LLM API Providers Leaderboard - Comparison of over 500 AI Model endpoints
Comparison of API provider performance across over 500 AI Model endpoints, including from OpenAI, Google, DeepSeek and others, across performance key metrics including price, output speed, latency, context window and more.
For more details including relating to our methodology, see our FAQs.
Further Analysis | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Claude Fable 5.1 (max with fallback) | 1M | Proprietary | 53 | $7.63 | 66 | 298.45 | 306.04 | -- | ||
Claude Fable 5.1 (xhigh with fallback) | 1M | Proprietary | 53 | $5.98 | 62 | 187.94 | 196.03 | -- | ||
GPT-6 Astra (max) | 1M | Proprietary | 53 | $3.26 | 65 | 259.33 | 266.99 | -- | ||
GPT-6 Astra (max) | 524k | Proprietary | 53 | $3.26 | 92 | 271.97 | 277.41 | -- | ||
GPT-6 Astra (xhigh) | 1M | Proprietary | 52 | $2.31 | 55 | 122.80 | 131.91 | -- | ||
Claude Fable 5.1 (high with fallback) | 1M | Proprietary | 51 | $3.91 | 56 | 20.56 | 29.52 | -- | ||
GPT-6 Astra (high) | 1M | Proprietary | 51 | $1.73 | 54 | 41.22 | 50.41 | -- | ||
Claude Opus 5 (max) | 1M | Proprietary | 51 | $5.86 | 57 | 58.34 | 67.08 | -- | ||
Claude Opus 5 (max) | 1M | Proprietary | 51 | $5.86 | 56 | 49.25 | 58.11 | -- | ||
Claude Opus 5 (max) | 1M | Proprietary | 51 | $9.38 | 56 | 39.74 | 48.74 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietary | 50 | $4.88 | 54 | 20.39 | 29.58 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietary | 50 | $7.75 | 54 | 29.51 | 38.72 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietary | 50 | $4.88 | 55 | 37.05 | 46.15 | -- | ||
GPT-6 Astra (medium) | 1M | Proprietary | 50 | $1.54 | 54 | 5.02 | 14.35 | -- | ||
Claude Fable 5.1 (medium with fallback) | 1M | Proprietary | 49 | $2.98 | 57 | 8.45 | 17.30 | -- | ||
Claude Opus 5 (high) | 1M | Proprietary | 48 | $3.61 | 57 | 13.55 | 22.26 | -- | ||
Claude Opus 5 (high) | 1M | Proprietary | 48 | $5.64 | 55 | 14.14 | 23.32 | -- | ||
Claude Opus 5 (high) | 1M | Proprietary | 48 | $3.61 | 56 | 8.46 | 17.38 | -- | ||
Muse Spark 1.3 (max) | 1.05M | Proprietary | 48 | $1.60 | 222 | 20.75 | 32.00 | 9.00 | ||
GPT-5.6 Sol (max) | 1M | Proprietary | 47 | $3.70 | 105 | 98.05 | 102.80 | -- | ||
GPT-5.6 Sol (max) | 1M | Proprietary | 47 | $1.99 | 84 | 124.25 | 130.19 | -- | ||
GPT-5.6 Sol (max) | 524k | Proprietary | 47 | -- | 115 | 103.70 | 108.07 | -- | ||
Claude Fable 5.1 (low with fallback) | 1M | Proprietary | 47 | $2.37 | 55 | 8.00 | 17.05 | -- | ||
Grok 4.7 (xhigh) | 500k | Proprietary | 46 | $3.74 | 39 | 0.85 | 13.52 | -- | ||
Grok 4.7 (high) | 500k | Proprietary | 46 | $2.73 | 55 | 0.84 | 9.88 | -- | ||
MiMo-V2.6-Pro | 1M | Open | 46 | $0.13 | 125 | 2.34 | 22.42 | 16.06 | ||
GPT-6 Astra (low) | 1M | Proprietary | 46 | $0.82 | 53 | 2.59 | 11.97 | -- | ||
Qwen3.8 Max (0902) | 984k | Proprietary | 45 | $5.41 | 39 | 2.92 | 66.62 | 50.96 | ||
Muse Spark 1.3 (xhigh) | 1.05M | Proprietary | 45 | $1.37 | 260 | 22.33 | 31.93 | 7.68 | ||
Claude Opus 5 (medium) | 1M | Proprietary | 45 | $2.19 | 58 | 4.84 | 13.51 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietary | 45 | $2.19 | 54 | 4.77 | 14.02 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietary | 45 | $3.32 | 53 | 3.74 | 13.10 | -- | ||
GLM-5.3 (max) | 1M | Open | 45 | $2.01 | 61 | 3.12 | 44.08 | 32.76 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $2.15 | 81 | 1.46 | 32.23 | 24.61 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $2.16 | 160 | 1.03 | 16.62 | 12.47 | ||
GLM-5.3 (max) | 164k | Open | 45 | $2.05 | -- | -- | -- | -- | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $1.73 | 42 | 1.09 | 60.43 | 47.47 | ||
GLM-5.3 (max) | 1M | Open | 45 | $1.97 | 210 | 1.01 | 12.92 | 9.53 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $2.58 | 230 | 0.65 | 11.53 | 8.71 | ||
GLM-5.3 (max) (FAST) | 1M | Open | 45 | $4.08 | 442 | 0.77 | 6.44 | 4.53 | ||
GLM-5.3 (max) | 1M | Open | 45 | $8.68 | 72 | 2.50 | 37.21 | 27.77 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $1.43 | 126 | 1.69 | 21.48 | 15.83 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $1.90 | 153 | 1.28 | 17.60 | 13.06 | ||
GLM-5.3 (max) | 1M | Open | 45 | $2.01 | 226 | 1.06 | 12.12 | 8.85 | ||
GLM-5.3 (max) | 1M | Open | 45 | $6.82 | 171 | 0.76 | 15.36 | 11.68 | ||
GLM-5.3 (max) | 1M | Open | 45 | $2.01 | 222 | 1.13 | 12.39 | 9.00 | ||
GLM-5.3 (max) | 1M | Open | 45 | $2.01 | 238 | 0.80 | 11.30 | 8.40 | ||
GLM-5.3 (max) (FAST) | 1M | Open | 45 | $2.15 | 163 | 0.66 | 16.00 | 12.27 | ||
GLM-5.3 (max) | 164k | Open | 45 | $2.04 | 147 | 2.68 | 19.71 | 13.62 | ||
GLM-5.3 (max) | 1M | Open | 45 | $4.99 | 134 | 2.11 | 20.72 | 14.89 | ||
GLM-5.3 (max) (FP4) | 786k | Open | 45 | $4.25 | 231 | 0.97 | 11.80 | 8.67 | ||
GLM-5.3 (max) (FP4) | 1M | Open | 45 | $8.68 | 373 | 1.92 | 8.63 | 5.36 | ||
GLM-5.3 (max) | 1M | Open | 45 | $1.72 | 71 | 1.82 | 36.89 | 28.06 | ||
Grok 4.6 (high) | 500k | Proprietary | 44 | $1.86 | 60 | 40.14 | 48.42 | -- | ||
Grok 4.6 (xhigh) | 500k | Proprietary | 44 | $2.32 | 58 | 48.65 | 57.24 | -- | ||
GPT-5.6 Sol (xhigh) | 1M | Proprietary | 44 | $1.18 | 72 | 37.38 | 44.29 | -- | ||
GPT-5.6 Sol (xhigh) | 524k | Proprietary | 44 | $1.26 | 106 | 25.61 | 30.34 | -- | ||
Step 5 Preview | 1M | Proprietary | 44 | $0.72 | 89 | 5.97 | 34.11 | 22.51 | ||
Kimi K3 (max) | 205k | Open | 44 | $1.85 | 124 | 0.97 | 21.20 | 16.18 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $5.42 | 45 | 2.19 | 57.75 | 44.45 | ||
Kimi K3 (max) (FAST) | 1.05M | Open | 44 | $5.80 | 71 | 1.12 | 36.21 | 28.07 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $1.81 | 84 | 1.41 | 31.22 | 23.85 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $4.34 | 85 | 0.81 | 30.35 | 23.63 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $2.25 | 36 | 1.23 | 71.03 | 55.84 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $2.01 | 112 | 0.98 | 23.26 | 17.82 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $2.42 | 114 | 1.32 | 23.22 | 17.52 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $1.21 | 61 | 1.49 | 42.22 | 32.59 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $9.22 | 236 | 1.55 | 12.15 | 8.48 | ||
Kimi K3 (max) | 262k | Open | 44 | $2.70 | 90 | 1.75 | 29.59 | 22.27 | ||
Kimi K3 (max) (FAST) | 1.05M | Open | 44 | $3.77 | 282 | 1.70 | 10.56 | 7.09 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $2.00 | 41 | 4.08 | 65.61 | 49.22 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $1.69 | 214 | 0.73 | 12.40 | 9.34 | ||
Kimi K3 (max) (FAST) | 1.05M | Open | 44 | $2.81 | 190 | 0.75 | 13.91 | 10.53 | ||
Kimi K3 (max) (ULTRA) | 1.05M | Open | 44 | $3.93 | 213 | 0.73 | 12.47 | 9.39 | ||
Grok 4.6 (medium) | 500k | Proprietary | 43 | $1.50 | 60 | 31.86 | 40.23 | -- | ||
GPT-5.6 Sol (high) | 1M | Proprietary | 42 | $0.81 | 71 | 9.06 | 16.08 | -- | ||
GPT-5.6 Sol (high) | 524k | Proprietary | 42 | $0.85 | 101 | 7.16 | 12.11 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietary | 42 | $1.40 | 105 | 223.75 | 228.53 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietary | 42 | $1.95 | 165 | 154.55 | 157.58 | -- | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.25 | 89 | 2.68 | 30.63 | 22.36 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.30 | 128 | 0.95 | 20.54 | 15.67 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.29 | 97 | 1.78 | 27.58 | 20.63 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.43 | 21 | 1.33 | 121.10 | 95.82 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.29 | 93 | 1.40 | 28.35 | 21.56 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.29 | 41 | 1.57 | 62.66 | 48.88 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.36 | 78 | 0.80 | 32.80 | 25.60 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.30 | 123 | 1.33 | 21.63 | 16.24 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.28 | 231 | 0.72 | 11.55 | 8.66 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.42 | 72 | 2.87 | 37.80 | 27.95 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.28 | 89 | 1.08 | 29.32 | 22.60 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.14 | 194 | 4.72 | 17.62 | 10.32 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.28 | 94 | 1.26 | 27.93 | 21.33 | ||
GLM-5.3-Flash | 1M | Open | 42 | $1.19 | -- | -- | -- | -- | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.33 | 104 | 0.91 | 25.05 | 19.31 | ||
GLM-5.3-Flash (FAST) | 1M | Open | 42 | $0.46 | 493 | 8.74 | 13.80 | 4.05 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.76 | 239 | 1.77 | 12.24 | 8.38 | ||
GLM-5.3-Flash (FP4) | 1.05M | Open | 42 | $0.60 | 189 | 1.19 | 14.42 | 10.58 | ||
Gemini 3.8 Flash (high) AI Studio | 1M | Proprietary | 41 | $1.24 | 344 | 15.01 | 16.47 | -- | ||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $1.87 | 132 | 0.99 | 19.94 | 15.16 | ||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $2.77 | 177 | 1.01 | 15.12 | 11.28 | ||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $2.89 | 111 | 1.44 | 24.03 | 18.07 | ||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $1.81 | 61 | 2.13 | 43.34 | 32.97 | ||
Qwen3.8 2.4T A95B (FP8) | 262k | Open | 40 | $1.54 | -- | -- | -- | -- | ||
Qwen3.8 2.4T A95B | 984k | Open | 40 | $2.16 | 39 | 3.02 | 67.02 | 51.20 | ||
Qwen3.8-Flash-Next | 1M | Open | 40 | $0.37 | 54 | 2.71 | 48.93 | 36.98 | ||
Gemini 3.8 Flash (medium) AI Studio | 1M | Proprietary | 40 | $0.93 | -- | -- | -- | -- | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.27 | 226 | 0.92 | 12.00 | 8.86 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $1.88 | 137 | 1.91 | 20.20 | 14.63 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.77 | 153 | 2.18 | 18.52 | 13.07 | ||
DeepSeek V4.1 Flash (max) | 524k | Open | 39 | $0.24 | 200 | 2.05 | 14.53 | 9.98 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.19 | 76 | 0.81 | 33.83 | 26.42 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.64 | 56 | 1.05 | 45.37 | 35.45 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.64 | 227 | 2.28 | 13.29 | 8.81 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $0.90 | 167 | 1.43 | 16.42 | 12.00 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $2.18 | 247 | 0.76 | 10.90 | 8.11 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $0.73 | 91 | 0.92 | 28.31 | 21.92 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.34 | 334 | 1.25 | 8.73 | 5.98 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.29 | 58 | 0.92 | 44.16 | 34.59 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $0.32 | 255 | 0.40 | 10.21 | 7.85 | ||
DeepSeek V4.1 Flash (max) (FAST) | 1.05M | Open | 39 | $0.49 | 579 | 1.43 | 5.75 | 3.46 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $0.16 | 327 | 0.89 | 8.53 | 6.11 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $1.61 | 181 | 0.76 | 14.58 | 11.06 | ||
Claude Opus 5 (low) | 1M | Proprietary | 39 | $1.10 | 60 | 2.94 | 11.28 | -- | ||
Claude Opus 5 (low) | 1M | Proprietary | 39 | $1.10 | 53 | 3.52 | 12.92 | -- | ||
Claude Opus 5 (low) | 1M | Proprietary | 39 | $1.57 | 56 | 2.91 | 11.90 | -- | ||
GPT-5.6 Sol (medium) | 1M | Proprietary | 39 | $0.50 | 64 | 5.10 | 12.95 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 38 | $7.36 | 82 | 196.21 | 202.31 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 38 | $4.75 | 86 | 169.00 | 174.83 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 38 | $5.09 | 77 | 141.26 | 147.72 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 38 | $6.21 | 70 | 218.74 | 225.85 | -- | ||
GPT-5.6 Terra (xhigh) | 1M | Proprietary | 38 | $0.63 | 94 | 18.40 | 23.74 | -- | ||
GPT-5.6 Terra (xhigh) | 524k | Proprietary | 38 | $0.67 | 121 | 21.78 | 25.92 | -- | ||
GPT-5.6 Luna (max) | 1M | Proprietary | 37 | $0.18 | 159 | 123.28 | 126.43 | -- | ||
GPT-5.6 Luna (max) | 1M | Proprietary | 37 | $1.02 | 260 | 112.98 | 114.90 | -- | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $0.67 | 74 | 1.65 | 35.56 | 27.13 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $1.61 | 80 | 3.77 | 35.02 | 25.00 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $6.15 | 80 | 12.14 | 43.24 | 24.88 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Open | 36 | $0.60 | 82 | 1.66 | 32.30 | 24.52 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Open | 36 | $6.17 | 185 | 1.08 | 14.58 | 10.80 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $1.65 | 167 | 1.68 | 16.69 | 12.00 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Open | 36 | $1.00 | 124 | 0.84 | 21.05 | 16.17 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $0.70 | 80 | 1.84 | 33.19 | 25.08 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $0.83 | 170 | 0.93 | 15.61 | 11.75 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $8.43 | 215 | 2.47 | 14.12 | 9.32 | ||
Agnes 3.0 Flash | 1M | Proprietary | 36* | -- | -- | -- | -- | -- | ||
Agnes 2.5 Pro Beta | 1M | Proprietary | 35* | -- | -- | -- | -- | -- | ||
Grok 4.6 (low) | 500k | Proprietary | 35 | $0.48 | 57 | 7.95 | 16.75 | -- | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $0.60 | 173 | 0.76 | 15.19 | 11.54 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $0.31 | 236 | 1.19 | 11.76 | 8.46 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $0.12 | 159 | 0.83 | 16.52 | 12.55 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $0.28 | 237 | 2.23 | 12.78 | 8.44 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $2.51 | 219 | 1.22 | 12.63 | 9.13 | ||
GPT-5.6 Luna (xhigh) | 1M | Proprietary | 35 | $0.09 | 160 | 34.56 | 37.68 | -- | ||
GPT-5.6 Luna (xhigh) | 524k | Proprietary | 35 | $0.09 | 158 | 63.73 | 66.90 | -- | ||
Kimi K3 (low) | 1.05M | Open | 34* | -- | 37 | 4.72 | 71.44 | 53.38 | ||
Kimi K3 (low) | 1M | Open | 34* | -- | 107 | 0.80 | 24.09 | 18.63 | ||
Kimi K3 (low) | 1M | Open | 34* | -- | 100 | 0.93 | 25.84 | 19.92 | ||
Claude Sonnet 5 (xhigh) | 1M | Proprietary | 34 | $2.87 | 71 | 48.40 | 55.42 | -- | ||
GPT-5.6 Terra (high) | 1M | Proprietary | 34 | $0.34 | 88 | 3.03 | 8.70 | -- | ||
GPT-5.6 Terra (high) | 524k | Proprietary | 34 | $0.35 | 116 | 3.47 | 7.80 | -- | ||
Qwen3.8 27B (xhigh) | 262k | Open | 34 | $0.65 | 32 | 1.10 | 78.31 | 61.77 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | Open | 34 | $0.92 | 62 | 1.80 | 42.02 | 32.18 | ||
Qwen3.8 27B (xhigh) | 1M | Open | 34 | $0.82 | 45 | 3.94 | 60.06 | 44.89 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | Open | 34 | $2.29 | 68 | 1.25 | 38.14 | 29.51 | ||
Qwen3.8 27B (xhigh) | 262k | Open | 34 | $1.98 | 211 | 0.98 | 12.84 | 9.49 | ||
GPT-5.6 Sol (low) | 1M | Proprietary | 33 | $0.26 | 67 | 3.71 | 11.17 | -- | ||
Gemini 3.8 Flash (low) AI Studio | 1M | Proprietary | 33 | -- | -- | -- | -- | -- | ||
GPT-5.3 Codex (xhigh) | 400k | Proprietary | 33* | -- | 176 | 61.50 | 64.35 | -- | ||
GPT-5.6 Luna (high) | 1M | Proprietary | 32 | $0.04 | 140 | 9.68 | 13.24 | -- | ||
GPT-5.6 Luna (high) | 524k | Proprietary | 32 | $0.05 | 158 | 8.64 | 11.81 | -- | ||
Claude Sonnet 5 (high) | 1M | Proprietary | 32 | $1.79 | 70 | 11.29 | 18.38 | -- | ||
Apodex 1.1 | 256k | Proprietary | 30* | -- | -- | -- | -- | -- | ||
GPT-5.6 Terra (medium) | 1M | Proprietary | 30 | $0.18 | 90 | 2.03 | 7.57 | -- | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | Proprietary | 30 | $0.67 | 122 | 37.84 | 41.95 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | Proprietary | 30 | $0.98 | 131 | 26.68 | 30.50 | -- | ||
MiniMax-M3 (MXFP8) | 1M | Open | 29 | $0.46 | 190 | 1.12 | 14.26 | 10.51 | ||
MiniMax-M3 (NVFP4) | 262k | Open | 29 | $0.40 | 56 | 1.42 | 45.72 | 35.44 | ||
MiniMax-M3 | 1M | Open | 29 | $0.70 | 117 | 0.70 | 22.06 | 17.09 | ||
MiniMax-M3 | 1M | Open | 29 | $0.46 | 147 | 1.22 | 18.26 | 13.63 | ||
MiniMax-M3 (FAST) | 1.05M | Open | 29 | $1.09 | 446 | 1.61 | 7.22 | 4.49 | ||
MiniMax-M3 | 1M | Open | 29 | $0.46 | -- | -- | -- | -- | ||
MiniMax-M3 (FP8) | 1.05M | Open | 29 | $1.91 | 284 | 1.91 | 10.72 | 7.05 | ||
MiniMax-M3 (FP8) | 1M | Open | 29 | $0.45 | 160 | 1.16 | 16.76 | 12.49 | ||
MiniMax-M3 | 524k | Open | 29 | $0.64 | 80 | 2.75 | 33.93 | 24.94 | ||
MiniMax-M3 | 512k | Open | 29 | $0.51 | 156 | 0.94 | 16.94 | 12.80 | ||
MiniMax-M3 | 524k | Open | 29 | $0.44 | 16 | 29.04 | 186.21 | 125.74 | ||
MiniMax-M3 | 1.05M | Open | 29 | -- | -- | -- | -- | -- | ||
MiniMax-M3 | 1.05M | Open | 29 | $3.83 | -- | -- | -- | -- | ||
MiniMax-M3 | 524k | Open | 29 | $0.50 | 172 | 1.02 | 15.54 | 11.62 | ||
GPT-5.6 Sol (Non-reasoning) | 1M | Proprietary | 28* | -- | 64 | 1.20 | 9.03 | -- | ||
GPT-5.6 Sol (Non-reasoning) | 1M | Proprietary | 28* | -- | 99 | 0.79 | 5.83 | -- | ||
Solar Pro 4 | 512k | Proprietary | 28* | -- | 66 | 2.03 | 39.84 | 30.25 | ||
Claude Sonnet 5 (medium) | 1M | Proprietary | 28 | $1.00 | 67 | 2.40 | 9.86 | -- | ||
Inkling Small | 256k | Open | 28* | -- | 194 | 2.05 | 14.97 | 10.33 | ||
Inkling Small | 524k | Open | 28* | -- | 192 | 0.56 | 13.61 | 10.44 | ||
Inkling Small | 262k | Open | 28* | -- | 256 | 0.52 | 10.27 | 7.80 | ||
Qwen3.8 27B (medium) | 1M | Open | 28 | $0.90 | 53 | 3.86 | 51.25 | 37.91 | ||
Qwen3.8 27B (medium) | 262k | Open | 28 | $2.36 | 204 | 1.04 | 13.27 | 9.78 | ||
GPT-5.6 Terra (low) | 1M | Proprietary | 27 | $0.14 | 87 | 1.95 | 7.72 | -- | ||
Agnes 2.5 Pro Alpha | 1M | Open | 27* | -- | 187 | 4.02 | 17.38 | 10.69 | ||
Quasar 438B (max) | 1M | Proprietary | 27 | $2.02 | 151 | 1.22 | 17.82 | 13.28 | ||
Qwen3.8 27B (low) | 1M | Open | 26 | $0.83 | 53 | 3.82 | 51.19 | 37.90 | ||
Qwen3.8 27B (low) | 262k | Open | 26 | $2.19 | 204 | 0.98 | 13.26 | 9.82 | ||
GPT-5.5 Instant (June 2026) | 400k | Proprietary | 26 | $0.69 | 144 | 1.05 | 18.46 | 13.93 | ||
MiMo-V2.5-Pro | 1.05M | Open | 26 | $0.07 | 53 | 2.91 | 50.37 | 37.97 | ||
MiMo-V2.5-Pro | 1.05M | Open | 26 | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | Open | 26 | $0.43 | 37 | 1.76 | 69.52 | 54.20 | ||
MiMo-V2.5-Pro | 1M | Open | 26 | $0.05 | 46 | 2.77 | 56.57 | 43.04 | ||
Kimi K2.7 Code (FP4) | 256k | Open | 26 | $1.89 | 188 | 1.77 | 16.29 | 11.86 | ||
Kimi K2.7 Code (FP8) | 65.5k | Open | 26 | $1.20 | 63 | 5.35 | 48.99 | 35.64 | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.89 | 277 | 1.23 | 11.08 | 8.05 | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.76 | 231 | 0.47 | 12.30 | 9.67 | ||
Kimi K2.7 Code | 262k | Open | 26 | $1.69 | -- | -- | -- | -- | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.55 | 60 | 3.99 | 49.17 | 36.90 | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.39 | 36 | 1.03 | 77.32 | 62.31 | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.52 | 88 | 0.76 | 31.76 | 25.32 | ||
Kimi K2.7 Code | 256k | Open | 26 | $0.54 | 61 | 3.03 | 47.78 | 36.55 | ||
Hy3 (FP8) | 256k | Open | 25 | $0.07 | 90 | 3.06 | 30.98 | 22.34 | ||
Hy3 | 262k | Open | 25 | $0.07 | 87 | 2.27 | 30.87 | 22.88 | ||
Hy3 (FP8) | 262k | Open | 25 | $0.07 | 122 | 1.06 | 21.52 | 16.37 | ||
Hy3 | 262k | Open | 25 | $0.07 | 89 | 3.53 | 31.70 | 22.54 | ||
MiMo-V2.5 | 1.05M | Open | 25* | -- | 32 | 5.58 | 83.35 | 62.22 | ||
MiMo-V2.5 | 262k | Open | 25* | -- | 12 | 1.21 | 217.49 | 173.03 | ||
MiMo-V2.5 | 1.05M | Open | 25* | -- | -- | -- | -- | -- | ||
MiMo-V2.5 | 1M | Open | 25* | -- | 34 | 3.72 | 76.68 | 58.37 | ||
Qwen3.7 Plus | 1M | Proprietary | 25 | $0.33 | 69 | 2.23 | 38.70 | 29.18 | ||
GPT-5.6 Luna (medium) | 1M | Proprietary | 25 | $0.02 | 148 | 2.31 | 5.68 | -- | ||
Inkling (FP8) | 131k | Open | 25 | $0.81 | 208 | 0.57 | 12.62 | 9.63 | ||
Inkling | 262k | Open | 25 | $0.72 | 215 | 0.66 | 12.29 | 9.30 | ||
Inkling | 524k | Open | 25 | $0.91 | 132 | 0.67 | 19.60 | 15.14 | ||
Inkling | 262k | Open | 25 | $0.61 | 100 | 2.42 | 27.45 | 20.03 | ||
Inkling | 1M | Open | 25 | $0.61 | 232 | 1.43 | 12.19 | 8.61 | ||
Ling 3.0 Flash | 131k | Open | 25* | -- | 47 | 1.77 | 54.50 | 42.19 | ||
Ling 3.0 Flash | 262k | Open | 25* | -- | 326 | 2.53 | 10.19 | 6.13 | ||
Ling-3.0-flash-VL | 262k | Open | 25 | -- | 148 | 3.29 | 20.18 | 13.51 | ||
Claude Sonnet 5 (low) | 1M | Proprietary | 24 | $0.51 | 64 | 1.81 | 9.65 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietary | 23* | -- | 65 | 1.28 | 8.96 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietary | 23* | -- | 64 | 1.92 | 9.76 | -- | ||
Nemotron 3 Ultra | 262k | Open | 23 | $0.19 | 204 | 1.08 | 14.69 | 11.16 | ||
Nemotron 3 Ultra | 262k | Open | 23 | -- | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Open | 23 | $0.47 | 118 | 5.11 | 28.71 | 19.35 | ||
Nemotron 3 Ultra BF16 | 262k | Open | 23 | $0.92 | 166 | 3.26 | 19.95 | 13.68 | ||
Nemotron 3 Ultra | 256k | Open | 23 | $1.16 | 356 | 2.34 | 10.12 | 6.38 | ||
Nemotron 3 Ultra | 262k | Open | 23 | $0.48 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Open | 23 | $0.37 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Open | 23 | $0.22 | 164 | 0.65 | 17.52 | 13.83 | ||
Ling-3.0-flash-Fin | 262k | Open | 23 | -- | 156 | 2.86 | 18.86 | 12.80 | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | Proprietary | 22 | $0.12 | 386 | 11.21 | 12.50 | -- | ||
G9v3-39A5B | 131k | Open | 22* | -- | -- | -- | -- | -- | ||
KAT-Coder-Pro V2 | 256k | Proprietary | 22* | -- | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | Open | 21* | -- | 183 | 0.87 | 3.60 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) (FP8) | 262k | Open | 21* | -- | 41 | 1.16 | 13.35 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | Open | 21* | -- | 89 | 2.18 | 7.77 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) (Base, FP4) | 262k | Open | 21* | -- | 142 | 2.05 | 5.58 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | Open | 21* | -- | 10 | 1.77 | 50.52 | -- | ||
Qwen3.5 397B A17B (Non-reasoning) | 262k | Open | 21* | -- | 85 | 1.70 | 7.56 | -- | ||
GPT-5.6 Luna (low) | 1M | Proprietary | 21 | $0.01 | 145 | 1.75 | 5.20 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 1M | Proprietary | 21 | $0.14 | 84 | 0.88 | 6.81 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 1M | Proprietary | 21 | $0.19 | 127 | 0.85 | 4.80 | -- | ||
Qwen3.5 Omni Plus | 256k | Proprietary | 20* | -- | 93 | 2.09 | 7.47 | -- | ||
o3 | 200k | Proprietary | 20* | -- | 109 | 36.58 | 41.16 | -- | ||
o3 | 200k | Proprietary | 20* | -- | -- | -- | -- | -- | ||
o3 | 200k | Proprietary | 20* | -- | 138 | 6.47 | 10.10 | -- | ||
Qwen3.8 27B | 1M | Open | 20 | $1.91 | 49 | 3.87 | 14.06 | -- | ||
Qwen3.8 27B | 262k | Open | 20 | $5.69 | 242 | 0.97 | 3.04 | -- | ||
Step 3.7 Flash | 256k | Open | 19* | -- | 195 | 2.55 | 15.38 | 10.26 | ||
Step 3.7 Flash | 256k | Open | 19* | -- | 168 | 0.67 | 15.59 | 11.94 | ||
LongCat 2.0 | 1M | Open | 19 | $0.06 | -- | -- | -- | -- | ||
LongCat 2.0 (FP8) | 262k | Open | 19 | $0.15 | 58 | 2.76 | 45.62 | 34.28 | ||
Gemma 4 31B | 262k | Open | 19* | -- | 46 | 2.31 | 50.85 | 37.69 | ||
Gemma 4 31B (NVFP4) | 262k | Open | 19* | -- | -- | -- | -- | -- | ||
Gemma 4 31B (FP8) | 262k | Open | 19* | -- | -- | -- | -- | -- | ||
Gemma 4 31B | 262k | Open | 19* | -- | -- | -- | -- | -- | ||
Gemma 4 31B | 131k | Open | 19* | -- | -- | -- | -- | -- | ||
Gemma 4 31B (AI Studio) | 262k | Open | 19* | -- | 35 | 1.03 | 64.11 | 48.97 | ||
Gemma 4 31B | 262k | Open | 19* | -- | 86 | 1.18 | 27.33 | 20.30 | ||
Gemma 4 31B | 262k | Open | 19* | -- | 21 | 2.02 | 107.80 | 82.13 | ||
Gemma 4 31B | 262k | Open | 19* | -- | 24 | 1.51 | 95.65 | 73.09 | ||
Gemma 4 31B (FP8) | 262k | Open | 19* | -- | 50 | 3.70 | 48.15 | 34.51 | ||
Gemma 4 31B | 131k | Open | 19* | -- | -- | -- | -- | -- | ||
Gemma 4 31B | 256k | Open | 19* | -- | 102 | 1.80 | 23.71 | 17.01 | ||
Gemma 4 31B | 131k | Open | 19* | -- | -- | -- | -- | -- | ||
Gemma 4 31B (FP8) | 262k | Open | 19* | -- | -- | -- | -- | -- | ||
Qwen3.5 397B A17B | 262k | Open | 18 | $0.47 | 89 | 2.24 | 43.72 | 35.85 | ||
Qwen3.5 397B A17B | 262k | Open | 18 | $0.34 | 180 | 0.84 | 21.30 | 17.68 | ||
Qwen3.5 397B A17B | 262k | Open | 18 | $0.30 | 69 | 1.05 | 54.72 | 46.39 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 18 | $0.31 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 18 | $0.23 | 42 | 1.01 | 88.16 | 75.33 | ||
Qwen3.5 397B A17B | 262k | Open | 18 | $0.17 | 12 | 1.29 | 303.16 | 260.92 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 18 | $0.47 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Open | 18 | $0.47 | 138 | 2.05 | 28.70 | 23.03 | ||
Qwen3.5 397B A17B | 262k | Open | 18 | $0.47 | 91 | 1.67 | 42.23 | 35.06 | ||
MiMo-V2.5-Pro (Non-reasoning) | 1.05M | Open | 18* | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro (Non-reasoning) | 65.5k | Open | 18* | -- | 35 | 1.54 | 15.87 | -- | ||
MiMo-V2.5-Pro (Non-reasoning) | 131k | Open | 18* | -- | 47 | 2.42 | 13.17 | -- | ||
MiMo-V2.5-Pro (Non-reasoning) | 1.05M | Open | 18* | -- | 52 | 4.10 | 13.72 | -- | ||
Qwen3.6 35B A3B | 229k | Open | 18 | $0.48 | 117 | 2.12 | 52.68 | 46.27 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 18 | $0.27 | 91 | 2.06 | 66.79 | 59.24 | ||
Qwen3.6 35B A3B | 262k | Open | 18 | $0.37 | 153 | 1.11 | 39.76 | 35.37 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 18 | $0.14 | 76 | 0.86 | 78.74 | 71.27 | ||
Qwen3.6 35B A3B FP8 | 262k | Open | 18 | $0.31 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | Open | 18 | $0.12 | 88 | 0.91 | 67.86 | 61.27 | ||
Qwen3.6 35B A3B | 205k | Open | 18 | $0.31 | 117 | 1.40 | 51.83 | 46.16 | ||
Qwen3.5 122B A10B (Non-reasoning) (FP4) | 262k | Open | 18* | -- | 164 | 0.64 | 3.68 | -- | ||
Qwen3.5 122B A10B (Non-reasoning) | 262k | Open | 18* | -- | 145 | 2.34 | 5.79 | -- | ||
Muse Glimmer (high) | 131k | Open | 17 | $0.09 | 99 | 0.76 | 25.98 | 20.18 | ||
Muse Glimmer (high) | 131k | Open | 17 | $0.05 | 134 | 0.83 | 19.42 | 14.87 | ||
Muse Glimmer (high) | 131k | Open | 17 | $0.06 | 63 | 1.14 | 40.77 | 31.71 | ||
Claude 4.5 Haiku | 200k | Proprietary | 17 | $0.20 | 103 | 10.36 | 15.22 | -- | ||
Claude 4.5 Haiku Vertex | 200k | Proprietary | 17 | $0.24 | 94 | 15.83 | 21.16 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 17 | $0.21 | 90 | 21.02 | 26.56 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 17 | $0.57 | 100 | 17.51 | 22.53 | -- | ||
Gemma 4 26B A4B | 1M | Open | 17* | -- | 102 | 1.06 | 25.50 | 19.55 | ||
Gemma 4 26B A4B | 262k | Open | 17* | -- | 118 | 1.62 | 22.72 | 16.88 | ||
Gemma 4 26B A4B AI Studio | 262k | Open | 17* | -- | 47 | 0.97 | 54.32 | 42.68 | ||
Gemma 4 26B A4B | 256k | Open | 17* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | Open | 17* | -- | 30 | 0.98 | 84.46 | 66.78 | ||
Gemma 4 26B A4B | 256k | Open | 17* | -- | 32 | 2.59 | 79.76 | 61.73 | ||
Gemma 4 26B A4B (FP8) | 1.05M | Open | 17* | -- | -- | -- | -- | -- | ||
Ring-2.6-1T | 262k | Open | 17 | $0.29 | 130 | 3.67 | 22.86 | 15.35 | ||
Qwen3.5 122B A10B (FP8) | 262k | Open | 16 | $0.21 | 56 | 1.60 | 46.31 | 35.77 | ||
Qwen3.5 122B A10B (FP4) | 262k | Open | 16 | $0.14 | 168 | 0.60 | 15.44 | 11.88 | ||
Qwen3.5 122B A10B | 262k | Open | 16 | $0.32 | 127 | 2.37 | 22.00 | 15.71 | ||
Qwen3.5 122B A10B (FP8) | 262k | Open | 16 | $0.32 | -- | -- | -- | -- | ||
Qwen3.5 122B A10B | 262k | Open | 16 | $0.32 | 102 | 1.94 | 26.42 | 19.58 | ||
GPT-5.6 Luna (Non-reasoning) | 1M | Proprietary | 16 | $0.01 | 151 | 0.83 | 4.14 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 1M | Proprietary | 16 | $0.06 | 238 | 0.71 | 2.80 | -- | ||
Claude 4.5 Haiku (Non-reasoning) | 200k | Proprietary | 15* | -- | 88 | 1.16 | 6.82 | -- | ||
Claude 4.5 Haiku (Non-reasoning) | 200k | Proprietary | 15* | -- | 101 | 0.80 | 5.76 | -- | ||
Claude 4.5 Haiku (Non-reasoning) | 200k | Proprietary | 15* | -- | 88 | 0.67 | 6.36 | -- | ||
Claude 4.5 Haiku (Non-reasoning) Vertex | 200k | Proprietary | 15* | -- | 89 | 0.83 | 6.47 | -- | ||
Ling 3.0 Tiny | 262k | Open | 15* | -- | 57 | 3.18 | 47.14 | 35.17 | ||
Qwen3.6 35B A3B (Non-reasoning) | 262k | Open | 15* | -- | 165 | 1.17 | 4.20 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) (FP8) | 262k | Open | 15* | -- | 84 | 0.79 | 6.74 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) | 205k | Open | 15* | -- | 128 | 1.48 | 5.39 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) FP8 | 262k | Open | 15* | -- | -- | -- | -- | -- | ||
Qwen3.6 35B A3B (Non-reasoning) (FP8) | 262k | Open | 15* | -- | 82 | 0.88 | 6.96 | -- | ||
Qwen3.6 35B A3B (Non-reasoning) | 262k | Open | 15* | -- | 124 | 2.23 | 6.27 | -- | ||
Granite 4.2 30B | 131k | Open | 15* | -- | 73 | 0.89 | 35.16 | 27.41 | ||
Mistral Medium 3.5 | 262k | Open | 14 | $0.44 | 138 | 2.26 | 20.36 | 14.48 | ||
Gemma 4 12B | 262k | Open | 14* | -- | 113 | 2.37 | 24.55 | 17.75 | ||
Nova 2.0 Pro Preview (medium) | 256k | Proprietary | 14* | -- | 115 | 14.66 | 36.45 | 17.44 | ||
Gemma 4 31B (Non-reasoning) (NVFP4) | 262k | Open | 14* | -- | -- | -- | -- | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Open | 14* | -- | 72 | 1.24 | 8.15 | -- | ||
Gemma 4 31B (Non-reasoning) | 131k | Open | 14* | -- | -- | -- | -- | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Open | 14* | -- | 86 | 1.87 | 7.69 | -- | ||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | Open | 14* | -- | -- | -- | -- | -- | ||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | Open | 14* | -- | 51 | 3.42 | 13.24 | -- | ||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | Open | 14* | -- | 23 | 1.66 | 23.74 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Open | 14* | -- | 33 | 2.51 | 17.49 | -- | ||
Gemma 4 31B (Non-reasoning) | 131k | Open | 14* | -- | -- | -- | -- | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Open | 14* | -- | 15 | 2.45 | 36.25 | -- | ||
Gemma 4 31B (Non-reasoning) | 262k | Open | 14* | -- | 22 | 2.14 | 24.97 | -- | ||
Mercury 2 | 128k | Proprietary | 14* | -- | 655 | 4.72 | 5.48 | -- | ||
Qwen3.5 9B (FP8) | 262k | Open | 14* | -- | 43 | 2.28 | 60.86 | 46.87 | ||
Qwen3.5 9B (FP8) | 262k | Open | 14* | -- | 84 | 0.81 | 30.67 | 23.89 | ||
Nova 2.0 Omni (medium) | 1M | Proprietary | 14* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (medium) | 1M | Proprietary | 14* | -- | -- | -- | -- | -- | ||
Apriel-v1.6-15B-Thinker | 131k | Open | 13* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietary | 13* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietary | 13* | -- | 163 | 13.31 | 28.67 | 12.28 | ||
Qwen3.5 9B (Non-reasoning) (FP8) | 262k | Open | 13* | -- | 92 | 0.75 | 6.20 | -- | ||
Command A+ | 200k | Open | 13 | $0.00 | 234 | 0.41 | 11.08 | 8.54 | ||
Gemma 4 26B A4B (Non-reasoning) | 1M | Open | 13* | -- | 85 | 1.06 | 6.93 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 262k | Open | 13* | -- | 24 | 1.85 | 22.77 | -- | ||
Gemma 4 26B A4B (Non-reasoning) (FP8) | 1.05M | Open | 13* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (Non-reasoning) (FP8) | 262k | Open | 13* | -- | 79 | 2.28 | 8.62 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 262k | Open | 13* | -- | 203 | 0.85 | 3.32 | -- | ||
Gemma 4 26B A4B (Non-reasoning) (FP8) | 262k | Open | 13* | -- | 30 | 0.84 | 17.74 | -- | ||
Gemma 4 26B A4B (Non-reasoning) | 262k | Open | 13* | -- | 94 | 1.50 | 6.84 | -- | ||
Qwen3.5 4B (FP8) | 262k | Open | 13* | -- | 20 | 0.78 | 124.00 | 98.57 | ||
Nemotron 3.5 Lightning (NVFP4) | 262k | Open | 13 | $0.12 | -- | -- | -- | -- | ||
Nemotron 3.5 Lightning (BF16) | 1.05M | Open | 13 | $0.09 | 270 | 1.09 | 10.34 | 7.40 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Open | 13 | $0.10 | 171 | 0.61 | 15.22 | 11.69 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Open | 13 | $0.12 | 83 | 11.91 | 41.97 | 24.05 | ||
Nemotron 3.5 Lightning (BF16) | 65.5k | Open | 13 | $0.00 | -- | -- | -- | -- | ||
Nemotron 3.5 Lightning (BF16) | 262k | Open | 13 | $0.02 | 430 | 0.47 | 6.29 | 4.65 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Open | 13 | $0.08 | 300 | 0.42 | 8.76 | 6.68 | ||
Nemotron 3 Super (FP8) | 262k | Open | 13 | $1.14 | 161 | 0.60 | 16.10 | 12.41 | ||
Nemotron 3 Super | 256k | Open | 13 | $1.64 | 222 | 1.70 | 12.95 | 9.00 | ||
Nemotron 3 Super | 262k | Open | 13 | $0.48 | -- | -- | -- | -- | ||
Nova 2.0 Pro Preview (low) | 256k | Proprietary | 13* | -- | 112 | 11.24 | 33.47 | 17.79 | ||
Nova 2.0 Lite (medium) | 1M | Proprietary | 12* | -- | 160 | 14.06 | 29.71 | 12.52 | ||
Qwen3.5 Omni Flash | 256k | Proprietary | 12* | -- | 246 | 1.97 | 4.00 | -- | ||
Nova 2.0 Lite (low) | 1M | Proprietary | 12* | -- | 157 | 8.74 | 24.63 | 12.71 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.08 | 476 | 0.70 | 5.96 | 4.21 | ||
gpt-oss-120b (high) | 116k | Open | 12 | $0.23 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | Open | 12 | $0.12 | 172 | 1.30 | 15.82 | 11.62 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.02 | 65 | 1.37 | 39.66 | 30.63 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.11 | 294 | 0.83 | 9.34 | 6.80 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.04 | 129 | 0.98 | 20.30 | 15.46 | ||
gpt-oss-120b (high) (Turbo) | 131k | Open | 12 | $0.11 | 352 | 0.74 | 7.84 | 5.68 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.04 | 268 | 0.35 | 9.68 | 7.46 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.03 | 47 | 0.65 | 54.03 | 42.70 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.23 | 1,768 | 0.49 | 1.91 | 1.13 | ||
gpt-oss-120b (high) Vertex | 131k | Open | 12 | $0.06 | 165 | 0.52 | 15.65 | 12.10 | ||
gpt-oss-120b (high) | 128k | Open | 12 | $0.07 | 259 | 0.26 | 9.92 | 7.72 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.15 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.06 | 148 | 0.87 | 17.73 | 13.49 | ||
gpt-oss-120b (high) (Base) | 128k | Open | 12 | $0.11 | 290 | 1.12 | 9.73 | 6.89 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.19 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.11 | 97 | 1.12 | 26.77 | 20.52 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.11 | 160 | 0.48 | 16.11 | 12.50 | ||
Mistral Small 4 | 256k | Open | 11 | $0.05 | 155 | 0.73 | 16.84 | 12.89 | ||
Qwen3 Next 80B A3B (Reasoning) | 262k | Open | 11* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B (Reasoning) Vertex | 262k | Open | 11* | -- | 159 | 0.66 | 16.39 | 12.58 | ||
Qwen3 Next 80B A3B (Reasoning) | 262k | Open | 11* | -- | 175 | 2.30 | 16.56 | 11.41 | ||
Qwen3 Next 80B A3B (Reasoning) | 262k | Open | 11* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (low) | 1M | Proprietary | 11* | -- | -- | -- | -- | -- | ||
Granite 4.2 8B | 131k | Open | 11 | $0.06 | 69 | 0.80 | 37.28 | 29.18 | ||
Granite 4.2 8B | 131k | Open | 11 | $0.02 | 89 | 0.87 | 29.00 | 22.50 | ||
G9v3-3B | 131k | Open | 11* | -- | -- | -- | -- | -- | ||
Trinity Large Thinking | 262k | Open | 11 | $0.35 | 303 | 1.35 | 9.60 | 6.60 | ||
Qwen3.5 4B (Non-reasoning) FP8 | 262k | Open | 11* | -- | 14 | 0.87 | 37.67 | -- | ||
Nemotron 3 Nano Omni 30B A3B | 262k | Open | 10* | -- | 269 | 0.49 | 9.79 | 7.44 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) Base | 128k | Open | 10* | -- | 284 | 1.05 | 9.86 | 7.05 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 269 | 0.36 | 9.65 | 7.44 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) Vertex | 131k | Open | 10* | -- | 165 | 0.45 | 15.59 | 12.11 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 48 | 0.63 | 53.25 | 42.09 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 53 | 1.36 | 48.44 | 37.66 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 1,719 | 0.49 | 1.95 | 1.16 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 309 | 0.79 | 8.89 | 6.48 | ||
gpt-oss-120b (low) | 128k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 128k | Open | 10* | -- | 246 | 0.25 | 10.40 | 8.12 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 112 | 1.06 | 23.48 | 17.93 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 139 | 0.87 | 18.83 | 14.37 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 164 | 0.48 | 15.75 | 12.22 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 474 | 0.73 | 6.01 | 4.22 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 109 | 0.96 | 23.87 | 18.33 | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 10* | -- | 99 | 0.84 | 5.90 | -- | ||
Llama 4 Maverick (FP8) | 128k | Open | 10* | -- | 490 | 1.33 | 2.35 | -- | ||
Llama 4 Maverick | 128k | Open | 10* | -- | 210 | 0.75 | 3.13 | -- | ||
Llama 4 Maverick | 1.05M | Open | 10* | -- | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 10* | -- | 95 | 0.52 | 5.79 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 10* | -- | 56 | 0.98 | 9.91 | -- | ||
Nova 2.0 Pro Preview (Non-reasoning) | 256k | Proprietary | 10* | -- | 103 | 0.97 | 5.82 | -- | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | 920 | 0.80 | 3.52 | 2.17 | ||
gpt-oss-20b (low) | 128k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | 152 | 0.66 | 17.11 | 13.16 | ||
gpt-oss-20b (low) | 128k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | 216 | 10.28 | 21.84 | 9.25 | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | 91 | 1.24 | 28.63 | 21.91 | ||
gpt-oss-20b (low) Vertex | 131k | Open | 10* | -- | 372 | 0.47 | 7.19 | 5.38 | ||
North Mini Code | 256k | Open | 10 | $0.00 | 98 | 0.37 | 25.77 | 20.32 | ||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Open | 10* | -- | 298 | 0.61 | 2.29 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | 99 | 0.93 | 6.00 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | 164 | 0.70 | 3.75 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | 174 | 0.88 | 3.75 | -- | ||
Qwen3 Next 80B A3B | 131k | Open | 10* | -- | 184 | 1.73 | 4.44 | -- | ||
Qwen3 Next 80B A3B | 131k | Open | 10* | -- | 175 | 2.18 | 5.04 | -- | ||
Gemma 4 12B (Non-reasoning) | 262k | Open | 9* | -- | 112 | 2.37 | 6.82 | -- | ||
Mistral Large 3 | 256k | Open | 9 | $0.10 | 199 | 1.08 | 3.59 | -- | ||
Mistral Large 3 | 256k | Open | 9 | $0.10 | 95 | 1.41 | 6.68 | -- | ||
Mistral Large 3 | 262k | Open | 9 | $0.10 | 75 | 1.01 | 7.70 | -- | ||
Qwen3 Coder Next | 128k | Open | 9 | $0.78 | 99 | 0.95 | 6.01 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 9 | $0.12 | 65 | 1.08 | 8.79 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 9 | $0.78 | -- | -- | -- | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 9 | $0.33 | 171 | 2.68 | 5.60 | -- | ||
Nova Premier | 1M | Proprietary | 9* | -- | -- | -- | -- | -- | ||
Granite 4.2 3B | 131k | Open | 9 | $0.01 | 222 | 0.43 | 11.71 | 9.02 | ||
Llama Nemotron Super 49B v1.5 | 131k | Open | 9* | -- | 161 | 3.58 | 19.13 | 12.44 | ||
Mistral Small 4 (Non-reasoning) | 262k | Open | 9* | -- | 151 | 0.72 | 4.03 | -- | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | 171 | 0.64 | 15.30 | 11.73 | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | 113 | 39.96 | 62.07 | 17.69 | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | 123 | 0.53 | 20.84 | 16.25 | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | Open | 9 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | Open | 9 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | 91 | 1.24 | 28.58 | 21.87 | ||
gpt-oss-20b (high) Vertex | 131k | Open | 9 | $0.01 | 394 | 0.53 | 6.88 | 5.08 | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.02 | 950 | 0.78 | 3.42 | 2.10 | ||
Gemma 4 E4B | 262k | Open | 9* | -- | 46 | 0.85 | 55.37 | 43.62 | ||
Nemotron 3 Nano | 262k | Open | 9 | $0.02 | 108 | 1.15 | 24.30 | 18.52 | ||
Nemotron 3 Nano (FP4) | 262k | Open | 9 | $0.02 | 304 | 1.00 | 9.22 | 6.57 | ||
Nemotron 3 Nano | 262k | Open | 9 | $0.02 | 102 | 11.76 | 36.19 | 19.55 | ||
Sarvam 105B (high) | 128k | Open | 9* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (Non-reasoning) | 1M | Proprietary | 9* | -- | 149 | 1.00 | 4.35 | -- | ||
Devstral 2 | 262k | Open | 9 | $0.00 | 132 | 2.28 | 6.07 | -- | ||
Magistral Small 1.2 | 128k | Open | 9* | -- | 99 | 1.16 | 26.40 | 20.19 | ||
LFM2.5-2.6B | 32.8k | Open | 8* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (Non-reasoning) | 1M | Proprietary | 8* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 328k | Open | 8* | -- | 42 | 0.73 | 12.59 | -- | ||
Llama 4 Scout | 128k | Open | 8* | -- | 105 | 0.96 | 5.73 | -- | ||
Llama 4 Scout Vertex | 1.31M | Open | 8* | -- | 152 | 0.71 | 4.01 | -- | ||
Llama 4 Scout | 131k | Open | 8* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 128k | Open | 8* | -- | 162 | 0.76 | 3.85 | -- | ||
Llama 4 Scout | 131k | Open | 8* | -- | 38 | 1.15 | 14.18 | -- | ||
Qwen3 Omni 30B A3B (Reasoning) | 65.5k | Open | 8* | -- | 100 | 2.00 | 27.12 | 20.09 | ||
Llama 3.3 70B | 131k | Open | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B Vertex | 128k | Open | 8* | -- | 148 | 0.64 | 4.01 | -- | ||
Llama 3.3 70B | 131k | Open | 8* | -- | 265 | 0.82 | 2.71 | -- | ||
Llama 3.3 70B | 131k | Open | 8* | -- | 43 | 1.77 | 13.47 | -- | ||
Llama 3.3 70B (FP8) | 131k | Open | 8* | -- | 67 | 2.71 | 10.13 | -- | ||
Llama 3.3 70B | 128k | Open | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B | 128k | Open | 8* | -- | 81 | 0.92 | 7.11 | -- | ||
Llama 3.3 70B Turbo | 131k | Open | 8* | -- | 69 | 1.68 | 8.95 | -- | ||
Llama 3.3 70B | 128k | Open | 8* | -- | 112 | 2.33 | 6.79 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | Open | 8* | -- | 16 | 2.39 | 33.49 | -- | ||
Llama 3.3 70B | 24k | Open | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B | 128k | Open | 8* | -- | 123 | 1.11 | 5.20 | -- | ||
Llama 3.3 70B | 100k | Open | 8* | -- | 80 | 1.34 | 7.63 | -- | ||
Devstral Small 2 | 256k | Open | 8 | $0.00 | 131 | 2.29 | 6.10 | -- | ||
ERNIE 4.5 300B A47B | 131k | Open | 8* | -- | -- | -- | -- | -- | ||
Hermes 4 405B (FP8) | 128k | Open | 7* | -- | 40 | 2.40 | 64.51 | 49.69 | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | Open | 7* | -- | 134 | 5.61 | 24.28 | 14.93 | ||
Gemma 4 E4B (Non-reasoning) | 262k | Open | 7* | -- | 45 | 0.78 | 11.94 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Open | 7* | -- | 115 | 7.88 | 29.54 | 17.33 | ||
Hermes 4 405B (Non-reasoning) (FP8) | 128k | Open | 7* | -- | 41 | 2.36 | 14.47 | -- | ||
Llama Nemotron Super 49B v1.5 (Non-reasoning) | 131k | Open | 7* | -- | 123 | 4.34 | 8.39 | -- | ||
LFM2.5-8B-A1B | 32.8k | Open | 7* | -- | -- | -- | -- | -- | ||
Ring-flash-2.0 | 131k | Open | 7* | -- | -- | -- | -- | -- | ||
Olmo 3.1 32B Think | 65.5k | Open | 7* | -- | -- | -- | -- | -- | ||
Command A | 288k | Open | 7* | -- | 60 | 1.77 | 10.04 | -- | ||
Command A | 256k | Open | 7* | -- | 43 | 3.15 | 14.79 | -- | ||
Llama 3.1 Nemotron 70B | 131k | Open | 7* | -- | 163 | 4.40 | 7.46 | -- | ||
Nemotron 3 Nano (Non-reasoning) (FP4) | 262k | Open | 7* | -- | 316 | 0.99 | 2.58 | -- | ||
Nemotron 3 Nano (Non-reasoning) | 262k | Open | 7* | -- | 109 | 0.70 | 5.30 | -- | ||
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 131k | Open | 7* | -- | 112 | 7.61 | 12.06 | -- | ||
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 131k | Open | 7* | -- | 168 | 1.11 | 4.09 | -- | ||
Sarvam 30B (high) | 64k | Open | 7* | -- | -- | -- | -- | -- | ||
Celeris-1 | 131k | Proprietary | 6 | $0.05 | 1,541 | 0.60 | 0.92 | -- | ||
Phi-4 Mini | 128k | Open | 6* | -- | 46 | 0.86 | 11.80 | -- | ||
Granite 4.0 H Small | 128k | Open | 6* | -- | 24 | 21.16 | 41.94 | -- | ||
Ministral 3 14B | 262k | Open | 6 | $0.14 | 89 | 0.88 | 6.49 | -- | ||
Ministral 3 14B | 256k | Open | 6 | $0.14 | 241 | 0.89 | 2.96 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | Open | 6* | -- | 95 | 1.90 | 7.19 | -- | ||
Phi-4 | 16.4k | Open | 6* | -- | 30 | 2.79 | 19.47 | -- | ||
Phi-4 | 16.4k | Open | 6* | -- | 69 | 0.99 | 8.22 | -- | ||
Nova Micro | 130k | Proprietary | 6* | -- | 252 | 0.84 | 2.83 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | 128k | Open | 6* | -- | 200 | 1.08 | 3.58 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) (FP8) | 131k | Open | 6* | -- | 141 | 4.64 | 8.19 | -- | ||
Phi-4 Multimodal | 128k | Open | 6* | -- | 17 | 0.84 | 30.13 | -- | ||
Reka Flash 3 | 54k | Open | 6* | -- | -- | -- | -- | -- | ||
Ministral 3 8B | 256k | Open | 5 | $0.07 | 292 | 0.90 | 2.61 | -- | ||
Ministral 3 8B | 262k | Open | 5 | $0.07 | 80 | 0.82 | 7.03 | -- | ||
Llama 3.2 11B (Vision) | 131k | Open | 5* | -- | 18 | 1.77 | 29.83 | -- | ||
Olmo 3 7B | 65.5k | Open | 5* | -- | -- | -- | -- | -- | ||
Apertus 70B Instruct | 64k | Open | 5* | -- | -- | -- | -- | -- | ||
Ministral 3 3B | 256k | Open | 5 | $0.04 | 426 | 0.91 | 2.08 | -- | ||
Ministral 3 3B | 131k | Open | 5 | $0.04 | 225 | 0.71 | 2.94 | -- | ||
LFM2.5-VL-1.6B | 32.8k | Open | 5* | -- | -- | -- | -- | -- | ||
Tiny Aya Global | 8.19k | Open | 5* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | Open | 5* | -- | -- | -- | -- | -- | ||
Cogito v2.1 | 164k | Open | -- | -- | -- | -- | -- | -- | ||