 | 34 | 4.50 | 78.36 | 59.08 | ||
Kimi K3 (max) | 1.05M | 开放 | 44 | $1.69 | 225 | 0.73 | 11.86 | 8.91 | ||
Kimi K3 (max) (FAST) | 1.05M | 开放 | 44 | $2.81 | 227 | 0.72 | 11.76 | 8.83 | ||
Kimi K3 (max) (ULTRA) | 1.05M | 开放 | 44 | $3.93 | 232 | 0.72 | 11.51 | 8.63 | ||
Claude Opus 5.5 (low with fallback) | 1M | 专有 | 42 | $0.55 | 72 | 12.39 | 19.32 | -- | ||
Claude Opus 5.5 (low with fallback) | 1M | 专有 | 42 | $0.55 | 58 | 13.48 | 22.16 | -- | ||
Claude Opus 5.5 (low with fallback) | 1M | 专有 | 42 | $1.08 | 72 | 14.38 | 21.35 | -- | ||
Grok 4.7 (low) | 500k | 专有 | 42 | $1.25 | 76 | 8.92 | 15.47 | -- | ||
GPT-6.1 Sol (low) | 1M | 专有 | 42 | $0.13 | 55 | 3.25 | 12.40 | -- | ||
GPT-5.6 Terra (max) | 1M | 专有 | 42 | $1.40 | 103 | 156.49 | 161.36 | -- | ||
GPT-5.6 Terra (max) | 1M | 专有 | 42 | $1.95 | 134 | 150.22 | 153.96 | -- | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $1.03 | 101 | 0.94 | 25.75 | 19.84 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.25 | 49 | 3.25 | 54.34 | 40.88 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.60 | 225 | 0.55 | 11.68 | 8.90 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.29 | 57 | 2.63 | 46.38 | 35.00 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.34 | 28 | 1.58 | 91.34 | 71.81 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.50 | 56 | 2.44 | 47.48 | 36.03 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.45 | 69 | 1.13 | 37.53 | 29.12 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.47 | 110 | 0.74 | 23.37 | 18.11 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.37 | 181 | 1.34 | 15.14 | 11.04 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.28 | 168 | 0.75 | 15.61 | 11.88 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.52 | 57 | 3.20 | 46.81 | 34.89 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.67 | 203 | 0.92 | 13.25 | 9.87 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.14 | 204 | 2.33 | 14.58 | 9.79 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.51 | 151 | 0.97 | 17.56 | 13.27 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $1.19 | 132 | 17.17 | 36.05 | 15.11 | ||
GLM-5.3-Flash | 1.05M | 开放 | 42 | $0.42 | 47 | 1.21 | 54.38 | 42.54 | ||
GLM-5.3-Flash | 1M | 开放 | 42 | $0.76 | 136 | 1.66 | 20.07 | 14.73 | ||
GLM-5.3-Flash (FP4) | 1.05M | 开放 | 42 | $0.81 | 134 | 0.95 | 19.56 | 14.89 | ||
GLM-5.3-Flash (FAST) | 1M | 开放 | 42 | $0.46 | 468 | 8.08 | 13.42 | 4.27 | ||
GLM-5.3-Flash (FP4) | 1.05M | 开放 | 42 | $0.44 | 522 | 1.18 | 5.97 | 3.83 | ||
GLM-5.3-Flash (FP4, ULTRA CHAT) | 1.05M | 开放 | 42 | $0.87 | 738 | 0.43 | 3.82 | 2.71 | ||
Ling 3.1 Flash | 1M | 开放 | 41 | $0.99 | 211 | 1.73 | 13.56 | 9.46 | ||
Gemini 3.8 Flash (high) AI Studio | 1M | 专有 | 41 | $1.24 | 237 | 14.73 | 16.84 | -- | ||
Claude Sonnet 5.5 (medium with fallback) | 1M | 专有 | 41 | $0.59 | 92 | 1.34 | 6.78 | -- | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 40 | $1.87 | 85 | 1.03 | 30.44 | 23.53 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 40 | $2.09 | 185 | 0.87 | 14.42 | 10.83 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 40 | $2.89 | 93 | 1.51 | 28.36 | 21.49 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 40 | $1.81 | 134 | 0.75 | 19.38 | 14.90 | ||
Qwen3.8 2.4T A95B | 262k | 开放 | 40 | $2.16 | 38 | 2.76 | 68.80 | 52.83 | ||
Qwen3.8 2.4T A95B | 1M | 开放 | 40 | $1.96 | 178 | 0.79 | 14.84 | 11.24 | ||
Qwen3.8-Flash-Next | 1M | 开放 | 40 | $0.37 | 55 | 2.50 | 47.66 | 36.12 | ||
Gemini 3.8 Flash (medium) AI Studio | 1M | 专有 | 40 | $0.93 | -- | -- | -- | -- | ||
DeepSeek V4.1 Flash (max) | 1.05M | 开放 | 39 | $3.13 | 156 | 1.48 | 17.49 | 12.81 | ||
DeepSeek V4.1 Flash (max) (FAST) | 1.05M | 开放 | 39 | $0.27 | 521 | 1.13 | 5.92 | 3.84 | ||
DeepSeek V4.1 Flash (max) (ULTRA) | 1.05M | 开放 | 39 | $0.38 | 549 | 0.98 | 5.53 | 3.64 | ||
DeepSeek V4.1 Flash (max) (ULTRA CHAT) | 1.05M | 开放 | 39 | $0.38 | 717 | 0.46 | 3.95 | 2.79 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $0.62 | 217 | 1.04 | 12.56 | 9.22 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $1.20 | 162 | 0.71 | 16.18 | 12.38 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $0.27 | 209 | 0.99 | 12.96 | 9.57 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $0.86 | 146 | 2.47 | 19.57 | 13.68 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $0.44 | 134 | 2.89 | 21.61 | 14.98 | ||
DeepSeek V4.1 Flash (max) | 524k | 开放 | 39 | $0.24 | 150 | 2.19 | 18.83 | 13.32 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $0.19 | 347 | 1.86 | 9.06 | 5.76 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $0.44 | 81 | 0.80 | 31.84 | 24.83 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $0.64 | 154 | 2.54 | 18.73 | 12.95 | ||
DeepSeek V4.1 Flash (max) | 1.05M | 开放 | 39 | $0.90 | 188 | 0.91 | 14.23 | 10.65 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $1.21 | 218 | 0.81 | 12.26 | 9.16 | ||
DeepSeek V4.1 Flash (max) | 1.05M | 开放 | 39 | $0.57 | 94 | 0.73 | 27.46 | 21.38 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $0.34 | 126 | 1.22 | 20.98 | 15.81 | ||
DeepSeek V4.1 Flash (max) | 1M | 开放 | 39 | $1.75 | 74 | 0.72 | 34.70 | 27.19 | ||
DeepSeek V4.1 Flash (max) | 1.05M | 开放 | 39 | $0.32 | 316 | 0.30 | 8.21 | 6.32 | ||
DeepSeek V4.1 Flash (max) (FAST) | 1.05M | 开放 | 39 | $0.49 | 596 | 1.47 | 5.67 | 3.36 | ||
DeepSeek V4.1 Flash (max) | 1.05M | 开放 | 39 | $0.16 | 547 | 0.93 | 5.51 | 3.66 | ||
DeepSeek V4.1 Flash (max) | 1.05M | 开放 | 39 | $1.11 | 315 | 0.67 | 8.62 | 6.36 | ||
GPT-6 Luna (max) | 1M | 专有 | 38 | $0.07 | 132 | 125.75 | 129.53 | -- | ||
GPT-6 Luna (max) | 524k | 专有 | 38 | -- | 212 | 59.57 | 61.93 | -- | ||
GPT-5.6 Terra (xhigh) | 1M | 专有 | 38 | $0.63 | 92 | 24.24 | 29.70 | -- | ||
GPT-5.6 Terra (xhigh) | 524k | 专有 | 38 | $0.67 | 125 | 21.86 | 25.87 | -- | ||
MiMo-V2.6-Flash | 1M | 开放 | 38 | $0.06 | 51 | 3.60 | 52.40 | 39.04 | ||
MiMo-V2.6-Flash | 1M | 开放 | 38 | $0.42 | 32 | 1.46 | 78.53 | 61.66 | ||
MiMo-V2.6-Flash | 1M | 开放 | 38 | $0.06 | 57 | 3.49 | 47.28 | 35.03 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $0.67 | 116 | 1.75 | 23.34 | 17.27 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $2.19 | 65 | 3.54 | 42.12 | 30.86 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $1.45 | 85 | 1.68 | 30.95 | 23.41 | ||
DeepSeek V4 Pro 0813 (max) | 1M | 开放 | 36 | $0.60 | -- | -- | -- | -- | ||
DeepSeek V4 Pro 0813 (max) | 1M | 开放 | 36 | $5.51 | 100 | 0.71 | 25.83 | 20.10 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $1.65 | 115 | 1.74 | 23.44 | 17.37 | ||
DeepSeek V4 Pro 0813 (max) | 1M | 开放 | 36 | $1.00 | 52 | 1.40 | 49.77 | 38.69 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $0.70 | 84 | 2.27 | 32.01 | 23.80 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $0.83 | 57 | 0.86 | 44.86 | 35.21 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | 开放 | 36 | $0.51 | 270 | 1.50 | 10.77 | 7.41 | ||
Claude Sonnet 5.5 (low with fallback) | 1M | 专有 | 36 | $0.42 | 93 | 1.19 | 6.59 | -- | ||
Claude Sonnet 5.5 (low with fallback) | 1M | 专有 | 36 | -- | 95 | 1.25 | 6.54 | -- | ||
Claude Sonnet 5.5 (low with fallback) | 1M | 专有 | 36 | -- | 96 | 1.36 | 6.57 | -- | ||
DeepSeek V4 Flash Vision (max) | 1M | 专有 | 35 | $0.51 | 126 | 0.95 | 20.84 | 15.91 | ||
DeepSeek V4 Flash Vision (max) | 1M | 专有 | 35 | $0.31 | 206 | 0.95 | 13.10 | 9.72 | ||
DeepSeek V4 Flash Vision (max) | 1M | 专有 | 35 | $0.12 | -- | -- | -- | -- | ||
DeepSeek V4 Flash Vision (max) | 1M | 专有 | 35 | $0.28 | 210 | 2.32 | 14.22 | 9.52 | ||
DeepSeek V4 Flash Vision (max) | 1M | 专有 | 35 | $2.51 | 214 | 1.27 | 12.96 | 9.36 | ||
GPT-6 Luna (xhigh) | 1M | 专有 | 35 | $0.04 | 136 | 22.85 | 26.52 | -- | ||
GLM-5.3 (low) | 1M | 开放 | 34 | $0.85 | 73 | 3.10 | 37.22 | 27.30 | ||
GLM-5.3 (low) (FP4) | 1M | 开放 | 34 | $0.50 | 209 | 1.76 | 13.71 | 9.56 | ||
GLM-5.3 (low) (FP4, FAST) | 1M | 开放 | 34 | $2.24 | 609 | 186.97 | 191.07 | 3.29 | ||
GLM-5.3 (low) | 1M | 开放 | 34 | $2.11 | 139 | 1.46 | 19.47 | 14.41 | ||
GPT-5.6 Terra (high) | 1M | 专有 | 34 | $0.34 | 85 | 3.08 | 8.96 | -- | ||
GPT-5.6 Terra (high) | 524k | 专有 | 34 | $0.35 | 117 | 2.86 | 7.11 | -- | ||
Qwen3.8 27B (xhigh) | 262k | 开放 | 34 | $0.52 | 38 | 1.01 | 67.26 | 53.00 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | 开放 | 34 | $0.92 | 63 | 1.63 | 41.62 | 31.99 | ||
Qwen3.8 27B (xhigh) | 1M | 开放 | 34 | $1.01 | 46 | 3.73 | 58.35 | 43.69 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | 开放 | 34 | $0.60 | 78 | 1.31 | 33.55 | 25.79 | ||
Qwen3.8 27B (xhigh) | 262k | 开放 | 34 | $1.98 | 194 | 0.80 | 13.70 | 10.32 | ||
Qwen3.8 27B (xhigh) | 262k | 开放 | 34 | $0.45 | 74 | 1.22 | 34.95 | 26.98 | ||
Qwen3.8 27B (xhigh) | 262k | 开放 | 34 | $0.91 | 189 | 0.86 | 14.06 | 10.55 | ||
Qwen3.8 27B (xhigh) (NVFP4) | 262k | 开放 | 34 | -- | 54 | 0.61 | 46.69 | 36.87 | ||
Gemini 3.8 Flash (low) AI Studio | 1M | 专有 | 33 | -- | -- | -- | -- | -- | ||
GPT-6 Luna (high) | 1M | 专有 | 33 | $0.03 | 133 | 13.92 | 17.67 | -- | ||
GPT-5.3 Codex (xhigh) | 400k | 专有 | 33* | -- | 95 | 71.47 | 76.75 | -- | ||
K2 Horizon 375B A23B | 524k | 开放 | 31 | $0.00 | 120 | 12.59 | 33.47 | 16.71 | ||
GPT-5.6 Terra (medium) | 1M | 专有 | 30 | $0.18 | 76 | 2.39 | 8.95 | -- | ||
Kimi K3 (low) | 1.05M | 开放 | 30 | $1.15 | 35 | 5.41 | 76.29 | 56.71 | ||
Kimi K3 (low) | 1M | 开放 | 30 | $1.41 | 162 | 0.99 | 16.44 | 12.36 | ||
Kimi K3 (low) | 1M | 开放 | 30 | $0.88 | 126 | 1.15 | 21.06 | 15.93 | ||
Kimi K3 (low) | 1M | 开放 | 30 | $5.77 | 202 | 1.10 | 13.46 | 9.89 | ||
Kimi K3 (low) | 262k | 开放 | 30 | $0.87 | 70 | 1.63 | 37.33 | 28.56 | ||
GPT-6 Luna (medium) | 1M | 专有 | 30 | $0.02 | -- | -- | -- | -- | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | 专有 | 30 | $0.67 | 117 | 24.14 | 28.43 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | 专有 | 30 | $0.98 | 100 | 26.44 | 31.44 | -- | ||
MiniMax-M3 (MXFP8) | 1M | 开放 | 29 | $0.46 | 129 | 1.14 | 20.45 | 15.45 | ||
MiniMax-M3 (NVFP4) | 262k | 开放 | 29 | -- | 33 | 1.73 | 77.43 | 60.56 | ||
MiniMax-M3 | 1M | 开放 | 29 | $0.58 | 62 | 0.78 | 41.01 | 32.18 | ||
MiniMax-M3 | 1M | 开放 | 29 | $0.46 | 94 | 1.45 | 28.09 | 21.31 | ||
MiniMax-M3 (FAST) | 1.05M | 开放 | 29 | $1.09 | 441 | 1.59 | 7.25 | 4.53 | ||
MiniMax-M3 | 1M | 开放 | 29 | $0.46 | 166 | 1.94 | 17.00 | 12.05 | ||
MiniMax-M3 (FP8) | 1.05M | 开放 | 29 | $1.91 | 317 | 1.47 | 9.36 | 6.31 | ||
MiniMax-M3 (FP8) | 1M | 开放 | 29 | $0.45 | 82 | 2.17 | 32.50 | 24.26 | ||
MiniMax-M3 | 512k | 开放 | 29 | $0.51 | 84 | 1.73 | 31.58 | 23.88 | ||
MiniMax-M3 | 524k | 开放 | 29 | $0.44 | 25 | 0.93 | 102.62 | 81.35 | ||
MiniMax-M3 | 1.05M | 开放 | 29 | -- | -- | -- | -- | -- | ||
MiniMax-M3 | 1.05M | 开放 | 29 | $3.83 | -- | -- | -- | -- | ||
MiniMax-M3 | 524k | 开放 | 29 | $0.50 | 165 | 0.96 | 16.10 | 12.12 | ||
MiniMax-M3 | 1.05M | 开放 | 29 | $0.54 | 94 | 1.71 | 28.31 | 21.28 | ||
Solar Pro 4 | 512k | 专有 | 28* | -- | 95 | 2.13 | 28.52 | 21.11 | ||
Qwen3.8 27B (medium) | 1M | 开放 | 28 | $1.13 | 50 | 3.90 | 53.42 | 39.62 | ||
Qwen3.8 27B (medium) | 262k | 开放 | 28 | $2.36 | 187 | 0.77 | 14.14 | 10.70 | ||
GPT-5.6 Terra (low) | 1M | 专有 | 27 | $0.14 | 85 | 1.66 | 7.56 | -- | ||
Quasar 438B (max) | 1M | 专有 | 27 | $2.02 | 139 | 1.15 | 19.18 | 14.42 | ||
Apodex 1.1 | 256k | 专有 | 26 | $0.46 | -- | -- | -- | -- | ||
Qwen3.8 27B (low) | 262k | 开放 | 26 | $2.19 | 187 | 0.85 | 14.22 | 10.70 | ||
Qwen3.8 27B (low) | 1M | 开放 | 26 | $1.05 | 51 | 3.70 | 52.76 | 39.25 | ||
GPT-5.5 Instant (June 2026) | 400k | 专有 | 26 | $0.69 | 118 | 0.92 | 22.17 | 17.01 | ||
Kimi K2.7 Code (FP4) | 256k | 开放 | 26 | $1.89 | 233 | 1.32 | 13.03 | 9.56 | ||
Kimi K2.7 Code (FP8) | 65.5k | 开放 | 26 | $1.37 | 97 | 5.02 | 33.29 | 23.09 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.83 | 249 | 1.14 | 12.08 | 8.94 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.65 | -- | -- | -- | -- | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.55 | 95 | 3.68 | 32.38 | 23.44 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.39 | 15 | 2.14 | 183.66 | 148.26 | ||
Kimi K2.7 Code | 262k | 开放 | 26 | $0.52 | -- | -- | -- | -- | ||
Kimi K2.7 Code | 256k | 开放 | 26 | $0.54 | 96 | 3.03 | 31.36 | 23.14 | ||
Inkling Small | 524k | 开放 | 26 | -- | 234 | 0.82 | 11.53 | 8.56 | ||
Inkling Small | 262k | 开放 | 26 | $0.12 | -- | -- | -- | -- | ||
Inkling Small | 256k | 开放 | 26 | $0.09 | 204 | 2.10 | 14.37 | 9.81 | ||
Hy3 (FP8) | 256k | 开放 | 25 | $0.07 | 90 | 3.06 | 30.89 | 22.26 | ||
Hy3 | 262k | 开放 | 25 | $0.07 | 93 | 3.31 | 30.06 | 21.40 | ||
Hy3 (FP8) | 262k | 开放 | 25 | $0.07 | 57 | 1.06 | 44.89 | 35.06 | ||
Hy3 | 262k | 开放 | 25 | $0.07 | 87 | 3.50 | 32.24 | 22.99 | ||
Qwen3.7 Plus | 1M | 专有 | 25 | $0.22 | 56 | 2.24 | 47.00 | 35.80 | ||
Inkling (xhigh) (FP8) | 131k | 开放 | 25 | -- | 114 | 0.73 | 22.57 | 17.47 | ||
Inkling (xhigh) | 262k | 开放 | 25 | $0.72 | -- | -- | -- | -- | ||
Inkling (xhigh) | 524k | 开放 | 25 | $0.91 | 129 | 0.62 | 20.03 | 15.52 | ||
Inkling (xhigh) (NVFP4) | 1.05M | 开放 | 25 | $0.86 | 171 | 0.95 | 15.53 | 11.66 | ||
Inkling (xhigh) | 262k | 开放 | 25 | -- | 173 | 1.84 | 16.28 | 11.56 | ||
Inkling (xhigh) | 1M | 开放 | 25 | $0.61 | 208 | 1.41 | 13.42 | 9.61 | ||
DeepSeek V4.1 Flash (non-reasoning) | 1M | 开放 | 25 | $0.15 | 207 | 0.91 | 3.32 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) | 1M | 开放 | 25 | $0.80 | 196 | 0.82 | 3.37 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) (FAST) | 1.05M | 开放 | 25 | $0.16 | 399 | 1.05 | 2.30 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) (ULTRA) | 1.05M | 开放 | 25 | $0.22 | 523 | 0.97 | 1.92 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) (ULTRA CHAT) | 1.05M | 开放 | 25 | $0.22 | 629 | 0.89 | 1.69 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) | 1M | 开放 | 25 | $0.41 | 212 | 0.88 | 3.25 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) | 1M | 开放 | 25 | $0.27 | 119 | 2.24 | 6.42 | -- | ||
Ling-3.0-flash-VL | 262k | 开放 | 25 | -- | 136 | 1.93 | 20.26 | 14.67 | ||
Solar Mini 4 | 1.05M | 专有 | 24 | $0.36 | 204 | 1.48 | 13.73 | 9.80 | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | $0.51 | 299 | 0.91 | 10.20 | 7.62 | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | -- | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | $0.47 | 39 | 1.46 | 72.71 | 58.41 | ||
Nemotron 3 Ultra BF16 | 262k | 开放 | 23 | $0.99 | 38 | 1.64 | 74.14 | 59.44 | ||
Nemotron 3 Ultra | 256k | 开放 | 23 | $1.16 | 314 | 2.01 | 10.85 | 7.25 | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | $0.37 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | 开放 | 23 | $0.32 | 153 | 0.69 | 18.82 | 14.86 | ||
Ling-3.0-flash-Fin | 262k | 开放 | 23 | -- | 343 | 1.73 | 9.02 | 5.83 | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | 专有 | 22 | $0.12 | 360 | 8.82 | 10.21 | -- | ||
G9v3-39A5B | 131k | 开放 | 22* | -- | -- | -- | -- | -- | ||
KAT-Coder-Pro V2 | 256k | 专有 | 22* | -- | -- | -- | -- | -- | ||
GPT-6 Luna (low) | 1M | 专有 | 22 | $0.0045 | 121 | 2.06 | 6.21 | -- | ||
Qwen3.5 397B A17B (non-reasoning) (FP8) | 262k | 开放 | 21* | -- | 33 | 1.26 | 16.38 | -- | ||
Qwen3.5 397B A17B (non-reasoning) | 262k | 开放 | 21* | -- | 84 | 2.21 | 8.14 | -- | ||
Qwen3.5 397B A17B (non-reasoning) (Base, FP4) | 262k | 开放 | 21* | -- | 141 | 1.65 | 5.18 | -- | ||
Qwen3.5 397B A17B (non-reasoning) | 131k | 开放 | 21* | -- | 12 | 1.65 | 44.46 | -- | ||
Qwen3.5 397B A17B (non-reasoning) | 262k | 开放 | 21* | -- | 86 | 1.70 | 7.49 | -- | ||
GPT-5.6 Terra (non-reasoning) | 1M | 专有 | 21 | $0.14 | 87 | 0.72 | 6.44 | -- | ||
GPT-5.6 Terra (non-reasoning) | 1M | 专有 | 21 | $0.19 | 108 | 0.72 | 5.34 | -- | ||
Qwen3.5 Omni Plus | 256k | 专有 | 20* | -- | 100 | 2.16 | 7.14 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1.05M | 开放 | 20 | $0.26 | 255 | 1.49 | 3.45 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1M | 开放 | 20 | $0.36 | 108 | 1.59 | 6.21 | -- | ||
o3 | 200k | 专有 | 20* | -- | 97 | 24.29 | 29.42 | -- | ||
o3 | 200k | 专有 | 20* | -- | -- | -- | -- | -- | ||
o3 | 200k | 专有 | 20* | -- | 102 | 7.32 | 12.22 | -- | ||
Qwen3.8 27B (non-reasoning) | 1M | 开放 | 20 | $2.49 | 50 | 3.81 | 13.79 | -- | ||
Qwen3.8 27B (non-reasoning) | 262k | 开放 | 20 | $5.69 | 207 | 0.71 | 3.13 | -- | ||
Qwen3.8 27B (non-reasoning) | 262k | 开放 | 20 | $0.92 | 76 | 1.23 | 7.85 | -- | ||
Qwen3.8 27B (non-reasoning) | 262k | 开放 | 20 | $2.42 | 219 | 0.87 | 3.16 | -- | ||
Qwen3.8 27B (non-reasoning) (NVFP4) | 262k | 开放 | 20 | -- | 40 | 0.68 | 13.13 | -- | ||
Ling 3.0 Flash | 131k | 开放 | 20 | $0.02 | 56 | 0.72 | 45.27 | 35.64 | ||
Ling 3.0 Flash | 262k | 开放 | 20 | -- | 332 | 2.71 | 10.24 | 6.02 | ||
LongCat 2.0 | 1M | 开放 | 19 | $0.06 | -- | -- | -- | -- | ||
LongCat 2.0 (FP8) | 262k | 开放 | 19 | $0.15 | 70 | 2.61 | 38.24 | 28.51 | ||
GPT-6 Luna (non-reasoning) | 1M | 专有 | 18 | $0.01 | 131 | 0.68 | 4.50 | -- | ||
Qwen3.5 397B A17B | 262k | 开放 | 18 | $0.47 | 87 | 2.23 | 44.44 | 36.49 | ||
Qwen3.5 397B A17B | 262k | 开放 | 18 | $0.29 | 50 | 1.31 | 75.63 | 64.24 | ||
Qwen3.5 397B A17B (FP8) | 262k | 开放 | 18 | -- | 34 | 1.26 | 110.86 | 94.74 | ||
Qwen3.5 397B A17B (FP8) | 262k | 开放 | 18 | $0.47 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | 开放 | 18 | $0.47 | 140 | 1.65 | 27.99 | 22.77 | ||
Qwen3.5 397B A17B | 262k | 开放 | 18 | $0.47 | 86 | 1.77 | 44.75 | 37.15 | ||
Qwen3.5 397B A17B | 131k | 开放 | 18 | $0.17 | 14 | 1.42 | 271.64 | 233.57 | ||
Qwen3.6 35B A3B | 229k | 开放 | 18 | $0.48 | 123 | 2.09 | 50.19 | 44.02 | ||
Qwen3.6 35B A3B (FP8) | 262k | 开放 | 18 | $0.32 | 96 | 1.88 | 63.52 | 56.41 | ||
Qwen3.6 35B A3B (FP8) | 262k | 开放 | 18 | $0.14 | 120 | 0.78 | 49.87 | 44.93 | ||
Qwen3.6 35B A3B (FP8) | 262k | 开放 | 18 | $0.31 | 151 | 0.96 | 40.13 | 35.84 | ||
Qwen3.6 35B A3B FP8 | 262k | 开放 | 18 | $0.31 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | 开放 | 18 | $0.12 | 86 | 1.04 | 69.64 | 62.78 | ||
Qwen3.6 35B A3B | 205k | 开放 | 18 | $0.31 | 134 | 1.38 | 45.46 | 40.34 | ||
Qwen3.6 35B A3B | 262k | 开放 | 18 | $0.37 | 130 | 1.21 | 46.61 | 41.56 | ||
Qwen3.5 122B A10B (non-reasoning) (FP4) | 262k | 开放 | 18* | -- | 173 | 0.68 | 3.57 | -- | ||
Qwen3.5 122B A10B (non-reasoning) | 262k | 开放 | 18* | -- | 139 | 2.34 | 5.92 | -- | ||
Muse Glimmer (high) | 131k | 开放 | 17 | $0.08 | 85 | 0.73 | 30.31 | 23.67 | ||
Muse Glimmer (high) | 131k | 开放 | 17 | $0.05 | 126 | 0.93 | 20.77 | 15.87 | ||
Muse Glimmer (high) | 131k | 开放 | 17 | $0.03 | 156 | 1.67 | 17.74 | 12.86 | ||
Muse Glimmer (high) | 131k | 开放 | 17 | $0.06 | -- | -- | -- | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 17 | $0.34 | 132 | 20.67 | 24.46 | -- | ||
Claude 4.5 Haiku Vertex | 200k | 专有 | 17 | $0.24 | 95 | 17.19 | 22.46 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 17 | $0.28 | 97 | 19.33 | 24.47 | -- | ||
Claude 4.5 Haiku | 200k | 专有 | 17 | $0.22 | 98 | 20.16 | 25.26 | -- | ||
Gemma 4 26B A4B | 1M | 开放 | 17* | -- | 245 | 2.64 | 12.83 | 8.16 | ||
Gemma 4 26B A4B | 262k | 开放 | 17* | -- | 31 | 1.60 | 82.56 | 64.77 | ||
Gemma 4 26B A4B AI Studio | 262k | 开放 | 17* | -- | 47 | 0.96 | 54.65 | 42.95 | ||
Gemma 4 26B A4B | 131k | 开放 | 17* | -- | 440 | 1.08 | 6.77 | 4.55 | ||
Gemma 4 26B A4B | 262k | 开放 | 17* | -- | 89 | 0.57 | 28.55 | 22.39 | ||
Gemma 4 26B A4B | 256k | 开放 | 17* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | 开放 | 17* | -- | 31 | 0.87 | 81.12 | 64.20 | ||
Gemma 4 26B A4B | 256k | 开放 | 17* | -- | 60 | 1.57 | 43.10 | 33.22 | ||
Gemma 4 26B A4B (FP8) | 1.05M | 开放 | 17* | -- | -- | -- | -- | -- | ||
Ring-2.6-1T | 262k | 开放 | 17 | $0.29 | 118 | 3.79 | 25.02 | 16.98 | ||
Qwen3.5 122B A10B (FP8) | 262k | 开放 | 16 | $0.21 | 65 | 1.68 | 40.20 | 30.82 | ||
Qwen3.5 122B A10B (FP4) | 262k | 开放 | 16 | $0.24 | 169 | 0.69 | 15.48 | 11.83 | ||
Qwen3.5 122B A10B | 262k | 开放 | 16 | $0.32 | 130 | 2.38 | 21.61 | 15.38 | ||
Qwen3.5 122B A10B (FP8) | 262k | 开放 | 16 | $0.32 | -- | -- | -- | -- | ||
Qwen3.5 122B A10B | 262k | 开放 | 16 | $0.32 | 121 | 1.97 | 22.58 | 16.48 | ||
Claude 4.5 Haiku (non-reasoning) | 200k | 专有 | 15* | -- | 100 | 0.80 | 5.82 | -- | ||
Claude 4.5 Haiku (non-reasoning) | 200k | 专有 | 15* | -- | 91 | 0.99 | 6.50 | -- | ||
Claude 4.5 Haiku (non-reasoning) | 200k | 专有 | 15* | -- | 88 | 0.56 | 6.21 | -- | ||
Claude 4.5 Haiku (non-reasoning) Vertex | 200k | 专有 | 15* | -- | 87 | 0.68 | 6.43 | -- | ||
Qwen3.6 35B A3B (non-reasoning) | 262k | 开放 | 15* | -- | 117 | 1.22 | 5.49 | -- | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | 262k | 开放 | 15* | -- | 165 | 0.98 | 4.01 | -- | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | 262k | 开放 | 15* | -- | 29 | 0.99 | 18.49 | -- | ||
Qwen3.6 35B A3B (non-reasoning) | 205k | 开放 | 15* | -- | 139 | 1.37 | 4.97 | -- | ||
Qwen3.6 35B A3B (non-reasoning) FP8 | 262k | 开放 | 15* | -- | -- | -- | -- | -- | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | 262k | 开放 | 15* | -- | 102 | 1.09 | 5.99 | -- | ||
Qwen3.6 35B A3B (non-reasoning) | 262k | 开放 | 15* | -- | 139 | 2.13 | 5.72 | -- | ||
Granite 4.2 30B | 131k | 开放 | 15* | -- | 77 | 0.83 | 33.41 | 26.06 | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.07 | 45 | 1.91 | 51.91 | 38.82 | ||
Gemma 4 31B (NVFP4) | 262k | 开放 | 15 | -- | 240 | 0.45 | 9.75 | 7.22 | ||
Gemma 4 31B (FP8) | 262k | 开放 | 15 | $0.10 | -- | -- | -- | -- | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.10 | 17 | 3.69 | 134.07 | 101.23 | ||
Gemma 4 31B (AI Studio) | 262k | 开放 | 15 | $0.00 | 36 | 1.12 | 63.71 | 48.60 | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.07 | 47 | 2.23 | 49.85 | 36.98 | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.10 | 15 | 3.39 | 151.83 | 115.25 | ||
Gemma 4 31B | 262k | 开放 | 15 | $0.10 | 27 | 1.32 | 82.91 | 63.34 | ||
Gemma 4 31B (FP8) | 262k | 开放 | 15 | $0.54 | 51 | 3.51 | 47.47 | 34.13 | ||
Gemma 4 31B | 131k | 开放 | 15 | $0.28 | 202 | 2.86 | 13.94 | 8.60 | ||
Gemma 4 31B | 256k | 开放 | 15 | $0.10 | 100 | 1.81 | 24.21 | 17.39 | ||
Mistral Medium 3.5 | 262k | 开放 | 14 | $0.50 | 168 | 2.27 | 17.15 | 11.91 | ||
Gemma 4 12B | 262k | 开放 | 14* | -- | 112 | 2.41 | 24.70 | 17.83 | ||
Nova 2.0 Pro Preview (medium) | 256k | 专有 | 14* | -- | 119 | 12.87 | 33.81 | 16.75 | ||
Gemma 4 31B (non-reasoning) (NVFP4) | 262k | 开放 | 14* | -- | 217 | 0.39 | 2.69 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | 开放 | 14* | -- | 55 | 2.22 | 11.24 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | 开放 | 14* | -- | 92 | 1.36 | 6.78 | -- | ||
Gemma 4 31B (non-reasoning) (FP8) | 262k | 开放 | 14* | -- | 16 | 2.10 | 32.96 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | 开放 | 14* | -- | 45 | 2.00 | 13.12 | -- | ||
Gemma 4 31B (non-reasoning) (FP8) | 262k | 开放 | 14* | -- | 46 | 3.54 | 14.39 | -- | ||
Gemma 4 31B (non-reasoning) | 131k | 开放 | 14* | -- | 203 | 2.86 | 5.33 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | 开放 | 14* | -- | 23 | 0.99 | 22.97 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | 开放 | 14* | -- | 14 | 3.00 | 39.57 | -- | ||
Nova 2.0 Omni (medium) | 1M | 专有 | 14* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (medium) | 1M | 专有 | 14* | -- | -- | -- | -- | -- | ||
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* | -- | 186 | 17.44 | 30.89 | 10.76 | ||
Qwen3.5 9B (non-reasoning) (FP8) | 262k | 开放 | 13* | -- | 102 | 0.66 | 5.56 | -- | ||
Command A+ | 200k | 开放 | 13 | $0.00 | 209 | 0.52 | 12.46 | 9.55 | ||
Gemma 4 26B A4B (non-reasoning) | 1M | 开放 | 13* | -- | 243 | 1.67 | 3.73 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | 开放 | 13* | -- | 68 | 1.71 | 9.09 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 131k | 开放 | 13* | -- | 451 | 1.06 | 2.17 | -- | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | 1.05M | 开放 | 13* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | 开放 | 13* | -- | 132 | 0.97 | 4.76 | -- | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | 262k | 开放 | 13* | -- | 100 | 2.28 | 7.28 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | 开放 | 13* | -- | 96 | 0.55 | 5.75 | -- | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | 262k | 开放 | 13* | -- | 32 | 0.78 | 16.57 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | 开放 | 13* | -- | 37 | 1.64 | 15.02 | -- | ||
Qwen3.5 4B (FP8) | 262k | 开放 | 13* | -- | 26 | 0.81 | 96.14 | 76.26 | ||
Nemotron 3.5 Lightning (NVFP4) | 262k | 开放 | 13 | $0.12 | 204 | 0.53 | 12.79 | 9.81 | ||
Nemotron 3.5 Lightning (BF16) | 1.05M | 开放 | 13 | $0.09 | 267 | 1.03 | 10.39 | 7.48 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 13 | $0.10 | 375 | 0.56 | 7.23 | 5.34 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 13 | $0.02 | 355 | 0.64 | 7.68 | 5.64 | ||
Nemotron 3.5 Lightning (BF16) | 262k | 开放 | 13 | $0.08 | 303 | 0.48 | 8.72 | 6.59 | ||
Nemotron 3 Super (FP8) | 262k | 开放 | 13 | $1.14 | 161 | 0.55 | 16.08 | 12.42 | ||
Nemotron 3 Super | 256k | 开放 | 13 | $1.64 | 210 | 1.38 | 13.30 | 9.54 | ||
Nemotron 3 Super | 262k | 开放 | 13 | $0.48 | 67 | 60.61 | 97.75 | 29.72 | ||
Nova 2.0 Pro Preview (low) | 256k | 专有 | 13* | -- | 125 | 13.25 | 33.20 | 15.96 | ||
Nova 2.0 Lite (medium) | 1M | 专有 | 12* | -- | 197 | 14.74 | 27.41 | 10.13 | ||
Qwen3.5 Omni Flash | 256k | 专有 | 12* | -- | 218 | 1.88 | 4.18 | -- | ||
Mercury 2.5 | 256k | 专有 | 12 | $0.12 | 621 | 3.73 | 4.54 | -- | ||
Nova 2.0 Lite (low) | 1M | 专有 | 12* | -- | 147 | 10.76 | 27.72 | 13.56 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | -- | 472 | 0.71 | 6.01 | 4.24 | ||
gpt-oss-120b (high) | 116k | 开放 | 12 | $0.23 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | 开放 | 12 | $0.12 | 109 | 1.38 | 24.40 | 18.42 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.02 | 39 | 1.20 | 65.94 | 51.80 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.11 | 315 | 0.72 | 8.65 | 6.34 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.04 | 184 | 1.27 | 14.87 | 10.88 | ||
gpt-oss-120b (high) (Turbo) | 131k | 开放 | 12 | $0.11 | 278 | 0.82 | 9.81 | 7.19 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.03 | 48 | 0.61 | 52.23 | 41.29 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.23 | 1,800 | 0.43 | 1.82 | 1.11 | ||
gpt-oss-120b (high) Vertex | 131k | 开放 | 12 | $0.06 | 46 | 72.31 | 126.18 | 43.10 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.04 | 213 | 0.39 | 12.16 | 9.41 | ||
gpt-oss-120b (high) | 128k | 开放 | 12 | $0.07 | 190 | 0.21 | 13.39 | 10.54 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.15 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.06 | 133 | 0.81 | 19.64 | 15.06 | ||
gpt-oss-120b (high) (Base) | 128k | 开放 | 12 | $0.11 | 236 | 1.03 | 11.61 | 8.46 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.19 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.11 | 95 | 1.08 | 27.49 | 21.13 | ||
gpt-oss-120b (high) | 131k | 开放 | 12 | $0.11 | 95 | 0.39 | 26.60 | 20.97 | ||
Mistral Small 4 | 256k | 开放 | 11 | $0.02 | 178 | 0.77 | 14.85 | 11.26 | ||
Qwen3 Next 80B A3B | 262k | 开放 | 11* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | 开放 | 11* | -- | 159 | 0.67 | 16.40 | 12.59 | ||
Qwen3 Next 80B A3B | 262k | 开放 | 11* | -- | 187 | 2.28 | 15.62 | 10.67 | ||
Qwen3 Next 80B A3B | 262k | 开放 | 11* | -- | -- | -- | -- | -- | ||
Qwen3.5 9B (FP8) | 262k | 开放 | 11 | $0.16 | 36 | 2.44 | 71.10 | 54.93 | ||
Qwen3.5 9B (FP8) | 262k | 开放 | 11 | $0.27 | 92 | 0.97 | 28.20 | 21.78 | ||
Nova 2.0 Omni (low) | 1M | 专有 | 11* | -- | -- | -- | -- | -- | ||
Granite 4.2 8B | 131k | 开放 | 11 | $0.05 | 94 | 0.70 | 27.25 | 21.24 | ||
Granite 4.2 8B | 131k | 开放 | 11 | $0.02 | 52 | 0.94 | 49.26 | 38.66 | ||
Ling 3.0 Tiny | 262k | 开放 | 11 | $0.00 | 53 | 2.62 | 49.64 | 37.61 | ||
G9v3-3B | 131k | 开放 | 11* | -- | -- | -- | -- | -- | ||
Trinity Large Thinking | 262k | 开放 | 11 | $0.12 | 344 | 1.18 | 8.45 | 5.82 | ||
Qwen3.5 4B (non-reasoning) FP8 | 262k | 开放 | 11* | -- | 13 | 0.94 | 39.51 | -- | ||
Nemotron 3 Nano Omni 30B A3B | 262k | 开放 | 10* | -- | 272 | 0.36 | 9.54 | 7.35 | ||
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* | -- | 242 | 1.08 | 11.39 | 8.25 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 746 | 1.26 | 4.61 | 2.68 | ||
gpt-oss-120b (low) Vertex | 131k | 开放 | 10* | -- | 91 | 4.56 | 31.92 | 21.89 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 203 | 0.39 | 12.72 | 9.86 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 47 | 0.67 | 54.16 | 42.79 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 38 | 1.21 | 66.78 | 52.46 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 1,717 | 0.40 | 1.86 | 1.17 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 332 | 0.83 | 8.36 | 6.03 | ||
gpt-oss-120b (low) | 128k | 开放 | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 128k | 开放 | 10* | -- | 215 | 0.19 | 11.82 | 9.30 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 86 | 1.10 | 30.17 | 23.25 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 133 | 0.84 | 19.67 | 15.07 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 124 | 0.43 | 20.58 | 16.12 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 472 | 0.69 | 5.99 | 4.24 | ||
gpt-oss-120b (low) | 131k | 开放 | 10* | -- | 200 | 1.11 | 13.59 | 9.99 | ||
Llama 4 Maverick (FP8) | 1.05M | 开放 | 10* | -- | 43 | 1.17 | 12.88 | -- | ||
Llama 4 Maverick (FP8) | 128k | 开放 | 10* | -- | 428 | 1.34 | 2.51 | -- | ||
Llama 4 Maverick | 128k | 开放 | 10* | -- | 258 | 0.98 | 2.91 | -- | ||
Llama 4 Maverick | 1.05M | 开放 | 10* | -- | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | 开放 | 10* | -- | 46 | 0.84 | 11.70 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | 开放 | 10* | -- | 75 | 1.26 | 7.92 | -- | ||
Nova 2.0 Pro Preview (non-reasoning) | 256k | 专有 | 10* | -- | 107 | 1.01 | 5.68 | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | 915 | 0.78 | 3.51 | 2.19 | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | 187 | 0.55 | 13.93 | 10.71 | ||
gpt-oss-20b (low) | 128k | 开放 | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | 81 | 13.57 | 44.51 | 24.75 | ||
gpt-oss-20b (low) | 131k | 开放 | 10* | -- | 132 | 1.24 | 20.23 | 15.19 | ||
gpt-oss-20b (low) Vertex | 131k | 开放 | 10* | -- | 403 | 0.33 | 6.53 | 4.96 | ||
North Mini Code | 256k | 开放 | 10 | $0.00 | 68 | 0.44 | 37.23 | 29.43 | ||
Qwen3 Next 80B A3B | 262k | 开放 | 10* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | 开放 | 10* | -- | 83 | 0.71 | 6.72 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 10* | -- | 71 | 0.96 | 7.97 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 10* | -- | 155 | 0.67 | 3.89 | -- | ||
Qwen3 Next 80B A3B | 262k | 开放 | 10* | -- | 156 | 1.21 | 4.43 | -- | ||
Qwen3 Next 80B A3B | 131k | 开放 | 10* | -- | 182 | 1.60 | 4.35 | -- | ||
Qwen3 Next 80B A3B | 131k | 开放 | 10* | -- | 169 | 2.15 | 5.11 | -- | ||
Gemma 4 12B (non-reasoning) | 262k | 开放 | 9* | -- | 117 | 2.43 | 6.72 | -- | ||
Mistral Large 3 | 256k | 开放 | 9 | $0.10 | 193 | 1.21 | 3.79 | -- | ||
Mistral Large 3 | 256k | 开放 | 9 | $0.10 | 56 | 1.79 | 10.70 | -- | ||
Mistral Large 3 | 262k | 开放 | 9 | $0.03 | 79 | 1.10 | 7.45 | -- | ||
Qwen3 Coder Next | 128k | 开放 | 9 | $0.78 | 69 | 1.16 | 8.37 | -- | ||
Qwen3 Coder Next (FP8) | 262k | 开放 | 9 | $0.12 | 66 | 1.05 | 8.57 | -- | ||
Qwen3 Coder Next (FP8) | 262k | 开放 | 9 | $0.78 | -- | -- | -- | -- | ||
Qwen3 Coder Next (FP8) | 262k | 开放 | 9 | $0.33 | 166 | 2.70 | 5.72 | -- | ||
Granite 4.2 3B | 131k | 开放 | 9 | $0.01 | 221 | 0.52 | 11.81 | 9.03 | ||
Mistral Small 4 (non-reasoning) | 262k | 开放 | 9* | -- | 168 | 0.74 | 3.71 | -- | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.01 | 151 | 0.56 | 17.16 | 13.28 | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.01 | 94 | 43.48 | 70.18 | 21.35 | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.01 | 113 | 0.52 | 22.58 | 17.64 | ||
gpt-oss-20b (high) | 131k | 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 | 167 | 1.18 | 16.19 | 12.00 | ||
gpt-oss-20b (high) Vertex | 131k | 开放 | 9 | $0.01 | 410 | 0.36 | 6.46 | 4.88 | ||
gpt-oss-20b (high) | 131k | 开放 | 9 | $0.02 | 929 | 0.81 | 3.50 | 2.15 | ||
Gemma 4 E4B | 131k | 开放 | 9* | -- | 46 | 1.21 | 55.13 | 43.14 | ||
Nemotron 3 Nano | 262k | 开放 | 9 | $0.02 | 135 | 1.04 | 19.51 | 14.78 | ||
Nemotron 3 Nano (FP4) | 262k | 开放 | 9 | $0.02 | 303 | 1.02 | 9.27 | 6.60 | ||
Nemotron 3 Nano | 262k | 开放 | 9 | $0.02 | 24 | 25.13 | 127.20 | 81.66 | ||
Nemotron 3 Nano (FP8) | 262k | 开放 | 9 | $0.01 | 268 | 0.29 | 9.63 | 7.47 | ||
Sarvam 105B (high) | 128k | 开放 | 9* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (non-reasoning) | 1M | 专有 | 9* | -- | 170 | 1.05 | 3.99 | -- | ||
Magistral Small 1.2 | 128k | 开放 | 9* | -- | 74 | 1.58 | 35.30 | 26.97 | ||
LFM2.5-2.6B | 32.8k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (non-reasoning) | 1M | 专有 | 8* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 131k | 开放 | 8* | -- | 26 | 0.83 | 20.06 | -- | ||
Llama 4 Scout | 128k | 开放 | 8* | -- | 134 | 0.86 | 4.59 | -- | ||
Llama 4 Scout Vertex | 1.31M | 开放 | 8* | -- | 151 | 0.72 | 4.02 | -- | ||
Llama 4 Scout | 131k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 128k | 开放 | 8* | -- | 197 | 1.23 | 3.77 | -- | ||
Llama 4 Scout | 131k | 开放 | 8* | -- | 27 | 1.32 | 19.61 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | 开放 | 8* | -- | 102 | 1.92 | 26.40 | 19.59 | ||
Llama 3.3 70B | 131k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B Vertex | 128k | 开放 | 8* | -- | 163 | 0.65 | 3.72 | -- | ||
Llama 3.3 70B | 131k | 开放 | 8* | -- | 306 | 0.84 | 2.47 | -- | ||
Llama 3.3 70B | 131k | 开放 | 8* | -- | 36 | 2.27 | 16.05 | -- | ||
Llama 3.3 70B (FP8) | 131k | 开放 | 8* | -- | 70 | 2.57 | 9.70 | -- | ||
Llama 3.3 70B | 128k | 开放 | 8* | -- | 274 | 2.12 | 3.94 | -- | ||
Llama 3.3 70B | 128k | 开放 | 8* | -- | 80 | 0.86 | 7.07 | -- | ||
Llama 3.3 70B Turbo | 131k | 开放 | 8* | -- | 64 | 1.54 | 9.38 | -- | ||
Llama 3.3 70B | 128k | 开放 | 8* | -- | 126 | 2.22 | 6.18 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | 开放 | 8* | -- | 20 | 2.27 | 27.42 | -- | ||
Llama 3.3 70B | 24k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B | 128k | 开放 | 8* | -- | 91 | 1.18 | 6.65 | -- | ||
Llama 3.3 70B | 100k | 开放 | 8* | -- | 60 | 1.36 | 9.64 | -- | ||
ERNIE 4.5 300B A47B | 131k | 开放 | 8* | -- | -- | -- | -- | -- | ||
Hermes 4 405B (FP8) | 128k | 开放 | 7* | -- | 40 | 2.37 | 65.61 | 50.60 | ||
Gemma 4 E4B (non-reasoning) | 131k | 开放 | 7* | -- | 72 | 0.80 | 7.70 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | 开放 | 7* | -- | 115 | 4.52 | 26.19 | 17.33 | ||
Hermes 4 405B (non-reasoning) (FP8) | 128k | 开放 | 7* | -- | 43 | 2.36 | 14.12 | -- | ||
Ring-flash-2.0 | 131k | 开放 | 7* | -- | -- | -- | -- | -- | ||
Olmo 3.1 32B Think | 65.5k | 开放 | 7* | -- | -- | -- | -- | -- | ||
Command A | 288k | 开放 | 7* | -- | 64 | 1.69 | 9.50 | -- | ||
Command A | 256k | 开放 | 7* | -- | 42 | 3.02 | 14.85 | -- | ||
Nemotron 3 Nano (non-reasoning) (FP4) | 262k | 开放 | 7* | -- | 287 | 1.06 | 2.80 | -- | ||
Nemotron 3 Nano (non-reasoning) | 262k | 开放 | 7* | -- | 100 | 0.69 | 5.68 | -- | ||
Nemotron 3 Nano (non-reasoning) (FP8) | 262k | 开放 | 7* | -- | 248 | 0.33 | 2.34 | -- | ||
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | 131k | 开放 | 7* | -- | 111 | 5.54 | 10.06 | -- | ||
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | 131k | 开放 | 7* | -- | 167 | 1.16 | 4.16 | -- | ||
Sarvam 30B (high) | 64k | 开放 | 7* | -- | -- | -- | -- | -- | ||
Celeris-1 | 131k | 专有 | 6 | $0.05 | 1,562 | 0.62 | 0.94 | -- | ||
Phi-4 Mini | 128k | 开放 | 6* | -- | 45 | 0.82 | 11.97 | -- | ||
Granite 4.0 H Small | 128k | 开放 | 6* | -- | 14 | 36.55 | 73.17 | -- | ||
Ministral 3 14B | 262k | 开放 | 6 | $0.02 | 76 | 0.97 | 7.52 | -- | ||
Ministral 3 14B | 256k | 开放 | 6 | $0.14 | 242 | 0.93 | 3.00 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | 开放 | 6* | -- | 97 | 1.87 | 7.03 | -- | ||
Phi-4 | 16.4k | 开放 | 6* | -- | 36 | 2.79 | 16.59 | -- | ||
Phi-4 | 16.4k | 开放 | 6* | -- | 73 | 0.98 | 7.85 | -- | ||
Nova Micro | 130k | 专有 | 6* | -- | 280 | 0.87 | 2.66 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (non-reasoning) | 128k | 开放 | 6* | -- | 183 | 1.12 | 3.86 | -- | ||
Phi-4 Multimodal | 4.1k | 开放 | 6* | -- | -- | -- | -- | -- | ||
Reka Flash 3 | 54k | 开放 | 6* | -- | -- | -- | -- | -- | ||
Ministral 3 8B | 256k | 开放 | 5 | $0.07 | 320 | 0.91 | 2.47 | -- | ||
Ministral 3 8B | 262k | 开放 | 5 | $0.01 | 102 | 0.77 | 5.69 | -- | ||
Llama 3.2 11B (Vision) | 131k | 开放 | 5* | -- | 17 | 3.76 | 33.78 | -- | ||
Olmo 3 7B | 65.5k | 开放 | 5* | -- | -- | -- | -- | -- | ||
Apertus 70B Instruct | 64k | 开放 | 5* | -- | -- | -- | -- | -- | ||
Ministral 3 3B | 256k | 开放 | 5 | $0.04 | 412 | 0.93 | 2.15 | -- | ||
Ministral 3 3B | 131k | 开放 | 5 | $0.01 | 206 | 0.69 | 3.11 | -- | ||
Tiny Aya Global | 8.19k | 开放 | 5* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | 开放 | 5* | -- | -- | -- | -- | -- | ||
Cogito v2.1 | 164k | 开放 | -- | -- | -- | -- | -- | -- | ||