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 Opus 5 (max) | 1M | Proprietary | 63 | $2.34 | 54 | 47.52 | 56.77 | -- | ||
Claude Opus 5 (max) | 1M | Proprietary | 63 | $2.34 | 55 | 51.81 | 60.90 | -- | ||
Claude Opus 5 (max) | 1M | Proprietary | 63 | $3.31 | 57 | 52.94 | 61.73 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietary | 63 | $1.80 | 55 | 23.46 | 32.63 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietary | 63 | $2.51 | 55 | 22.94 | 32.02 | -- | ||
Claude Opus 5 (xhigh) | 1M | Proprietary | 63 | $1.80 | 58 | 32.81 | 41.40 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietary | 62 | $3.14 | 68 | 94.09 | 101.44 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietary | 62 | $3.32 | 72 | 109.18 | 116.09 | -- | ||
Claude Fable 5 (with fallback) | 1M | Proprietary | 62 | $10.16 | 73 | 128.01 | 134.84 | -- | ||
Claude Opus 5 (high) | 1M | Proprietary | 61 | $1.23 | 56 | 20.64 | 29.59 | -- | ||
Claude Opus 5 (high) | 1M | Proprietary | 61 | $1.67 | 57 | 18.34 | 27.07 | -- | ||
Claude Opus 5 (high) | 1M | Proprietary | 61 | $1.23 | 56 | 12.09 | 21.00 | -- | ||
GPT-5.6 Sol (max) | 262k | Proprietary | 61 | $1.66 | 116 | 112.29 | 116.59 | -- | ||
GPT-5.6 Sol (max) | 1M | Proprietary | 61 | $1.23 | 62 | 132.01 | 140.02 | -- | ||
Kimi K3 (max) | 1.05M | Open | 60 | $0.84 | 39 | 3.13 | 67.36 | 51.38 | ||
Kimi K3 (max) | 1.05M | Open | 60 | $0.89 | 152 | 1.17 | 17.67 | 13.20 | ||
Kimi K3 (max) | 1.05M | Open | 60 | $1.24 | 160 | 1.94 | 17.54 | 12.48 | ||
Kimi K3 (max) | 1M | Open | 60 | $1.43 | 87 | 0.92 | 29.62 | 22.96 | ||
Kimi K3 (max) | 1.05M | Open | 60 | $1.01 | 45 | 2.42 | 58.45 | 44.82 | ||
Kimi K3 (max) | 1.05M | Open | 60 | $1.26 | 121 | 1.64 | 22.27 | 16.51 | ||
Kimi K3 (max) | 1.05M | Open | 60 | $0.78 | 133 | 2.16 | 21.02 | 15.09 | ||
Kimi K3 (max) | 1.05M | Open | 60 | $0.66 | 57 | 1.54 | 45.47 | 35.15 | ||
Kimi K3 (max) | 1.05M | Open | 60 | $3.11 | 122 | 1.63 | 22.18 | 16.45 | ||
Kimi K3 (max) (FAST) | 1M | Open | 60 | $1.27 | 111 | 0.93 | 23.40 | 17.98 | ||
GPT-5.6 Sol (xhigh) | 1M | Proprietary | 59 | $0.81 | 64 | 50.15 | 58.01 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietary | 59 | $0.72 | 55 | 5.85 | 14.98 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietary | 59 | $0.72 | 55 | 5.69 | 14.85 | -- | ||
Claude Opus 5 (medium) | 1M | Proprietary | 59 | $0.95 | 54 | 4.62 | 13.82 | -- | ||
Qwen3.8 Max | 1M | Proprietary | 58 | $1.13 | 71 | 2.62 | 38.06 | 28.36 | ||
GPT-5.6 Sol (high) | 1M | Proprietary | 57 | $0.55 | 61 | 12.87 | 21.03 | -- | ||
Muse Spark 1.2 (xhigh) | 1.05M | Proprietary | 57 | $0.40 | -- | -- | -- | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietary | 57 | $0.51 | 129 | 168.93 | 172.80 | -- | ||
GPT-5.6 Terra (max) | 262k | Proprietary | 57 | $0.97 | 153 | 123.20 | 126.47 | -- | ||
Grok 4.5 (high) | 500k | Proprietary | 56 | $0.36 | 58 | 7.86 | 16.45 | -- | ||
GPT-5.6 Sol (medium) | 1M | Proprietary | 56 | $0.37 | 58 | 5.68 | 14.25 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 55 | $2.22 | 77 | 198.56 | 205.03 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 55 | $1.64 | 82 | 190.64 | 196.73 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 55 | $1.72 | 71 | 195.66 | 202.65 | -- | ||
Claude Sonnet 5 (max) | 1M | Proprietary | 55 | $1.96 | 75 | 146.91 | 153.58 | -- | ||
GPT-5.6 Terra (xhigh) | 1M | Proprietary | 53 | $0.31 | 115 | 13.71 | 18.04 | -- | ||
GLM-5.2 (max) | 205k | Open | 53 | $0.36 | 143 | 7.20 | 24.74 | 14.03 | ||
GLM-5.2 (max) | 1M | Open | 53 | $0.42 | 223 | 1.41 | 12.62 | 8.96 | ||
GLM-5.2 (max) (NVFP4) | 1M | Open | 53 | $0.48 | 240 | 0.90 | 11.31 | 8.33 | ||
GLM-5.2 (max) (FP8) | 1.05M | Open | 53 | $0.42 | 41 | 2.78 | 63.60 | 48.65 | ||
GLM-5.2 (max) | 261k | Open | 53 | $0.46 | 130 | 1.73 | 20.90 | 15.33 | ||
GLM-5.2 (max) (NVFP4) | 1M | Open | 53 | -- | 171 | 1.38 | 16.01 | 11.70 | ||
GLM-5.2 (max) | 262k | Open | 53 | $0.38 | 181 | 1.46 | 15.27 | 11.05 | ||
GLM-5.2 (max) (FP4) | 1.05M | Open | 53 | $0.25 | 46 | 1.38 | 56.17 | 43.83 | ||
GLM-5.2 (max) (FP4) | 432k | Open | 53 | $1.06 | 281 | 1.13 | 10.02 | 7.11 | ||
GLM-5.2 (max) | 1.05M | Open | 53 | $0.44 | 182 | 1.52 | 15.24 | 10.98 | ||
GLM-5.2 (max) | 262k | Open | 53 | $1.57 | 64 | 1.96 | 41.10 | 31.31 | ||
GLM-5.2 (max) (NVFP4) | 1M | Open | 53 | $0.36 | 189 | 4.66 | 17.87 | 10.57 | ||
GLM-5.2 (max) | 1M | Open | 53 | $0.48 | 65 | 0.97 | 39.29 | 30.66 | ||
GLM-5.2 (max) (FP8) | 1.05M | Open | 53 | -- | -- | -- | -- | -- | ||
GLM-5.2 (max) (FP8) | 1.05M | Open | 53 | $0.62 | 64 | 1.78 | 40.94 | 31.33 | ||
Claude Opus 5 (low) | 1M | Proprietary | 52 | $0.43 | 57 | 3.84 | 12.68 | -- | ||
Claude Opus 5 (low) | 1M | Proprietary | 52 | $0.43 | 56 | 3.12 | 12.11 | -- | ||
Claude Opus 5 (low) | 1M | Proprietary | 52 | $0.55 | 58 | 2.77 | 11.41 | -- | ||
GPT-5.6 Luna (max) | 1M | Proprietary | 52 | $0.05 | 183 | 84.22 | 86.96 | -- | ||
GPT-5.6 Luna (max) | 262k | Proprietary | 52 | $0.34 | 258 | 78.63 | 80.56 | -- | ||
DeepSeek V4 Flash 0731 (max) | 1M | Open | 52 | $0.03 | 113 | 1.15 | 23.31 | 17.73 | ||
DeepSeek V4 Flash 0731 (max) | 1M | Open | 52 | $0.06 | 75 | 0.93 | 34.14 | 26.57 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Open | 52 | $0.13 | 75 | 1.46 | 34.86 | 26.72 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Open | 52 | $0.08 | 152 | 0.92 | 17.39 | 13.18 | ||
DeepSeek V4 Flash 0731 (max) | 1.05M | Open | 52 | $0.09 | 114 | 1.38 | 23.31 | 17.55 | ||
DeepSeek V4 Flash 0731 (max) | 1M | Open | 52 | $0.20 | 201 | 0.76 | 13.22 | 9.96 | ||
Gemini 3.6 Flash AI Studio | 1M | Proprietary | 52 | $0.56 | 218 | 19.41 | 21.71 | -- | ||
GPT-5.6 Sol (low) | 1M | Proprietary | 51 | $0.23 | 62 | 3.53 | 11.64 | -- | ||
GPT-5.6 Terra (high) | 1M | Proprietary | 50 | $0.22 | 115 | 2.58 | 6.93 | -- | ||
GPT-5.6 Luna (xhigh) | 1M | Proprietary | 50 | $0.03 | 179 | 36.09 | 38.89 | -- | ||
Kimi K3 (low) | 1.05M | Open | 48 | $0.24 | 43 | 3.38 | 61.75 | 46.70 | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | Proprietary | 48 | $0.33 | 133 | 31.34 | 35.10 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | Proprietary | 48 | $0.43 | 127 | 41.83 | 45.78 | -- | ||
GPT-5.6 Luna (high) | 1M | Proprietary | 47 | $0.02 | 181 | 8.68 | 11.44 | -- | ||
GPT-5.6 Terra (medium) | 1M | Proprietary | 47 | $0.12 | 113 | 1.65 | 6.08 | -- | ||
Gemini 3.5 Flash (medium) | 1M | Proprietary | 47* | -- | 189 | 18.96 | 21.60 | -- | ||
GPT-5.3 Codex (xhigh) | 400k | Proprietary | 46* | -- | 126 | 77.22 | 81.19 | -- | ||
MiniMax-M3 (MXFP8) | 1M | Open | 45 | $0.18 | 61 | 1.32 | 42.53 | 32.97 | ||
MiniMax-M3 | 262k | Open | 45 | $0.11 | 301 | 1.15 | 9.45 | 6.64 | ||
MiniMax-M3 | 1M | Open | 45 | $0.21 | 61 | 1.01 | 41.74 | 32.58 | ||
MiniMax-M3 | 1M | Open | 45 | $0.13 | 110 | 1.48 | 24.26 | 18.23 | ||
MiniMax-M3 | 524k | Open | 45 | $0.13 | 32 | 1.01 | 80.35 | 63.47 | ||
MiniMax-M3 (FP8) | 1.05M | Open | 45 | $0.45 | 203 | 1.94 | 14.26 | 9.86 | ||
MiniMax-M3 (FP8) | 1M | Open | 45 | $0.12 | 81 | 1.87 | 32.91 | 24.83 | ||
MiniMax-M3 | 512k | Open | 45 | $0.14 | 109 | 1.69 | 24.64 | 18.36 | ||
MiniMax-M3 | 1.05M | Open | 45 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) (FP4) | 1.05M | Open | 45 | $0.27 | 41 | 1.67 | 121.32 | 107.38 | ||
DeepSeek V4 Pro (max) | 1M | Open | 45 | $0.89 | 81 | 1.59 | 61.82 | 54.05 | ||
DeepSeek V4 Pro (max) | 1.05M | Open | 45 | $0.23 | 61 | 1.87 | 81.77 | 71.71 | ||
DeepSeek V4 Pro (max) | 1M | Open | 45 | $0.75 | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) (FP8) | 1.05M | Open | 45 | $0.31 | 53 | 1.76 | 93.78 | 82.58 | ||
DeepSeek V4 Pro (max) | 1.05M | Open | 45 | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro (max) | 1M | Open | 45 | $0.90 | 86 | 1.37 | 58.37 | 51.15 | ||
DeepSeek V4 Pro (max) | 1.05M | Open | 45 | $0.38 | 71 | 1.41 | 70.42 | 61.93 | ||
DeepSeek V4 Pro (max) | 1M | Open | 45 | $0.05 | 64 | 1.71 | 77.32 | 67.85 | ||
DeepSeek V4 Pro (high) (FP4) | 65.5k | Open | 44 | $0.26 | 35 | 1.61 | 72.83 | 56.93 | ||
DeepSeek V4 Pro (high) | 1.05M | Open | 44 | $0.36 | 164 | 1.41 | 16.56 | 12.11 | ||
DeepSeek V4 Pro (high) | 1M | Open | 44 | $0.94 | 87 | 1.52 | 30.11 | 22.85 | ||
DeepSeek V4 Pro (high) | 1M | Open | 44 | $0.04 | 57 | 1.70 | 45.44 | 34.96 | ||
DeepSeek V4 Pro (high) (FP8) | 1.05M | Open | 44 | $0.29 | 52 | 1.73 | 49.76 | 38.39 | ||
DeepSeek V4 Pro (high) | 1M | Open | 44 | $0.94 | 71 | 1.48 | 36.39 | 27.91 | ||
DeepSeek V4 Pro (high) | 1M | Open | 44 | $0.78 | -- | -- | -- | -- | ||
DeepSeek V4 Pro (high) | 1.05M | Open | 44 | $0.20 | 58 | 1.89 | 44.57 | 34.12 | ||
DeepSeek V4 Pro (high) | 131k | Open | 44 | $0.68 | 143 | 0.60 | 18.02 | 13.93 | ||
Kimi K2.7 Code (FP4) | 256k | Open | 43 | $0.64 | 205 | 1.77 | 15.09 | 10.88 | ||
Kimi K2.7 Code (FP8) | 65.5k | Open | 43 | $0.46 | 42 | 6.12 | 71.21 | 53.17 | ||
Kimi K2.7 Code | 262k | Open | 43 | $0.28 | 320 | 1.15 | 9.67 | 6.96 | ||
Kimi K2.7 Code | 262k | Open | 43 | $0.18 | 81 | 1.31 | 35.03 | 27.54 | ||
Kimi K2.7 Code | 262k | Open | 43 | $0.30 | 264 | 0.47 | 10.81 | 8.44 | ||
Kimi K2.7 Code | 262k | Open | 43 | $0.23 | 39 | 3.82 | 73.40 | 56.83 | ||
Kimi K2.7 Code | 262k | Open | 43 | $0.18 | 85 | 0.65 | 32.61 | 26.10 | ||
Kimi K2.7 Code | 256k | Open | 43 | $0.22 | 39 | 2.92 | 73.41 | 57.57 | ||
MiMo-V2.5-Pro | 1.05M | Open | 43 | $0.04 | 56 | 1.95 | 46.43 | 35.58 | ||
MiMo-V2.5-Pro | 1.05M | Open | 43 | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | Open | 43 | $0.18 | 123 | 0.92 | 21.18 | 16.21 | ||
MiMo-V2.5-Pro | 1M | Open | 43 | $0.03 | 74 | 2.80 | 36.66 | 27.09 | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietary | 43 | $0.42 | 64 | 1.78 | 9.61 | -- | ||
Claude Sonnet 5 (Non-reasoning) | 1M | Proprietary | 43 | $0.61 | 64 | 1.95 | 9.77 | -- | ||
Inkling (FP8) | 131k | Open | 42 | $0.43 | 112 | 0.72 | 22.94 | 17.78 | ||
Inkling | 524k | Open | 42 | $0.62 | 82 | 0.61 | 30.96 | 24.28 | ||
Inkling | 262k | Open | 42 | $0.34 | 77 | 1.81 | 34.08 | 25.82 | ||
Hy3 (FP8) | 256k | Open | 42 | $0.03 | 69 | 2.82 | 39.15 | 29.06 | ||
Hy3 | 262k | Open | 42 | $0.04 | 66 | 2.80 | 40.90 | 30.48 | ||
Hy3 (FP8) | 262k | Open | 42 | $0.04 | 57 | 0.60 | 44.23 | 34.90 | ||
Hy3 | 262k | Open | 42 | $0.03 | 71 | 4.09 | 39.28 | 28.15 | ||
GPT-5.6 Sol (Non-reasoning) | 1M | Proprietary | 42 | $0.24 | 58 | 1.15 | 9.83 | -- | ||
GPT-5.6 Sol (Non-reasoning) | 262k | Proprietary | 42 | $0.30 | 99 | 8.11 | 13.17 | -- | ||
Nex-N2-Pro (FP8) | 262k | Open | 42 | -- | 129 | 1.63 | 21.02 | 15.51 | ||
GPT-5.6 Terra (low) | 1M | Proprietary | 41 | $0.09 | 120 | 1.47 | 5.65 | -- | ||
Inkling Small | 256k | Open | 41 | $0.07 | 145 | 1.59 | 18.84 | 13.81 | ||
Inkling Small | 524k | Open | 41 | $0.15 | 165 | 0.74 | 15.92 | 12.14 | ||
Agnes 2.5 Pro Alpha | 1M | Proprietary | 40 | -- | 129 | 2.61 | 21.92 | 15.45 | ||
Qwen3.7 Plus | 1M | Proprietary | 39 | $0.24 | 57 | 2.44 | 46.65 | 35.37 | ||
GPT-5.6 Luna (medium) | 1M | Proprietary | 39 | $0.01 | 180 | 2.38 | 5.16 | -- | ||
Nemotron 3 Ultra | 262k | Open | 38 | $0.16 | 237 | 1.13 | 12.83 | 9.59 | ||
Nemotron 3 Ultra | 262k | Open | 38 | -- | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 512k | Open | 38 | $0.40 | 142 | 0.69 | 20.21 | 16.01 | ||
Nemotron 3 Ultra | 262k | Open | 38 | $0.23 | 72 | 6.06 | 44.74 | 31.71 | ||
Nemotron 3 Ultra BF16 | 262k | Open | 38 | -- | 68 | 4.30 | 45.03 | 33.39 | ||
Nemotron 3 Ultra | 256k | Open | 38 | $0.60 | 262 | 2.21 | 12.81 | 8.69 | ||
Nemotron 3 Ultra | 262k | Open | 38 | $0.25 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Open | 38 | $0.22 | -- | -- | -- | -- | ||
MiMo-V2.5 | 1.05M | Open | 38 | $0.01 | 86 | 4.60 | 33.83 | 23.38 | ||
MiMo-V2.5 | 1M | Open | 38 | $0.04 | 70 | 1.67 | 37.24 | 28.46 | ||
MiMo-V2.5 | 262k | Open | 38 | $0.08 | 44 | 1.10 | 58.14 | 45.63 | ||
MiMo-V2.5 | 1.05M | Open | 38 | $0.02 | -- | -- | -- | -- | ||
MiMo-V2.5 | 1M | Open | 38 | $0.01 | 90 | 3.02 | 30.69 | 22.13 | ||
Ling 3.0 Flash | 131k | Open | 38 | $0.04 | 350 | 0.83 | 7.97 | 5.71 | ||
Ling 3.0 Flash | 262k | Open | 38 | $0.04 | 363 | 1.98 | 8.86 | 5.51 | ||
Qwen3.6 27B FP8 | 262k | Open | 38 | $0.19 | 49 | 1.21 | 127.15 | 115.74 | ||
Qwen3.6 27B | 131k | Open | 38 | $0.27 | 465 | 1.11 | 14.38 | 12.20 | ||
Qwen3.6 27B | 262k | Open | 38 | $0.29 | 58 | 3.05 | 110.06 | 98.35 | ||
Qwen3.6 27B | 262k | Open | 38 | $0.29 | 53 | 3.75 | 120.74 | 107.52 | ||
Qwen3.6 27B (FP8) | 262k | Open | 38 | $0.19 | 41 | 3.57 | 153.30 | 137.61 | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | Proprietary | 37 | $0.10 | 379 | 9.33 | 10.65 | -- | ||
Grok 4.3 (medium) | 524k | Proprietary | 37* | -- | 143 | 10.44 | 13.94 | -- | ||
Grok 4.3 (medium) | 200k | Proprietary | 37* | -- | 146 | 9.33 | 12.75 | -- | ||
Grok 4.3 (medium) | 1M | Proprietary | 37* | -- | 125 | 11.94 | 15.95 | -- | ||
Grok 4.3 (low) | 524k | Proprietary | 36* | -- | 143 | 4.85 | 8.35 | -- | ||
Grok 4.3 (low) | 200k | Proprietary | 36* | -- | 156 | 5.52 | 8.71 | -- | ||
Grok 4.3 (low) | 1M | Proprietary | 36* | -- | 122 | 5.96 | 10.05 | -- | ||
Gemini 3.5 Flash (minimal) AI Studio | 1M | Proprietary | 36* | -- | 166 | 1.01 | 4.02 | -- | ||
Claude Sonnet 4.6 (Non-reasoning, Low Effort) | 1M | Proprietary | 35* | -- | 43 | 1.89 | 13.60 | -- | ||
GLM-5.2 (FP4) | 432k | Open | 35 | -- | 287 | 1.16 | 2.90 | -- | ||
GLM-5.2 | 262k | Open | 35 | -- | 50 | 1.94 | 11.89 | -- | ||
GLM-5.2 | 205k | Open | 35 | -- | 207 | 5.96 | 8.37 | -- | ||
GLM-5.2 (FP8) | 1.05M | Open | 35 | -- | 59 | 1.64 | 10.09 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 1M | Proprietary | 35 | $0.10 | 111 | 0.78 | 5.29 | -- | ||
GPT-5.6 Terra (Non-reasoning) | 262k | Proprietary | 35 | $0.20 | 133 | 0.82 | 4.58 | -- | ||
Qwen3.5 397B A17B | 256k | Open | 34 | $0.36 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.36 | 80 | 2.17 | 48.39 | 39.94 | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.12 | 83 | 2.08 | 46.31 | 38.23 | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.23 | 85 | 1.07 | 44.20 | 37.28 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 34 | $0.23 | 101 | 2.10 | 38.42 | 31.39 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 34 | $0.19 | 51 | 0.99 | 73.12 | 62.35 | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.12 | 13 | 1.59 | 290.30 | 249.55 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 34 | $0.36 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Open | 34 | $0.36 | 134 | 2.05 | 29.56 | 23.78 | ||
Qwen3.5 397B A17B | 262k | Open | 34 | $0.36 | 82 | 1.47 | 46.33 | 38.77 | ||
LongCat 2.0 (FP8) | 1M | Open | 34 | $0.12 | 41 | 3.08 | 64.42 | 49.08 | ||
KAT-Coder-Pro V2 | 256k | Proprietary | 34 | -- | 107 | 1.83 | 6.50 | -- | ||
KAT-Coder-Pro V2 | 256k | Proprietary | 34 | -- | -- | -- | -- | -- | ||
GPT-5.6 Luna (low) | 1M | Proprietary | 34 | $0.01 | 167 | 2.09 | 5.09 | -- | ||
Qwen3.5 122B A10B (FP8) | 262k | Open | 33 | $0.16 | 56 | 1.99 | 46.83 | 35.88 | ||
Qwen3.5 122B A10B (FP4) | 262k | Open | 33 | $0.12 | 171 | 0.64 | 15.29 | 11.72 | ||
Qwen3.5 122B A10B | 262k | Open | 33 | $0.25 | 125 | 2.65 | 22.65 | 16.00 | ||
Qwen3.5 122B A10B (FP8) | 262k | Open | 33 | $0.25 | -- | -- | -- | -- | ||
Qwen3.5 122B A10B | 262k | Open | 33 | $0.25 | 106 | 1.84 | 25.52 | 18.94 | ||
Qwen3.5 397B A17B | 262k | Open | 33* | -- | 82 | 2.15 | 8.23 | -- | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 33* | -- | 44 | 1.05 | 12.31 | -- | ||
Qwen3.5 397B A17B | 262k | Open | 33* | -- | 82 | 2.18 | 8.24 | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Open | 33* | -- | 135 | 2.03 | 5.73 | -- | ||
Qwen3.5 397B A17B | 262k | Open | 33* | -- | 12 | 4.20 | 47.44 | -- | ||
Qwen3.5 397B A17B | 262k | Open | 33* | -- | 78 | 1.38 | 7.76 | -- | ||
Qwen3.6 35B A3B | 229k | Open | 32 | $0.19 | 119 | 2.50 | 52.19 | 45.47 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 32 | $0.17 | 88 | 2.21 | 68.86 | 61.00 | ||
Qwen3.6 35B A3B | 262k | Open | 32 | $0.23 | 111 | 0.96 | 53.87 | 48.43 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 32 | $0.09 | 35 | 0.69 | 169.77 | 154.74 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 32 | $0.47 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B FP8 | 262k | Open | 32 | $0.19 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | Open | 32 | $0.08 | 100 | 1.25 | 60.25 | 53.99 | ||
Qwen3.6 35B A3B | 205k | Open | 32 | $0.19 | 129 | 1.55 | 47.27 | 41.84 | ||
DeepSeek V4 Pro | 1M | Open | 32* | -- | 89 | 1.65 | 7.24 | -- | ||
DeepSeek V4 Pro | 1.05M | Open | 32* | -- | 68 | 1.50 | 8.86 | -- | ||
DeepSeek V4 Pro | 1M | Open | 32* | -- | -- | -- | -- | -- | ||
DeepSeek V4 Pro | 1M | Open | 32* | -- | 54 | 1.58 | 10.82 | -- | ||
G9v3-39A5B | 131k | Open | 31 | $0.00 | -- | -- | -- | -- | ||
Qwen3.5 Omni Plus | 256k | Proprietary | 31* | -- | 49 | 2.39 | 12.64 | -- | ||
Qwen3.6 27B | 131k | Open | 31 | $0.39 | 475 | 0.98 | 2.03 | -- | ||
Qwen3.6 27B FP8 | 262k | Open | 31 | $0.23 | 51 | 1.07 | 10.90 | -- | ||
Qwen3.6 27B | 262k | Open | 31 | $0.40 | 62 | 3.79 | 11.84 | -- | ||
Qwen3.6 27B | 262k | Open | 31 | $0.40 | 60 | 3.01 | 11.27 | -- | ||
Ring-2.6-1T | 262k | Open | 31 | $0.37 | -- | -- | -- | -- | ||
o3 | 200k | Proprietary | 31* | -- | 108 | 45.49 | 50.13 | -- | ||
o3 | 200k | Proprietary | 31* | -- | -- | -- | -- | -- | ||
o3 | 200k | Proprietary | 31* | -- | 127 | 8.69 | 12.64 | -- | ||
Step 3.7 Flash | 256k | Open | 31 | $0.09 | 377 | 0.97 | 7.60 | 5.31 | ||
Step 3.7 Flash | 256k | Open | 31 | -- | 197 | 0.57 | 13.23 | 10.13 | ||
Mistral Medium 3.5 | 262k | Open | 30 | $0.46 | 143 | 1.75 | 19.22 | 13.98 | ||
Claude 4.5 Haiku | 200k | Proprietary | 30 | $0.24 | 125 | 12.58 | 16.57 | -- | ||
Claude 4.5 Haiku Vertex | 200k | Proprietary | 30 | $0.25 | 96 | 13.86 | 19.08 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 30 | $0.22 | 96 | 10.06 | 15.29 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 30 | $0.54 | 96 | 10.00 | 15.22 | -- | ||
Gemma 4 31B | 262k | Open | 30 | -- | 36 | 1.96 | 64.77 | 48.76 | ||
Gemma 4 31B (FP8) | 262k | Open | 30 | $0.04 | -- | -- | -- | -- | ||
Gemma 4 31B | 262k | Open | 30 | $0.04 | -- | -- | -- | -- | ||
Gemma 4 31B | 131k | Open | 30 | $0.25 | 1,489 | 1.02 | 2.52 | 1.17 | ||
Gemma 4 31B (AI Studio) | 262k | Open | 30 | $0.00 | 35 | 1.17 | 64.71 | 49.34 | ||
Gemma 4 31B | 262k | Open | 30 | $0.03 | 42 | 4.07 | 57.35 | 41.37 | ||
Gemma 4 31B | 262k | Open | 30 | $0.01 | 18 | 2.83 | 130.14 | 98.84 | ||
Gemma 4 31B (FP8) | 262k | Open | 30 | $0.03 | 50 | 3.84 | 48.58 | 34.74 | ||
Gemma 4 31B | 131k | Open | 30 | $0.10 | 200 | 2.70 | 13.90 | 8.70 | ||
Gemma 4 31B | 256k | Open | 30 | $0.04 | 150 | 2.11 | 17.05 | 11.60 | ||
Gemma 4 31B | 131k | Open | 30 | $0.04 | 145 | 0.81 | 16.25 | 11.99 | ||
Gemma 4 31B (FP8) | 262k | Open | 30 | $0.10 | 52 | 1.32 | 44.45 | 33.48 | ||
DeepSeek V4 Flash | 1.05M | Open | 29* | -- | -- | -- | -- | -- | ||
DeepSeek V4 Flash | 1M | Open | 29* | -- | 224 | 0.65 | 2.88 | -- | ||
DeepSeek V4 Flash | 1M | Open | 29* | -- | 71 | 1.60 | 8.61 | -- | ||
GPT-5.5 Instant (June 2026) | 400k | Proprietary | 29 | $0.54 | 164 | 1.08 | 16.30 | 12.18 | ||
MiMo-V2.5-Pro | 1.05M | Open | 28* | -- | -- | -- | -- | -- | ||
MiMo-V2.5-Pro | 65.5k | Open | 28* | -- | 119 | 0.88 | 5.08 | -- | ||
MiMo-V2.5-Pro | 131k | Open | 28* | -- | 69 | 3.68 | 10.93 | -- | ||
MiMo-V2.5-Pro | 1.05M | Open | 28* | -- | 54 | 1.88 | 11.07 | -- | ||
Qwen3.5 122B A10B (FP4) | 262k | Open | 28 | $0.10 | 190 | 0.67 | 3.30 | -- | ||
Qwen3.5 122B A10B | 262k | Open | 28 | $0.20 | 137 | 2.61 | 6.25 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 1M | Proprietary | 27 | $0.01 | 166 | 0.83 | 3.84 | -- | ||
GPT-5.6 Luna (Non-reasoning) | 262k | Proprietary | 27 | $0.09 | 236 | 0.66 | 2.78 | -- | ||
Gemma 4 26B A4B | 1M | Open | 26 | $0.02 | 169 | 0.98 | 15.73 | 11.80 | ||
Gemma 4 26B A4B | 262k | Open | 26 | $0.04 | 32 | 1.46 | 79.27 | 62.25 | ||
Gemma 4 26B A4B AI Studio | 262k | Open | 26 | $0.00 | 46 | 1.18 | 55.04 | 43.08 | ||
Gemma 4 26B A4B | 256k | Open | 26 | $0.03 | 96 | 1.40 | 27.32 | 20.73 | ||
Gemma 4 26B A4B | 262k | Open | 26 | $0.03 | 34 | 0.64 | 73.62 | 58.39 | ||
Gemma 4 26B A4B | 256k | Open | 26 | $0.03 | 45 | 1.97 | 58.02 | 44.84 | ||
Gemma 4 26B A4B | 256k | Open | 26 | $0.20 | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 1.05M | Open | 26 | $0.04 | -- | -- | -- | -- | ||
Nemotron 3 Super | 262k | Open | 26 | $0.23 | 137 | 0.97 | 19.16 | 14.56 | ||
Nemotron 3 Super | 256k | Open | 26 | $0.33 | 272 | 1.83 | 11.01 | 7.35 | ||
Nemotron 3 Super | 262k | Open | 26 | $0.10 | 63 | 26.48 | 66.13 | 31.73 | ||
Grok 4.3 (Non-reasoning) | 524k | Proprietary | 25 | $0.91 | 159 | 0.99 | 4.12 | -- | ||
Grok 4.3 (Non-reasoning) | 1M | Proprietary | 25 | $0.29 | 110 | 0.72 | 5.27 | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 25 | $1.20 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | Open | 25 | $0.49 | 112 | 0.93 | 5.40 | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 25 | $0.29 | 35 | 0.84 | 14.97 | -- | ||
Qwen3.6 35B A3B | 205k | Open | 25 | $0.42 | 167 | 1.53 | 4.52 | -- | ||
Qwen3.6 35B A3B FP8 | 262k | Open | 25 | $0.42 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 25 | $0.15 | 92 | 1.40 | 6.81 | -- | ||
Qwen3.6 35B A3B | 262k | Open | 25 | $0.63 | 144 | 2.44 | 5.92 | -- | ||
Ling 3.0 Tiny | 262k | Proprietary | 25 | $0.00 | 378 | 1.35 | 7.97 | 5.29 | ||
Ling 3.0 Tiny | 262k | Proprietary | 25 | $0.00 | 184 | 1.86 | 15.43 | 10.86 | ||
Qwen3.5 35B A3B FP8 | 262k | Open | 24 | $0.07 | 144 | 0.49 | 3.97 | -- | ||
Qwen3.5 35B A3B | 262k | Open | 24 | $0.24 | 172 | 2.10 | 5.01 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 24* | -- | 87 | 1.34 | 7.08 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 24* | -- | 107 | 1.04 | 5.72 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 24* | -- | 86 | 1.06 | 6.86 | -- | ||
Claude 4.5 Haiku Vertex | 200k | Proprietary | 24* | -- | 88 | 0.64 | 6.34 | -- | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.06 | 473 | 0.69 | 5.97 | 4.23 | ||
gpt-oss-120b (high) | 116k | Open | 24 | $0.15 | 101 | 0.94 | 25.66 | 19.78 | ||
gpt-oss-120b (high) | 128k | Open | 24 | $0.08 | 152 | 1.14 | 17.63 | 13.19 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.02 | 45 | 0.62 | 56.33 | 44.57 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.02 | 34 | 1.40 | 74.31 | 58.33 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.07 | 303 | 0.84 | 9.10 | 6.61 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.03 | 104 | 1.03 | 25.12 | 19.27 | ||
gpt-oss-120b (high) (Turbo) | 131k | Open | 24 | $0.07 | 164 | 0.71 | 15.94 | 12.18 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.15 | 1,882 | 0.52 | 1.85 | 1.06 | ||
gpt-oss-120b (high) Vertex | 131k | Open | 24 | $0.04 | 408 | 0.39 | 6.52 | 4.90 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.04 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | Open | 24 | $0.05 | 171 | 0.28 | 14.91 | 11.70 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.10 | 706 | 0.96 | 4.51 | 2.83 | ||
gpt-oss-120b (high) | 131k | Open | 24 | -- | 148 | 0.87 | 17.79 | 13.54 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-120b (high) (Base) | 128k | Open | 24 | $0.07 | 105 | 1.06 | 24.78 | 18.97 | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.11 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | Open | 24 | $0.07 | 84 | 1.04 | 30.91 | 23.90 | ||
Command A+ | 200k | Open | 23 | $0.00 | 193 | 0.40 | 13.32 | 10.34 | ||
Gemma 4 12B | 262k | Open | 22 | $0.08 | 39 | 2.50 | 67.19 | 51.75 | ||
Gemma 4 31B | 262k | Open | 22 | $0.03 | 39 | 3.73 | 16.49 | -- | ||
Gemma 4 31B | 131k | Open | 22 | $0.28 | 1,313 | 1.04 | 1.42 | -- | ||
Gemma 4 31B | 262k | Open | 22 | $0.04 | 141 | 1.74 | 5.29 | -- | ||
Gemma 4 31B (FP8) | 262k | Open | 22 | $0.11 | 59 | 1.21 | 9.74 | -- | ||
Gemma 4 31B (FP8) | 262k | Open | 22 | $0.04 | 54 | 3.01 | 12.20 | -- | ||
Gemma 4 31B (FP8) | 262k | Open | 22 | $0.04 | 12 | 2.53 | 45.81 | -- | ||
Gemma 4 31B | 131k | Open | 22 | $0.11 | 202 | 2.68 | 5.16 | -- | ||
Gemma 4 31B | 262k | Open | 22 | $0.04 | 8 | 2.81 | 64.67 | -- | ||
Nova 2.0 Pro Preview (medium) | 256k | Proprietary | 22 | $0.18 | 122 | 14.61 | 35.14 | 16.42 | ||
Mercury 2 | 128k | Proprietary | 22 | $0.08 | 816 | 3.92 | 4.53 | -- | ||
Qwen3.5 9B (FP8) | 262k | Open | 22 | $0.18 | 61 | 2.43 | 43.66 | 32.99 | ||
Qwen3.5 9B (FP8) | 262k | Open | 22 | $0.30 | 88 | 0.80 | 29.15 | 22.67 | ||
Qwen3 Coder Next | 128k | Open | 21 | $0.47 | 160 | 1.01 | 4.12 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 21 | $0.08 | 77 | 1.03 | 7.52 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 21 | $0.47 | -- | -- | -- | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 21 | $0.21 | 170 | 2.80 | 5.74 | -- | ||
Nova 2.0 Omni (medium) | 1M | Proprietary | 21* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (medium) | 1M | Proprietary | 21* | -- | -- | -- | -- | -- | ||
Apriel-v1.6-15B-Thinker | 131k | Open | 21* | -- | -- | -- | -- | -- | ||
Qwen3.5 9B (FP8) | 262k | Open | 21* | -- | 98 | 0.81 | 5.89 | -- | ||
Gemma 4 26B A4B | 1M | Open | 20* | -- | 178 | 0.99 | 3.81 | -- | ||
Gemma 4 26B A4B | 262k | Open | 20* | -- | 27 | 2.09 | 20.53 | -- | ||
Gemma 4 26B A4B (FP8) | 1.05M | Open | 20* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | Open | 20* | -- | 116 | 2.14 | 6.47 | -- | ||
Gemma 4 26B A4B | 256k | Open | 20* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B | 262k | Open | 20* | -- | 145 | 0.91 | 4.37 | -- | ||
Gemma 4 26B A4B (FP8) | 262k | Open | 20* | -- | 26 | 0.61 | 19.52 | -- | ||
Gemma 4 26B A4B | 262k | Open | 20* | -- | 34 | 3.20 | 18.00 | -- | ||
Qwen3.5 4B (FP8) | 262k | Open | 20* | -- | 38 | 0.69 | 66.84 | 52.92 | ||
North Mini Code | 256k | Open | 20 | $0.00 | 21 | 0.60 | 118.14 | 94.03 | ||
Nova 2.0 Pro Preview (low) | 256k | Proprietary | 20 | $0.23 | 128 | 10.44 | 29.99 | 15.64 | ||
Mistral Small 4 | 256k | Open | 20 | $0.10 | 163 | 1.01 | 16.37 | 12.29 | ||
Devstral 2 | 262k | Open | 19 | $0.00 | 47 | 1.42 | 12.00 | -- | ||
Nova 2.0 Lite (medium) | 1M | Proprietary | 19* | -- | 168 | 16.48 | 31.32 | 11.87 | ||
Qwen3.5 Omni Flash | 256k | Proprietary | 19* | -- | 252 | 1.84 | 3.83 | -- | ||
Trinity Large Thinking | 262k | Open | 19 | $0.20 | 238 | 1.34 | 11.84 | 8.40 | ||
Trinity Large Thinking (FP8) | 262k | Open | 19 | $0.08 | 190 | 1.03 | 14.17 | 10.51 | ||
Nova 2.0 Lite (high) | 1M | Proprietary | 18 | $0.24 | -- | -- | -- | -- | ||
Nova 2.0 Lite (high) | 1M | Proprietary | 18 | $0.24 | 164 | 14.52 | 29.73 | 12.17 | ||
HyperNova 60B 2605 | 131k | Open | 18 | $0.02 | 399 | 0.74 | 7.01 | 5.02 | ||
Magistral Medium 1.2 | 131k | Proprietary | 18 | $0.89 | 67 | 2.37 | 39.68 | 29.85 | ||
Nova 2.0 Lite (low) | 1M | Proprietary | 18* | -- | 163 | 7.84 | 23.17 | 12.26 | ||
Devstral Small 2 | 256k | Open | 18 | $0.00 | 96 | 2.16 | 7.36 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 17 | $0.05 | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Open | 17 | $0.04 | 151 | 0.78 | 17.37 | 13.28 | ||
Qwen3 Next 80B A3B | 262k | Open | 17 | $0.19 | 204 | 2.29 | 14.57 | 9.82 | ||
Qwen3 Next 80B A3B (FP8) | 262k | Open | 17 | $0.04 | 94 | 1.16 | 27.87 | 21.36 | ||
Qwen3 Next 80B A3B | 262k | Open | 17 | $0.03 | -- | -- | -- | -- | ||
Nova 2.0 Omni (low) | 1M | Proprietary | 17* | -- | -- | -- | -- | -- | ||
G9v3-3B | 131k | Open | 16 | $0.00 | -- | -- | -- | -- | ||
Qwen3.5 4B FP8 | 262k | Open | 16* | -- | 33 | 0.72 | 16.04 | -- | ||
Mistral Large 3 | 256k | Open | 16 | $0.08 | 200 | 1.14 | 3.63 | -- | ||
Mistral Large 3 | 256k | Open | 16 | $0.08 | 60 | 1.85 | 10.25 | -- | ||
Mistral Large 3 | 262k | Open | 16 | $0.08 | 46 | 1.22 | 12.07 | -- | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.01 | 117 | 0.96 | 22.39 | 17.14 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.03 | 153 | 31.83 | 48.19 | 13.09 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.01 | 113 | 0.47 | 22.59 | 17.70 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.04 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | Open | 15 | $0.02 | 226 | 0.70 | 11.75 | 8.84 | ||
gpt-oss-20b (high) | 128k | Open | 15 | $0.08 | 156 | 0.74 | 16.74 | 12.80 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.02 | 67 | 1.14 | 38.53 | 29.91 | ||
gpt-oss-20b (high) Vertex | 131k | Open | 15 | $0.03 | 245 | 2.24 | 12.45 | 8.17 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.03 | 936 | 0.81 | 3.48 | 2.14 | ||
gpt-oss-20b (high) | 131k | Open | 15 | $0.02 | -- | -- | -- | -- | ||
Nemotron 3 Nano Omni 30B A3B Reasoning | 262k | Open | 15* | -- | -- | -- | -- | -- | ||
Nemotron 3 Nano Omni 30B A3B Reasoning (FP8) | 65.5k | Open | 15* | -- | 324 | 1.02 | 8.74 | 6.17 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.04 | -- | -- | -- | -- | ||
gpt-oss-120b (low) Base | 128k | Open | 15 | $0.02 | 204 | 1.04 | 13.29 | 9.80 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.03 | 731 | 0.96 | 4.38 | 2.73 | ||
gpt-oss-120b (low) Vertex | 131k | Open | 15 | $0.01 | 416 | 0.39 | 6.40 | 4.80 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.0042 | 41 | 1.42 | 62.60 | 48.94 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.05 | 1,824 | 0.57 | 1.94 | 1.10 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.02 | 320 | 0.98 | 8.80 | 6.25 | ||
gpt-oss-120b (low) | 128k | Open | 15 | $0.05 | 92 | 0.97 | 28.03 | 21.65 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 128k | Open | 15 | $0.01 | 163 | 0.28 | 15.66 | 12.30 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.02 | 81 | 1.09 | 31.91 | 24.65 | ||
gpt-oss-120b (low) | 131k | Open | 15 | -- | 115 | 0.86 | 22.68 | 17.46 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.02 | 477 | 0.70 | 5.94 | 4.19 | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | Open | 15 | $0.01 | 101 | 1.05 | 25.77 | 19.78 | ||
NVIDIA Nemotron 3 Nano | 262k | Open | 15 | $0.03 | 341 | 1.06 | 8.39 | 5.87 | ||
NVIDIA Nemotron 3 Nano (FP4) | 262k | Open | 15 | $0.02 | 296 | 6.90 | 15.35 | 6.76 | ||
NVIDIA Nemotron 3 Nano | 262k | Open | 15 | $0.02 | 173 | 3.20 | 17.65 | 11.56 | ||
Solar Pro 3 | 131k | Proprietary | 14 | $0.15 | 144 | 2.32 | 19.64 | 13.86 | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 14 | $0.04 | 72 | 0.89 | 7.80 | -- | ||
Llama 4 Maverick (FP8) | 128k | Open | 14 | $0.03 | 208 | 1.68 | 4.08 | -- | ||
Llama 4 Maverick | 128k | Open | 14 | $0.03 | 232 | 0.79 | 2.94 | -- | ||
Llama 4 Maverick | 131k | Open | 14 | $0.06 | 129 | 1.14 | 5.00 | -- | ||
Llama 4 Maverick | 1.05M | Open | 14 | $0.04 | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 14 | $0.03 | 70 | 0.59 | 7.74 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 14 | $0.03 | 128 | 1.01 | 4.91 | -- | ||
Nova 2.0 Pro Preview | 256k | Proprietary | 14 | $0.26 | 94 | 1.07 | 6.40 | -- | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | 938 | 0.78 | 3.45 | 2.13 | ||
gpt-oss-20b (low) | 128k | Open | 14* | -- | 241 | 0.70 | 11.07 | 8.29 | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | 99 | 0.97 | 26.34 | 20.29 | ||
gpt-oss-20b (low) | 128k | Open | 14* | -- | 145 | 0.78 | 18.01 | 13.79 | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | 131 | 16.24 | 35.33 | 15.27 | ||
gpt-oss-20b (low) | 131k | Open | 14* | -- | 88 | 1.10 | 29.51 | 22.73 | ||
gpt-oss-20b (low) Vertex | 131k | Open | 14* | -- | 201 | 2.44 | 14.87 | 9.94 | ||
Qwen3 Next 80B A3B | 262k | Open | 14* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Open | 14* | -- | 204 | 0.83 | 3.28 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 14* | -- | 181 | 2.43 | 5.18 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 14* | -- | 115 | 0.71 | 5.04 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 14* | -- | 139 | 0.95 | 4.55 | -- | ||
Qwen3 Next 80B A3B | 131k | Open | 14* | -- | 183 | 1.67 | 4.41 | -- | ||
Qwen3 Next 80B A3B | 131k | Open | 14* | -- | 185 | 2.18 | 4.89 | -- | ||
Gemma 4 12B (Non-reasoning) | 262k | Open | 13* | -- | 38 | 2.58 | 15.76 | -- | ||
Nova Premier | 1M | Proprietary | 13* | -- | 33 | 2.85 | 18.18 | -- | ||
Celeris-1 | 131k | Proprietary | 12 | $0.26 | 1,882 | 0.78 | 1.04 | -- | ||
Llama Nemotron Super 49B v1.5 | 131k | Open | 12* | -- | 71 | 6.29 | 41.41 | 28.10 | ||
Gemma 4 E4B | 262k | Open | 12 | $0.01 | 71 | 0.86 | 35.94 | 28.06 | ||
Mistral Small 4 | 262k | Open | 12* | -- | 144 | 0.96 | 4.44 | -- | ||
Sarvam 105B (high) | 128k | Open | 12* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite | 1M | Proprietary | 12* | -- | 165 | 1.14 | 4.18 | -- | ||
Magistral Small 1.2 | 128k | Open | 11 | $0.30 | 75 | 1.56 | 34.75 | 26.56 | ||
Magistral Small 1.2 | 131k | Open | 11 | $0.30 | 129 | 0.83 | 20.17 | 15.47 | ||
Ministral 3 14B | 262k | Open | 11 | $0.16 | 90 | 0.92 | 6.49 | -- | ||
Ministral 3 14B | 256k | Open | 11 | $0.16 | 181 | 1.15 | 3.91 | -- | ||
Nova 2.0 Omni | 1M | Proprietary | 10* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 328k | Open | 10 | $0.01 | 47 | 0.57 | 11.26 | -- | ||
Llama 4 Scout | 128k | Open | 10 | $0.01 | -- | -- | -- | -- | ||
Llama 4 Scout Vertex | 1.31M | Open | 10 | $0.01 | 144 | 0.76 | 4.24 | -- | ||
Llama 4 Scout | 131k | Open | 10 | $0.02 | 59 | 0.70 | 9.19 | -- | ||
Llama 4 Scout | 128k | Open | 10 | $0.01 | 177 | 0.81 | 3.63 | -- | ||
Llama 4 Scout | 131k | Open | 10 | $0.01 | 49 | 0.90 | 11.10 | -- | ||
Llama 4 Scout | 131k | Open | 10 | $0.01 | 446 | 0.70 | 1.82 | -- | ||
Hermes 4 70B (FP8) | 128k | Open | 10* | -- | 89 | 1.45 | 29.61 | 22.53 | ||
Qwen3 Omni 30B A3B | 65.5k | Open | 10* | -- | 101 | 1.96 | 26.69 | 19.78 | ||
Llama 3.3 70B | 131k | Open | 9 | $0.14 | -- | -- | -- | -- | ||
Llama 3.3 70B Vertex | 128k | Open | 9 | $0.11 | 144 | 0.72 | 4.20 | -- | ||
Llama 3.3 70B | 131k | Open | 9 | $0.09 | 325 | 0.93 | 2.47 | -- | ||
Llama 3.3 70B | 131k | Open | 9 | $0.02 | 44 | 1.76 | 13.13 | -- | ||
Llama 3.3 70B (FP8) | 131k | Open | 9 | $0.02 | 48 | 2.70 | 13.15 | -- | ||
Llama 3.3 70B | 128k | Open | 9 | $0.09 | 286 | 2.03 | 3.78 | -- | ||
Llama 3.3 70B Base | 128k | Open | 9 | $0.02 | 13 | 7.66 | 47.66 | -- | ||
Llama 3.3 70B | 128k | Open | 9 | $0.11 | 78 | 0.90 | 7.33 | -- | ||
Llama 3.3 70B Turbo | 131k | Open | 9 | $0.16 | 91 | 1.36 | 6.86 | -- | ||
Llama 3.3 70B | 128k | Open | 9 | $0.11 | 98 | 2.32 | 7.43 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | Open | 9 | $0.02 | 12 | 2.05 | 43.40 | -- | ||
Llama 3.3 70B | 24k | Open | 9 | $0.05 | 57 | 3.69 | 12.41 | -- | ||
Llama 3.3 70B | 128k | Open | 9 | $0.11 | 120 | 1.14 | 5.32 | -- | ||
Llama 3.3 70B | 100k | Open | 9 | $0.16 | 85 | 1.32 | 7.18 | -- | ||
Ministral 3 8B | 256k | Open | 9 | $0.18 | 259 | 0.93 | 2.86 | -- | ||
Ministral 3 8B | 262k | Open | 9 | $0.18 | 112 | 0.75 | 5.22 | -- | ||
Llama Nemotron Ultra Base | 131k | Open | 9* | -- | 53 | 2.38 | 49.97 | 38.07 | ||
ERNIE 4.5 300B A47B | 131k | Open | 9* | -- | -- | -- | -- | -- | ||
Hermes 4 405B (FP8) | 128k | Open | 9* | -- | 35 | 2.43 | 74.89 | 57.97 | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | Open | 9* | -- | 61 | 5.54 | 46.45 | 32.73 | ||
Gemma 4 E4B | 262k | Open | 9* | -- | 68 | 0.95 | 8.31 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Open | 9* | -- | 175 | 4.52 | 18.77 | 11.40 | ||
Hermes 4 405B (FP8) | 128k | Open | 9* | -- | 39 | 2.34 | 15.12 | -- | ||
Llama Nemotron Super 49B v1.5 | 131k | Open | 9* | -- | 75 | 5.35 | 11.99 | -- | ||
LFM2.5-8B-A1B | 32.8k | Open | 8* | -- | 337 | 1.57 | 8.98 | 5.93 | ||
Ring-flash-2.0 | 131k | Open | 8* | -- | -- | -- | -- | -- | ||
Olmo 3.1 32B Think | 65.5k | Open | 8* | -- | -- | -- | -- | -- | ||
Command A | 288k | Open | 7* | -- | 62 | 1.72 | 9.77 | -- | ||
Command A | 256k | Open | 7* | -- | 42 | 3.00 | 14.97 | -- | ||
Llama 3.1 Nemotron 70B | 131k | Open | 7* | -- | 76 | 6.26 | 12.85 | -- | ||
NVIDIA Nemotron 3 Nano (FP4) | 262k | Open | 7* | -- | 213 | 7.59 | 9.93 | -- | ||
NVIDIA Nemotron 3 Nano | 262k | Open | 7* | -- | 175 | 0.40 | 3.26 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Open | 7* | -- | 178 | 4.13 | 6.93 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Open | 7* | -- | 164 | 1.11 | 4.15 | -- | ||
Ministral 3 3B | 256k | Open | 7 | $0.13 | 406 | 0.93 | 2.16 | -- | ||
Ministral 3 3B | 131k | Open | 7 | $0.13 | 218 | 0.60 | 2.90 | -- | ||
Hermes 4 70B (FP8) | 128k | Open | 7* | -- | 86 | 1.41 | 7.21 | -- | ||
Granite 4.1 8B | 131k | Open | 6* | -- | 102 | 0.80 | 5.69 | -- | ||
Sarvam 30B (high) | 64k | Open | 6* | -- | -- | -- | -- | -- | ||
Phi-4 Mini | 128k | Open | 6 | $0.00 | 43 | 0.84 | 12.55 | -- | ||
Jamba 1.7 Large | 256k | Open | 5* | -- | 54 | 1.31 | 10.55 | -- | ||
Granite 4.0 H Small | 128k | Open | 5* | -- | 48 | 10.31 | 20.65 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | Open | 5* | -- | 95 | 1.88 | 7.12 | -- | ||
Phi-4 | 16.4k | Open | 5* | -- | -- | -- | -- | -- | ||
Phi-4 | 16.4k | Open | 5* | -- | 73 | 0.89 | 7.77 | -- | ||
Nova Micro | 130k | Proprietary | 4* | -- | 298 | 0.92 | 2.60 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL | 128k | Open | 4* | -- | 210 | 1.11 | 3.49 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (FP8) | 131k | Open | 4* | -- | 64 | 6.72 | 14.56 | -- | ||
Phi-4 Multimodal | 128k | Open | 4* | -- | 18 | 0.81 | 29.03 | -- | ||
Reka Flash 3 | 54k | Open | 4* | -- | -- | -- | -- | -- | ||
Llama 3.2 11B (Vision) | 131k | Open | 3* | -- | 9 | 3.54 | 59.58 | -- | ||
Olmo 3 7B | 65.5k | Open | 2* | -- | -- | -- | -- | -- | ||
Apertus 70B Instruct | 64k | Open | 2* | -- | -- | -- | -- | -- | ||
LFM2.5-VL-1.6B | 32.8k | Open | 1* | -- | 391 | 0.79 | 2.07 | -- | ||
Tiny Aya Global | 8.19k | Open | 1* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | Open | 1* | -- | -- | -- | -- | -- | ||
Claude Sonnet 5 (low) | 1M | Proprietary | -- | -- | 60 | 2.45 | 10.76 | -- | ||
Claude Sonnet 5 (xhigh) | 1M | Proprietary | -- | -- | 71 | 42.59 | 49.59 | -- | ||
Claude Sonnet 5 (high) | 1M | Proprietary | -- | -- | 65 | 8.40 | 16.09 | -- | ||
Cogito v2.1 | 164k | Open | -- | -- | -- | -- | -- | -- | ||
Claude Sonnet 5 (medium) | 1M | Proprietary | -- | -- | 66 | 3.27 | 10.84 | -- | ||