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 5.5 (max with fallback) | 1M | Proprietary | 58 | $5.98 | 95 | 703.73 | 709.01 | -- | ||
Claude Opus 5.5 (max with fallback) | 1M | Proprietary | 58 | $5.98 | 69 | 1,104.27 | 1,111.54 | -- | ||
Claude Opus 5.5 (max with fallback) | 1M | Proprietary | 58 | $15.80 | 95 | 687.60 | 692.86 | -- | ||
Claude Opus 5.5 (max with fallback) | 1M | Proprietary | 58 | $6.70 | 95 | 734.99 | 740.25 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietary | 56 | $7.67 | 125 | 441.91 | 445.91 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietary | 56 | -- | 132 | 470.61 | 474.39 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietary | 56 | -- | 135 | 490.46 | 494.17 | -- | ||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietary | 56 | $7.19 | 135 | 491.20 | 494.89 | -- | ||
Claude Opus 5.5 (xhigh with fallback) | 1M | Proprietary | 56 | $3.46 | 77 | 136.26 | 142.75 | -- | ||
Claude Opus 5.5 (high with fallback) | 1M | Proprietary | 54 | $1.82 | 73 | 33.37 | 40.22 | -- | ||
Claude Fable 5.1 (max with fallback) | 1M | Proprietary | 53 | $7.63 | 66 | 296.74 | 304.31 | -- | ||
Claude Fable 5.1 (xhigh with fallback) | 1M | Proprietary | 53 | $5.98 | 56 | 70.05 | 79.02 | -- | ||
GPT-6 Astra (max) | 524k | Proprietary | 53 | $3.19 | 63 | 304.78 | 312.73 | -- | ||
GPT-6 Astra (max) | 1M | Proprietary | 53 | $3.26 | 48 | 410.56 | 421.03 | -- | ||
GPT-6 Astra (max) | 524k | Proprietary | 53 | $3.26 | 83 | 282.63 | 288.68 | -- | ||
Gemini 4 Argon (high) AI Studio (1M output) | 1M | Proprietary | 53 | $1.99 | -- | -- | -- | -- | ||
GPT-6 Astra (xhigh) | 1M | Proprietary | 52 | $2.31 | 52 | 189.68 | 199.34 | -- | ||
Claude Sonnet 5.5 (xhigh with fallback) | 1M | Proprietary | 52 | $2.75 | 101 | 35.00 | 39.97 | -- | ||
GPT-6.1 Sol (max) | 1M | Proprietary | 52 | $0.72 | 56 | 326.94 | 335.94 | -- | ||
GPT-6.1 Sol (max) | 1M | Proprietary | 52 | -- | -- | -- | -- | -- | ||
GPT-6.1 Sol (max) | 1.05M | Proprietary | 52 | $0.70 | 77 | 306.74 | 313.22 | -- | ||
Claude Opus 5.5 (medium with fallback) | 1M | Proprietary | 51 | $1.34 | 75 | 22.00 | 28.71 | -- | ||
Claude Fable 5.1 (high with fallback) | 1M | Proprietary | 51 | $3.91 | 56 | 24.61 | 33.57 | -- | ||
GPT-6.1 Sol (xhigh) | 1M | Proprietary | 51 | $0.39 | 55 | 133.22 | 142.30 | -- | ||
GPT-6 Astra (high) | 1M | Proprietary | 51 | $1.73 | 50 | 83.11 | 93.07 | -- | ||
GPT-6.1 Sol (high) | 1M | Proprietary | 50 | $0.32 | 52 | 46.35 | 56.00 | -- | ||
GPT-6 Astra (medium) | 1M | Proprietary | 50 | $1.54 | 49 | 4.46 | 14.76 | -- | ||
Claude Fable 5.1 (medium with fallback) | 1M | Proprietary | 49 | $2.98 | 53 | 6.35 | 15.75 | -- | ||
Muse Spark 1.3 (max) | 1.05M | Proprietary | 48 | $1.60 | 209 | 54.81 | 66.74 | 9.55 | ||
GPT-6.1 Sol (medium) | 1M | Proprietary | 48 | $0.21 | 50 | 6.17 | 16.16 | -- | ||
Claude Fable 5.1 (low with fallback) | 1M | Proprietary | 47 | $2.37 | 54 | 3.87 | 13.06 | -- | ||
Claude Sonnet 5.5 (high with fallback) | 1M | Proprietary | 47 | $1.12 | 99 | 11.94 | 16.98 | -- | ||
Grok 4.7 (xhigh) | 500k | Proprietary | 46 | $3.74 | 73 | 35.72 | 42.60 | -- | ||
Grok 4.7 (high) | 500k | Proprietary | 46 | $2.73 | 81 | 87.05 | 93.25 | -- | ||
MiMo-V2.6-Pro | 1M | Open | 46 | $0.13 | 40 | 5.48 | 68.38 | 50.32 | ||
MiMo-V2.6-Pro | 1M | Open | 46 | $0.96 | 32 | 1.61 | 80.42 | 63.05 | ||
MiMo-V2.6-Pro | 1.05M | Open | 46 | $0.14 | 193 | 1.12 | 14.05 | 10.35 | ||
MiMo-V2.6-Pro (BF16) | 1M | Open | 46 | $0.12 | 48 | 4.92 | 56.64 | 41.38 | ||
MiMo-V2.6-Pro | 1M | Open | 46 | $0.13 | 38 | 4.27 | 69.87 | 52.49 | ||
GPT-6 Astra (low) | 524k | Proprietary | 46 | $0.79 | 57 | 2.92 | 11.63 | -- | ||
GPT-6 Astra (low) | 1M | Proprietary | 46 | $0.82 | 46 | 2.66 | 13.51 | -- | ||
Qwen3.8 Max (0902) | 984k | Proprietary | 45 | $5.41 | 38 | 2.74 | 68.21 | 52.37 | ||
Muse Spark 1.3 (xhigh) | 1.05M | Proprietary | 45 | $1.37 | 252 | 41.62 | 51.55 | 7.95 | ||
GLM-5.3 (max) | 1M | Open | 45 | $1.97 | 167 | 0.87 | 15.86 | 11.99 | ||
GLM-5.3 (max) | 1M | Open | 45 | $2.01 | 79 | 2.70 | 34.22 | 25.21 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $0.97 | 64 | 1.37 | 40.16 | 31.03 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $2.96 | 183 | 0.69 | 14.32 | 10.90 | ||
GLM-5.3 (max) | 1M | Open | 45 | $1.97 | 149 | 1.10 | 17.82 | 13.38 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $1.97 | 174 | 0.59 | 14.97 | 11.50 | ||
GLM-5.3 (max) (FAST) | 1M | Open | 45 | $4.08 | 437 | 0.86 | 6.58 | 4.58 | ||
GLM-5.3 (max) | 1M | Open | 45 | $2.00 | 56 | 2.88 | 47.39 | 35.62 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $1.43 | 125 | 2.17 | 22.16 | 15.99 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $1.97 | 54 | 0.87 | 46.83 | 36.77 | ||
GLM-5.3 (max) | 1.05M | Open | 45 | $1.90 | 158 | 0.82 | 16.64 | 12.65 | ||
GLM-5.3 (max) | 1M | Open | 45 | $2.73 | 196 | 1.05 | 13.83 | 10.22 | ||
GLM-5.3 (max) | 1M | Open | 45 | $2.01 | 148 | 0.83 | 17.70 | 13.50 | ||
GLM-5.3 (max) (FAST) | 1M | Open | 45 | $3.75 | 241 | 0.57 | 10.94 | 8.29 | ||
GLM-5.3 (max) (FP4) | 1.05M | Open | 45 | $2.35 | 443 | 0.60 | 6.24 | 4.51 | ||
GLM-5.3 (max) (FP4 ULTRA CHAT) | 1.05M | Open | 45 | $5.14 | 555 | 0.58 | 5.08 | 3.60 | ||
GLM-5.3 (max) | 164k | Open | 45 | $2.04 | 137 | 1.90 | 20.19 | 14.63 | ||
GLM-5.3 (max) | 1M | Open | 45 | $4.99 | 137 | 1.56 | 19.80 | 14.60 | ||
GLM-5.3 (max) (FP4) | 786k | Open | 45 | $3.36 | 197 | 0.87 | 13.54 | 10.14 | ||
GLM-5.3 (max) (FP4) | 1M | Open | 45 | $1.19 | 256 | 1.74 | 11.52 | 7.82 | ||
GLM-5.3 (max) | 1M | Open | 45 | $1.81 | 186 | 1.16 | 14.58 | 10.74 | ||
GLM-5.3 (max) (FP4, FAST) | 1M | Open | 45 | $5.29 | 574 | 1.34 | 5.69 | 3.49 | ||
GLM-5.3 (max) (FP4) | 1M | Open | 45 | $8.68 | 276 | 1.48 | 10.53 | 7.24 | ||
GLM-5.3 (max) | 1M | Open | 45 | $1.42 | 79 | 3.92 | 35.59 | 25.34 | ||
GLM-5.3 (max) | 1M | Open | 45 | $4.70 | 119 | 1.59 | 22.57 | 16.78 | ||
Step 5 Preview | 1M | Proprietary | 44 | $0.72 | 90 | 2.83 | 30.69 | 22.29 | ||
Kimi K3 (max) | 205k | Open | 44 | $1.85 | 123 | 0.90 | 21.14 | 16.20 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $1.91 | 112 | 0.97 | 23.33 | 17.89 | ||
Kimi K3 (max) (FAST) | 1.05M | Open | 44 | $2.72 | 111 | 0.98 | 23.55 | 18.05 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $3.48 | 93 | 1.25 | 28.25 | 21.60 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $2.16 | 74 | 0.99 | 34.58 | 26.87 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $1.90 | 42 | 1.19 | 60.03 | 47.07 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $2.42 | 135 | 1.29 | 19.84 | 14.84 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $4.14 | 144 | 1.24 | 18.60 | 13.89 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $1.33 | 86 | 1.16 | 30.36 | 23.36 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $9.22 | 225 | 1.12 | 12.25 | 8.90 | ||
Kimi K3 (max) (ULTRA CHAT) | 1.05M | Open | 44 | $3.93 | 307 | 0.72 | 8.87 | 6.52 | ||
Kimi K3 (max) (FAST) | 1.05M | Open | 44 | $3.77 | 312 | 1.63 | 9.65 | 6.41 | ||
Kimi K3 (max) | 1M | Open | 44 | $1.87 | 141 | 1.73 | 19.43 | 14.16 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $2.00 | 42 | 3.54 | 62.80 | 47.41 | ||
Kimi K3 (max) | 1.05M | Open | 44 | $1.69 | 227 | 0.72 | 11.74 | 8.82 | ||
Kimi K3 (max) (FAST) | 1.05M | Open | 44 | $2.81 | 221 | 0.74 | 12.05 | 9.05 | ||
Kimi K3 (max) (ULTRA) | 1.05M | Open | 44 | $3.93 | 228 | 0.75 | 11.71 | 8.77 | ||
Kimi K3 (max) | 1M | Open | 44 | $1.88 | 93 | 1.49 | 28.51 | 21.61 | ||
Claude Haiku 5.5 (max with fallback) | 1M | Proprietary | 43 | $0.21 | -- | -- | -- | -- | ||
Claude Opus 5.5 (low with fallback) | 1M | Proprietary | 42 | $0.55 | 76 | 8.15 | 14.74 | -- | ||
Claude Opus 5.5 (low with fallback) | 1M | Proprietary | 42 | $0.55 | 56 | 7.62 | 16.51 | -- | ||
Claude Opus 5.5 (low with fallback) | 1M | Proprietary | 42 | $0.84 | 75 | 6.15 | 12.82 | -- | ||
Claude Opus 5.5 (low with fallback) | 1M | Proprietary | 42 | $0.59 | 70 | 8.19 | 15.34 | -- | ||
Grok 4.7 (low) | 500k | Proprietary | 42 | $1.25 | 69 | 5.07 | 12.32 | -- | ||
GPT-6.1 Sol (low) | 1M | Proprietary | 42 | $0.13 | 49 | 3.11 | 13.35 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietary | 42 | $1.40 | 110 | 122.78 | 127.34 | -- | ||
GPT-5.6 Terra (max) | 1M | Proprietary | 42 | $1.95 | 128 | 122.97 | 126.88 | -- | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.88 | 87 | 0.87 | 29.56 | 22.95 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.25 | 51 | 3.28 | 52.10 | 39.06 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.60 | 203 | 0.58 | 12.92 | 9.87 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.29 | 40 | 2.13 | 64.45 | 49.86 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.34 | 39 | 1.17 | 65.38 | 51.37 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.50 | 55 | 1.47 | 46.78 | 36.25 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.45 | 58 | 0.87 | 44.01 | 34.51 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.47 | 108 | 0.62 | 23.69 | 18.45 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.37 | 186 | 1.36 | 14.80 | 10.76 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.28 | 143 | 0.76 | 18.28 | 14.02 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.31 | 54 | 4.03 | 50.10 | 36.85 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.67 | 149 | 1.01 | 17.81 | 13.44 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.14 | 179 | 1.61 | 15.54 | 11.15 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.51 | 158 | 0.97 | 16.82 | 12.69 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $1.19 | 138 | 1.65 | 19.77 | 14.49 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.42 | 38 | 0.90 | 66.13 | 52.18 | ||
GLM-5.3-Flash | 1M | Open | 42 | $0.65 | 152 | 1.60 | 17.99 | 13.12 | ||
GLM-5.3-Flash (FP4) | 1.05M | Open | 42 | $0.81 | 142 | 1.14 | 18.73 | 14.07 | ||
GLM-5.3-Flash (FAST) | 1M | Open | 42 | $0.28 | 703 | 6.45 | 10.00 | 2.84 | ||
GLM-5.3-Flash (FP4) | 1.05M | Open | 42 | $0.29 | 507 | 1.18 | 6.12 | 3.95 | ||
GLM-5.3-Flash (FP4, ULTRA CHAT) | 1.05M | Open | 42 | $0.56 | 807 | 0.43 | 3.52 | 2.48 | ||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.44 | 276 | 0.75 | 9.81 | 7.25 | ||
Claude Haiku 5.5 (xhigh with fallback) | 1M | Proprietary | 41 | $0.12 | -- | -- | -- | -- | ||
Ling 3.1 Flash | 1M | Proprietary | 41 | $0.99 | 211 | 1.76 | 13.59 | 9.46 | ||
Gemini 3.8 Flash (high) AI Studio | 1M | Proprietary | 41 | $1.24 | 129 | 24.33 | 28.21 | -- | ||
Claude Sonnet 5.5 (medium with fallback) | 1M | Proprietary | 41 | $0.59 | 97 | 4.48 | 9.66 | -- | ||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $1.87 | 80 | 1.05 | 32.35 | 25.04 | ||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $2.09 | 122 | 1.15 | 21.64 | 16.39 | ||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $2.89 | 113 | 1.20 | 23.38 | 17.74 | ||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $1.81 | 104 | 0.85 | 24.96 | 19.28 | ||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $2.16 | 38 | 2.77 | 68.81 | 52.84 | ||
Qwen3.8 2.4T A95B | 1M | Open | 40 | $1.96 | 184 | 0.75 | 14.34 | 10.87 | ||
Qwen3.8-Flash-Next | 1M | Open | 40 | $0.37 | 56 | 2.53 | 47.05 | 35.61 | ||
Gemini 3.8 Flash (medium) AI Studio | 1M | Proprietary | 40 | $0.93 | -- | -- | -- | -- | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $3.13 | 365 | 1.33 | 8.18 | 5.48 | ||
DeepSeek V4.1 Flash (max) (FAST) | 1.05M | Open | 39 | $0.27 | 583 | 1.88 | 6.17 | 3.43 | ||
DeepSeek V4.1 Flash (max) (ULTRA) | 1.05M | Open | 39 | $0.38 | 577 | 1.64 | 5.97 | 3.47 | ||
DeepSeek V4.1 Flash (max) (ULTRA CHAT) | 1.05M | Open | 39 | $0.38 | 850 | 0.59 | 3.53 | 2.35 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $1.03 | 216 | 0.87 | 12.45 | 9.27 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.52 | 227 | 0.64 | 11.67 | 8.82 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.27 | 216 | 1.17 | 12.74 | 9.25 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.86 | 152 | 2.05 | 18.49 | 13.15 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.44 | 135 | 2.18 | 20.75 | 14.85 | ||
DeepSeek V4.1 Flash (max) | 524k | Open | 39 | $0.24 | 166 | 1.87 | 16.91 | 12.03 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.44 | 90 | 0.81 | 28.48 | 22.14 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.38 | 161 | 2.14 | 17.62 | 12.38 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $0.28 | 215 | 0.87 | 12.49 | 9.30 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $1.21 | 304 | 0.67 | 8.89 | 6.58 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $0.57 | 95 | 0.79 | 27.12 | 21.07 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.34 | 99 | 1.37 | 26.60 | 20.18 | ||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $1.75 | 73 | 0.76 | 35.03 | 27.42 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $0.32 | 280 | 0.33 | 9.25 | 7.14 | ||
DeepSeek V4.1 Flash (max) (FAST) | 1.05M | Open | 39 | $0.49 | 802 | 1.47 | 4.59 | 2.49 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $0.16 | 345 | 1.86 | 9.11 | 5.80 | ||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $1.11 | 262 | 0.66 | 10.20 | 7.64 | ||
Mistral Large 4 Preview | 524k | Proprietary | 38 | $1.13 | 116 | 1.46 | 23.00 | 17.23 | ||
GPT-6 Luna (max) | 1M | Proprietary | 38 | $0.07 | 128 | 106.02 | 109.93 | -- | ||
GPT-6 Luna (max) | 524k | Proprietary | 38 | -- | 194 | 65.40 | 67.97 | -- | ||
GPT-5.6 Terra (xhigh) | 1M | Proprietary | 38 | $0.63 | 102 | 18.51 | 23.43 | -- | ||
GPT-5.6 Terra (xhigh) | 524k | Proprietary | 38 | $0.67 | 121 | 11.37 | 15.52 | -- | ||
MiMo-V2.6-Flash | 1M | Open | 38 | $0.06 | 58 | 5.47 | 48.75 | 34.62 | ||
MiMo-V2.6-Flash | 1M | Open | 38 | $0.42 | 35 | 1.36 | 72.44 | 56.86 | ||
MiMo-V2.6-Flash | 1M | Open | 38 | $0.06 | 49 | 4.35 | 55.70 | 41.08 | ||
MiMo-V2.6-Flash (BF16) | 524k | Open | 38 | $0.06 | 51 | 4.02 | 53.00 | 39.19 | ||
Claude Haiku 5.5 (high with fallback) | 1M | Proprietary | 38 | $0.08 | -- | -- | -- | -- | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $0.67 | 99 | 1.65 | 26.88 | 20.19 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $1.76 | 69 | 3.60 | 39.87 | 29.02 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $1.45 | 88 | 1.70 | 30.01 | 22.65 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Open | 36 | $0.60 | -- | -- | -- | -- | ||
DeepSeek V4 Pro 0813 (max) | 1M | Open | 36 | $5.51 | 96 | 0.68 | 26.82 | 20.91 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $1.65 | 193 | 1.64 | 14.58 | 10.35 | ||
DeepSeek V4 Pro 0813 (max) | 1M | Open | 36 | $1.00 | 45 | 1.20 | 56.24 | 44.03 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $0.70 | 75 | 2.46 | 35.74 | 26.62 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $1.61 | 50 | 0.84 | 50.47 | 39.70 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $0.51 | 278 | 1.50 | 10.50 | 7.20 | ||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $8.43 | 171 | 2.04 | 16.65 | 11.69 | ||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietary | 36 | $0.42 | 101 | 1.05 | 6.02 | -- | ||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietary | 36 | -- | 102 | 1.35 | 6.23 | -- | ||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietary | 36 | -- | 103 | 1.39 | 6.24 | -- | ||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietary | 36 | $0.40 | 92 | 1.26 | 6.68 | -- | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $0.51 | 129 | 1.12 | 20.48 | 15.49 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $0.31 | 221 | 1.02 | 12.33 | 9.05 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $0.12 | -- | -- | -- | -- | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $0.28 | 218 | 2.44 | 13.89 | 9.16 | ||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $2.51 | 216 | 1.52 | 13.11 | 9.27 | ||
GPT-6 Luna (xhigh) | 1M | Proprietary | 35 | $0.04 | 115 | 25.15 | 29.49 | -- | ||
Claude Haiku 5.5 (medium with fallback) | 1M | Proprietary | 34 | $0.05 | -- | -- | -- | -- | ||
GLM-5.3 (low) | 1M | Open | 34 | $0.85 | 80 | 2.94 | 34.29 | 25.08 | ||
GLM-5.3 (low) (FP4) | 1M | Open | 34 | $0.50 | 226 | 1.82 | 12.85 | 8.83 | ||
GLM-5.3 (low) (FP4, FAST) | 1M | Open | 34 | $2.24 | 595 | 1.35 | 5.55 | 3.36 | ||
GLM-5.3 (low) | 1M | Open | 34 | $2.11 | 132 | 1.42 | 20.43 | 15.21 | ||
GLM-5.3 (low) | 1.05M | Open | 34 | $0.84 | 57 | 0.82 | 44.52 | 34.96 | ||
GPT-5.6 Terra (high) | 1M | Proprietary | 34 | $0.34 | 92 | 2.73 | 8.19 | -- | ||
GPT-5.6 Terra (high) | 524k | Proprietary | 34 | $0.35 | 116 | 2.41 | 6.73 | -- | ||
Qwen3.8 27B (xhigh) | 262k | Open | 34 | $0.52 | 36 | 0.96 | 71.35 | 56.31 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | Open | 34 | $0.92 | 62 | 1.67 | 41.74 | 32.06 | ||
Qwen3.8 27B (xhigh) | 1M | Open | 34 | $1.01 | 47 | 3.85 | 56.68 | 42.27 | ||
Qwen3.8 27B (xhigh) (FP8) | 262k | Open | 34 | $0.60 | 69 | 1.27 | 37.54 | 29.01 | ||
Qwen3.8 27B (xhigh) | 262k | Open | 34 | $1.98 | 196 | 0.86 | 13.65 | 10.23 | ||
Qwen3.8 27B (xhigh) | 262k | Open | 34 | $0.41 | 70 | 1.25 | 36.78 | 28.42 | ||
Qwen3.8 27B (xhigh) | 262k | Open | 34 | $0.84 | 205 | 0.93 | 13.14 | 9.77 | ||
Qwen3.8 27B (xhigh) (NVFP4) | 262k | Open | 34 | -- | 211 | 0.60 | 12.42 | 9.46 | ||
Gemini 3.8 Flash (low) AI Studio | 1M | Proprietary | 33 | -- | -- | -- | -- | -- | ||
GPT-6 Luna (high) | 1M | Proprietary | 33 | $0.03 | 112 | 11.23 | 15.69 | -- | ||
GPT-6 Luna (high) | 524k | Proprietary | 33 | $0.03 | 190 | 7.57 | 10.20 | -- | ||
GPT-5.3 Codex (xhigh) | 400k | Proprietary | 33* | -- | 87 | 71.52 | 77.26 | -- | ||
K2 Horizon 375B A23B | 524k | Open | 31 | $0.00 | 118 | 21.64 | 42.76 | 16.89 | ||
GPT-5.6 Terra (medium) | 1M | Proprietary | 30 | $0.18 | 94 | 1.76 | 7.09 | -- | ||
Kimi K3 (low) | 1.05M | Open | 30 | $1.15 | 41 | 3.74 | 64.88 | 48.91 | ||
Kimi K3 (low) | 1M | Open | 30 | $1.41 | 152 | 1.02 | 17.42 | 13.12 | ||
Kimi K3 (low) | 1M | Open | 30 | $0.88 | 123 | 1.27 | 21.57 | 16.24 | ||
Kimi K3 (low) | 1.05M | Open | 30 | $5.77 | 202 | 1.09 | 13.45 | 9.89 | ||
Kimi K3 (low) | 1M | Open | 30 | $0.92 | 43 | 1.16 | 59.43 | 46.62 | ||
GPT-6 Luna (medium) | 1M | Proprietary | 30 | $0.02 | -- | -- | -- | -- | ||
Gemini 3.1 Pro Preview (AI Studio) | 1M | Proprietary | 30 | $1.30 | 122 | 23.40 | 27.51 | -- | ||
Gemini 3.1 Pro Preview (Vertex) | 1M | Proprietary | 30 | $1.31 | 98 | 24.41 | 29.50 | -- | ||
Claude Haiku 5.5 (low with fallback) | 1M | Proprietary | 29 | $0.02 | -- | -- | -- | -- | ||
MiniMax-M3 (MXFP8) | 1M | Open | 29 | $0.46 | 151 | 1.15 | 17.69 | 13.23 | ||
MiniMax-M3 (NVFP4) | 262k | Open | 29 | -- | 74 | 1.53 | 35.25 | 26.98 | ||
MiniMax-M3 | 1M | Open | 29 | $0.58 | 46 | 0.80 | 54.90 | 43.28 | ||
MiniMax-M3 | 1M | Open | 29 | $0.46 | 79 | 3.37 | 34.94 | 25.26 | ||
MiniMax-M3 (FAST) | 1.05M | Open | 29 | $1.09 | 427 | 1.62 | 7.47 | 4.68 | ||
MiniMax-M3 | 1M | Open | 29 | $0.46 | 203 | 1.54 | 13.83 | 9.83 | ||
MiniMax-M3 (FP8) | 1.05M | Open | 29 | $1.91 | 318 | 1.47 | 9.34 | 6.30 | ||
MiniMax-M3 (FP8) | 1M | Open | 29 | $0.45 | 84 | 2.91 | 32.52 | 23.69 | ||
MiniMax-M3 | 512k | Open | 29 | $0.51 | 94 | 2.59 | 29.21 | 21.29 | ||
MiniMax-M3 | 524k | Open | 29 | $0.44 | 25 | 0.99 | 101.14 | 80.12 | ||
MiniMax-M3 | 1.05M | Open | 29 | -- | -- | -- | -- | -- | ||
MiniMax-M3 | 1.05M | Open | 29 | $3.83 | 125 | 3.53 | 23.52 | 16.00 | ||
MiniMax-M3 | 524k | Open | 29 | $0.50 | 149 | 0.90 | 17.72 | 13.45 | ||
MiniMax-M3 | 1.05M | Open | 29 | $0.54 | 86 | 2.77 | 31.76 | 23.19 | ||
Solar Pro 4 | 512k | Proprietary | 28* | -- | 115 | 2.05 | 23.73 | 17.34 | ||
Qwen3.8 27B (medium) | 1M | Open | 28 | $1.13 | 54 | 3.76 | 49.72 | 36.77 | ||
GPT-5.6 Terra (low) | 1M | Proprietary | 27 | $0.14 | 90 | 1.55 | 7.08 | -- | ||
Quasar 438B (max) | 1M | Proprietary | 27 | $2.02 | 126 | 1.29 | 21.14 | 15.88 | ||
Apodex 1.1 | 256k | Proprietary | 26 | $0.46 | -- | -- | -- | -- | ||
Qwen3.8 27B (low) | 1M | Open | 26 | $1.05 | 53 | 3.72 | 50.49 | 37.41 | ||
GPT-5.5 Instant (June 2026) | 400k | Proprietary | 26 | $0.69 | 127 | 0.90 | 20.53 | 15.71 | ||
Kimi K2.7 Code (FP4) | 256k | Open | 26 | $1.89 | 231 | 1.39 | 13.18 | 9.63 | ||
Kimi K2.7 Code (FP8) | 65.5k | Open | 26 | $1.37 | 92 | 4.91 | 34.66 | 24.31 | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.83 | 294 | 0.96 | 10.23 | 7.57 | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.65 | -- | -- | -- | -- | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.55 | 97 | 3.26 | 31.53 | 23.09 | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.39 | 68 | 1.23 | 41.61 | 32.98 | ||
Kimi K2.7 Code | 262k | Open | 26 | $0.52 | -- | -- | -- | -- | ||
Kimi K2.7 Code | 256k | Open | 26 | $0.54 | 82 | 2.91 | 36.06 | 27.07 | ||
Inkling Small | 524k | Open | 26 | -- | 145 | 0.85 | 18.08 | 13.78 | ||
Inkling Small | 262k | Open | 26 | $0.12 | -- | -- | -- | -- | ||
Inkling Small | 256k | Open | 26 | $0.09 | 205 | 2.24 | 14.46 | 9.78 | ||
Hy3 (FP8) | 256k | Open | 25 | $0.07 | 83 | 2.89 | 33.05 | 24.13 | ||
Hy3 | 262k | Open | 25 | $0.07 | 92 | 3.31 | 30.42 | 21.69 | ||
Hy3 (FP8) | 262k | Open | 25 | $0.07 | 50 | 1.02 | 51.18 | 40.13 | ||
Hy3 | 262k | Open | 25 | $0.07 | 88 | 3.39 | 31.80 | 22.73 | ||
Qwen3.7 Plus | 1M | Proprietary | 25 | $0.22 | 55 | 2.25 | 48.03 | 36.62 | ||
Inkling (xhigh) (FP8) | 131k | Open | 25 | -- | 76 | 0.73 | 33.84 | 26.48 | ||
Inkling (xhigh) | 262k | Open | 25 | $0.72 | -- | -- | -- | -- | ||
Inkling (xhigh) | 524k | Open | 25 | $0.91 | 88 | 0.74 | 29.08 | 22.67 | ||
Inkling (xhigh) (NVFP4) | 1.05M | Open | 25 | $0.86 | 179 | 0.99 | 14.94 | 11.16 | ||
Inkling (xhigh) | 262k | Open | 25 | -- | 157 | 1.91 | 17.80 | 12.72 | ||
Inkling (xhigh) | 1M | Open | 25 | $0.61 | 214 | 1.33 | 13.02 | 9.36 | ||
DeepSeek V4.1 Flash (non-reasoning) | 1M | Open | 25 | $0.15 | 219 | 1.06 | 3.35 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) | 1M | Open | 25 | $0.33 | 281 | 0.65 | 2.43 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) (FAST) | 1.05M | Open | 25 | $0.16 | 533 | 1.70 | 2.64 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) (ULTRA) | 1.05M | Open | 25 | $0.22 | 555 | 1.24 | 2.15 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) (ULTRA CHAT) | 1.05M | Open | 25 | $0.22 | 869 | 0.90 | 1.48 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) | 1M | Open | 25 | $0.70 | 224 | 0.90 | 3.13 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) | 1M | Open | 25 | $0.27 | 155 | 2.05 | 5.27 | -- | ||
DeepSeek V4.1 Flash (non-reasoning) | 1.05M | Open | 25 | $1.20 | 73 | 0.77 | 7.67 | -- | ||
Ling-3.0-flash-VL | 262k | Open | 25 | -- | 145 | 2.06 | 19.29 | 13.79 | ||
Solar Mini 4 | 524k | Proprietary | 24 | $0.36 | 82 | 1.82 | 32.49 | 24.54 | ||
Nemotron 3 Ultra | 262k | Open | 23 | $0.51 | 293 | 0.95 | 10.40 | 7.75 | ||
Nemotron 3 Ultra | 262k | Open | 23 | -- | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Open | 23 | $0.39 | 47 | 1.58 | 60.95 | 48.67 | ||
Nemotron 3 Ultra BF16 | 262k | Open | 23 | $0.99 | 43 | 1.45 | 65.72 | 52.70 | ||
Nemotron 3 Ultra | 256k | Open | 23 | $1.16 | 303 | 2.02 | 11.18 | 7.51 | ||
Nemotron 3 Ultra | 262k | Open | 23 | $0.37 | -- | -- | -- | -- | ||
Nemotron 3 Ultra | 262k | Open | 23 | $0.32 | 139 | 0.71 | 20.69 | 16.38 | ||
Ling-3.0-flash-Fin | 262k | Open | 23 | -- | 322 | 1.70 | 9.47 | 6.21 | ||
Gemini 3.5 Flash-Lite AI Studio | 1M | Proprietary | 22 | $0.19 | 349 | 8.75 | 10.18 | -- | ||
G9v3-39A5B | 131k | Open | 22* | -- | -- | -- | -- | -- | ||
KAT-Coder-Pro V2 | 256k | Proprietary | 22* | -- | -- | -- | -- | -- | ||
GPT-6 Luna (low) | 1M | Proprietary | 22 | $0.0045 | 121 | 2.40 | 6.53 | -- | ||
Qwen3.5 397B A17B (non-reasoning) (FP8) | 262k | Open | 21* | -- | 38 | 1.13 | 14.45 | -- | ||
Qwen3.5 397B A17B (non-reasoning) | 262k | Open | 21* | -- | 88 | 2.30 | 8.01 | -- | ||
Qwen3.5 397B A17B (non-reasoning) (Base, FP4) | 262k | Open | 21* | -- | 135 | 1.61 | 5.30 | -- | ||
Qwen3.5 397B A17B (non-reasoning) | 131k | Open | 21* | -- | 9 | 1.65 | 60.34 | -- | ||
Qwen3.5 397B A17B (non-reasoning) | 262k | Open | 21* | -- | 85 | 1.74 | 7.59 | -- | ||
GPT-5.6 Terra (non-reasoning) | 1M | Proprietary | 21 | $0.14 | 92 | 0.75 | 6.18 | -- | ||
GPT-5.6 Terra (non-reasoning) | 1M | Proprietary | 21 | $0.19 | 110 | 0.67 | 5.22 | -- | ||
Qwen3.5 Omni Plus | 256k | Proprietary | 20* | -- | 101 | 2.03 | 7.01 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1.05M | Open | 20 | $0.26 | 263 | 1.49 | 3.39 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1M | Open | 20 | $0.36 | 93 | 1.56 | 6.93 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1.05M | Open | 20 | $4.28 | 161 | 2.06 | 5.17 | -- | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 1.05M | Open | 20 | $0.43 | 53 | 0.84 | 10.35 | -- | ||
o3 | 200k | Proprietary | 20* | -- | 122 | 25.60 | 29.71 | -- | ||
o3 | 200k | Proprietary | 20* | -- | -- | -- | -- | -- | ||
o3 | 200k | Proprietary | 20* | -- | 124 | 6.83 | 10.87 | -- | ||
Qwen3.8 27B (non-reasoning) | 1M | Open | 20 | $2.49 | 54 | 3.67 | 12.97 | -- | ||
Qwen3.8 27B (non-reasoning) | 262k | Open | 20 | $5.69 | 214 | 0.88 | 3.21 | -- | ||
Qwen3.8 27B (non-reasoning) | 262k | Open | 20 | $0.79 | 75 | 1.25 | 7.88 | -- | ||
Qwen3.8 27B (non-reasoning) | 262k | Open | 20 | $2.18 | 225 | 0.90 | 3.12 | -- | ||
Qwen3.8 27B (non-reasoning) (NVFP4) | 262k | Open | 20 | -- | 251 | 0.63 | 2.62 | -- | ||
Ling 3.0 Flash | 131k | Open | 20 | $0.02 | 54 | 0.64 | 47.35 | 37.37 | ||
Ling 3.0 Flash | 262k | Open | 20 | -- | 332 | 2.52 | 10.06 | 6.03 | ||
LongCat 2.0 | 1M | Open | 19 | $0.06 | -- | -- | -- | -- | ||
LongCat 2.0 (FP8) | 262k | Open | 19 | $0.15 | 72 | 2.52 | 37.32 | 27.84 | ||
GPT-6 Luna (non-reasoning) | 1M | Proprietary | 18 | $0.01 | 120 | 0.76 | 4.93 | -- | ||
GPT-6 Luna (non-reasoning) | 524k | Proprietary | 18 | $0.01 | 169 | 1.25 | 4.21 | -- | ||
Qwen3.5 397B A17B | 262k | Open | 18 | $0.47 | 90 | 2.22 | 43.12 | 35.36 | ||
Qwen3.5 397B A17B | 262k | Open | 18 | $0.29 | 78 | 1.40 | 48.67 | 40.85 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 18 | -- | 40 | 1.07 | 93.01 | 79.47 | ||
Qwen3.5 397B A17B (FP8) | 262k | Open | 18 | $0.47 | -- | -- | -- | -- | ||
Qwen3.5 397B A17B (Base, FP4) | 262k | Open | 18 | $0.47 | 134 | 1.63 | 29.19 | 23.81 | ||
Qwen3.5 397B A17B | 262k | Open | 18 | $0.47 | 89 | 1.64 | 43.18 | 35.91 | ||
Qwen3.5 397B A17B | 131k | Open | 18 | $0.17 | 13 | 1.39 | 284.86 | 245.01 | ||
Qwen3.6 35B A3B | 229k | Open | 18 | $0.48 | 134 | 2.02 | 46.14 | 40.38 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 18 | $0.32 | 97 | 1.86 | 62.54 | 55.53 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 18 | $0.14 | 114 | 0.79 | 52.30 | 47.14 | ||
Qwen3.6 35B A3B (FP8) | 262k | Open | 18 | $0.31 | 171 | 0.97 | 35.43 | 31.53 | ||
Qwen3.6 35B A3B FP8 | 262k | Open | 18 | $0.31 | -- | -- | -- | -- | ||
Qwen3.6 35B A3B | 262k | Open | 18 | $0.12 | 99 | 1.17 | 60.61 | 54.41 | ||
Qwen3.6 35B A3B | 205k | Open | 18 | $0.31 | 128 | 1.43 | 47.56 | 42.22 | ||
Qwen3.6 35B A3B | 262k | Open | 18 | $0.37 | 81 | 1.23 | 73.94 | 66.54 | ||
Qwen3.5 122B A10B (non-reasoning) (FP4) | 262k | Open | 18* | -- | 31 | 1.32 | 17.70 | -- | ||
Qwen3.5 122B A10B (non-reasoning) | 262k | Open | 18* | -- | 144 | 2.29 | 5.76 | -- | ||
Muse Glimmer (high) | 131k | Open | 17 | $0.08 | 71 | 0.95 | 36.36 | 28.32 | ||
Muse Glimmer (high) | 131k | Open | 17 | $0.05 | 56 | 4.10 | 48.81 | 35.78 | ||
Muse Glimmer (high) | 131k | Open | 17 | $0.03 | 167 | 1.54 | 16.52 | 11.98 | ||
Muse Glimmer (high) | 131k | Open | 17 | $0.06 | -- | -- | -- | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 17 | $0.34 | 126 | 11.56 | 15.51 | -- | ||
Claude 4.5 Haiku Vertex | 200k | Proprietary | 17 | $0.24 | 96 | 20.99 | 26.19 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 17 | $0.28 | 99 | 14.45 | 19.50 | -- | ||
Claude 4.5 Haiku | 200k | Proprietary | 17 | $0.22 | 95 | 15.77 | 21.04 | -- | ||
Gemma 4 26B A4B | 262k | Open | 17* | -- | 151 | 1.53 | 18.14 | 13.29 | ||
Gemma 4 26B A4B AI Studio | 262k | Open | 17* | -- | 47 | 0.97 | 54.71 | 42.99 | ||
Gemma 4 26B A4B | 131k | Open | 17* | -- | 481 | 1.05 | 6.26 | 4.16 | ||
Gemma 4 26B A4B | 262k | Open | 17* | -- | 80 | 0.67 | 31.98 | 25.04 | ||
Gemma 4 26B A4B | 256k | Open | 17* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (FP8) | 262k | Open | 17* | -- | 30 | 0.88 | 84.58 | 66.96 | ||
Gemma 4 26B A4B | 256k | Open | 17* | -- | 55 | 1.66 | 47.28 | 36.49 | ||
Gemma 4 26B A4B (FP8) | 1.05M | Open | 17* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B | 1M | Open | 17* | -- | 285 | 0.69 | 9.45 | 7.01 | ||
Ring-2.6-1T | 262k | Open | 17 | $0.29 | 111 | 3.82 | 26.39 | 18.05 | ||
Qwen3.5 122B A10B (FP8) | 262k | Open | 16 | $0.21 | 55 | 1.73 | 46.98 | 36.20 | ||
Qwen3.5 122B A10B (FP4) | 262k | Open | 16 | $0.24 | 40 | 1.20 | 64.35 | 50.52 | ||
Qwen3.5 122B A10B | 262k | Open | 16 | $0.32 | 130 | 2.33 | 21.62 | 15.43 | ||
Qwen3.5 122B A10B (FP8) | 262k | Open | 16 | $0.32 | -- | -- | -- | -- | ||
Qwen3.5 122B A10B | 262k | Open | 16 | $0.32 | 111 | 1.98 | 24.40 | 17.94 | ||
Claude 4.5 Haiku (non-reasoning) | 200k | Proprietary | 15* | -- | 101 | 0.79 | 5.74 | -- | ||
Claude 4.5 Haiku (non-reasoning) | 200k | Proprietary | 15* | -- | 85 | 0.93 | 6.78 | -- | ||
Claude 4.5 Haiku (non-reasoning) | 200k | Proprietary | 15* | -- | 90 | 0.59 | 6.14 | -- | ||
Claude 4.5 Haiku (non-reasoning) Vertex | 200k | Proprietary | 15* | -- | 87 | 0.65 | 6.39 | -- | ||
Qwen3.6 35B A3B (non-reasoning) | 262k | Open | 15* | -- | 71 | 1.28 | 8.29 | -- | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | 262k | Open | 15* | -- | 177 | 0.97 | 3.80 | -- | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | 262k | Open | 15* | -- | 128 | 0.77 | 4.69 | -- | ||
Qwen3.6 35B A3B (non-reasoning) | 205k | Open | 15* | -- | 149 | 1.66 | 5.01 | -- | ||
Qwen3.6 35B A3B (non-reasoning) FP8 | 262k | Open | 15* | -- | -- | -- | -- | -- | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | 262k | Open | 15* | -- | 92 | 1.04 | 6.44 | -- | ||
Qwen3.6 35B A3B (non-reasoning) | 262k | Open | 15* | -- | 146 | 2.07 | 5.49 | -- | ||
Granite 4.2 30B | 131k | Open | 15* | -- | 75 | 0.86 | 34.38 | 26.81 | ||
Gemma 4 31B | 262k | Open | 15 | $0.07 | 50 | 1.88 | 46.89 | 34.94 | ||
Gemma 4 31B (NVFP4) | 262k | Open | 15 | -- | 131 | 0.47 | 17.57 | 13.28 | ||
Gemma 4 31B (FP8) | 262k | Open | 15 | $0.10 | -- | -- | -- | -- | ||
Gemma 4 31B | 262k | Open | 15 | $0.10 | 15 | 4.31 | 151.70 | 114.43 | ||
Gemma 4 31B (AI Studio) | 262k | Open | 15 | $0.00 | 35 | 1.13 | 64.25 | 49.01 | ||
Gemma 4 31B | 262k | Open | 15 | $0.07 | 47 | 3.20 | 50.92 | 37.05 | ||
Gemma 4 31B | 262k | Open | 15 | $0.15 | 14 | 2.83 | 167.38 | 127.75 | ||
Gemma 4 31B | 262k | Open | 15 | $0.10 | 22 | 1.31 | 105.27 | 80.71 | ||
Gemma 4 31B (FP8) | 262k | Open | 15 | $0.54 | 39 | 3.78 | 61.58 | 44.88 | ||
Gemma 4 31B | 131k | Open | 15 | $0.28 | 441 | 3.83 | 8.90 | 3.93 | ||
Gemma 4 31B | 256k | Open | 15 | $0.10 | 123 | 0.97 | 19.11 | 14.08 | ||
Gemma 4 31B | 262k | Open | 15 | $0.05 | 42 | 2.11 | 55.40 | 41.38 | ||
Mistral Medium 3.5 | 262k | Open | 14 | $0.50 | 169 | 2.24 | 17.01 | 11.81 | ||
Gemma 4 12B | 262k | Open | 14* | -- | 116 | 2.43 | 24.06 | 17.30 | ||
Nova 2.0 Pro Preview (medium) | 256k | Proprietary | 14* | -- | 119 | 11.90 | 32.83 | 16.74 | ||
Gemma 4 31B (non-reasoning) (NVFP4) | 262k | Open | 14* | -- | 101 | 0.39 | 5.32 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Open | 14* | -- | 50 | 2.41 | 12.47 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Open | 14* | -- | 103 | 0.78 | 5.62 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Open | 14* | -- | 57 | 1.95 | 10.73 | -- | ||
Gemma 4 31B (non-reasoning) (FP8) | 262k | Open | 14* | -- | 39 | 3.51 | 16.33 | -- | ||
Gemma 4 31B (non-reasoning) | 131k | Open | 14* | -- | 202 | 2.90 | 5.37 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Open | 14* | -- | 22 | 1.00 | 24.06 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Open | 14* | -- | 14 | 3.16 | 39.73 | -- | ||
Gemma 4 31B (non-reasoning) | 262k | Open | 14* | -- | 46 | 2.06 | 13.04 | -- | ||
Gemma 4 31B (non-reasoning) (FP8) | 262k | Open | 14* | -- | 13 | 2.24 | 40.98 | -- | ||
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* | -- | 187 | 14.82 | 28.19 | 10.70 | ||
Qwen3.5 9B (non-reasoning) (FP8) | 262k | Open | 13* | -- | 80 | 0.72 | 7.01 | -- | ||
Command A+ | 200k | Open | 13 | $0.00 | 152 | 0.49 | 16.97 | 13.18 | ||
Gemma 4 26B A4B (non-reasoning) | 262k | Open | 13* | -- | 69 | 1.79 | 9.04 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 131k | Open | 13* | -- | 518 | 1.01 | 1.98 | -- | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | 1.05M | Open | 13* | -- | -- | -- | -- | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | Open | 13* | -- | 118 | 0.97 | 5.19 | -- | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | 262k | Open | 13* | -- | 103 | 2.53 | 7.40 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | Open | 13* | -- | 79 | 0.75 | 7.07 | -- | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | 262k | Open | 13* | -- | 25 | 0.77 | 20.52 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 262k | Open | 13* | -- | 54 | 1.06 | 10.39 | -- | ||
Gemma 4 26B A4B (non-reasoning) | 1M | Open | 13* | -- | 350 | 0.61 | 2.03 | -- | ||
Qwen3.5 4B (FP8) | 262k | Open | 13* | -- | 18 | 0.84 | 139.22 | 110.70 | ||
Nemotron 3.5 Lightning (NVFP4) | 262k | Open | 13 | $0.09 | 289 | 0.55 | 9.21 | 6.92 | ||
Nemotron 3.5 Lightning (BF16) | 1.05M | Open | 13 | $0.09 | 264 | 0.97 | 10.44 | 7.57 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Open | 13 | $0.10 | 386 | 0.57 | 7.05 | 5.19 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Open | 13 | $0.02 | 457 | 0.48 | 5.95 | 4.38 | ||
Nemotron 3.5 Lightning (BF16) | 262k | Open | 13 | $0.08 | 297 | 0.46 | 8.87 | 6.73 | ||
Nemotron 3 Super (FP8) | 262k | Open | 13 | $1.14 | 152 | 0.58 | 17.03 | 13.16 | ||
Nemotron 3 Super | 256k | Open | 13 | $1.64 | 184 | 1.40 | 14.97 | 10.86 | ||
Nemotron 3 Super | 262k | Open | 13 | $0.48 | 60 | 15.04 | 57.01 | 33.57 | ||
Nova 2.0 Pro Preview (low) | 256k | Proprietary | 13* | -- | 117 | 7.79 | 29.12 | 17.07 | ||
Nova 2.0 Lite (medium) | 1M | Proprietary | 12* | -- | 184 | 17.40 | 30.99 | 10.87 | ||
Qwen3.5 Omni Flash | 256k | Proprietary | 12* | -- | 220 | 1.81 | 4.08 | -- | ||
Mercury 2.5 | 256k | Proprietary | 12 | $0.12 | 618 | 3.21 | 4.02 | -- | ||
Nova 2.0 Lite (low) | 1M | Proprietary | 12* | -- | 167 | 9.99 | 24.99 | 12.01 | ||
gpt-oss-120b (high) | 131k | Open | 12 | -- | 471 | 0.70 | 6.01 | 4.24 | ||
gpt-oss-120b (high) | 116k | Open | 12 | $0.23 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 128k | Open | 12 | $0.12 | 135 | 1.39 | 19.91 | 14.82 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.02 | 39 | 1.26 | 65.33 | 51.25 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.11 | 354 | 0.86 | 7.93 | 5.66 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.04 | 167 | 0.98 | 15.92 | 11.95 | ||
gpt-oss-120b (high) (Turbo) | 131k | Open | 12 | $0.11 | 210 | 0.89 | 12.78 | 9.51 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.03 | 56 | 0.61 | 44.98 | 35.50 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.23 | 1,817 | 0.43 | 1.81 | 1.10 | ||
gpt-oss-120b (high) Vertex | 131k | Open | 12 | $0.06 | 45 | 1.77 | 57.93 | 44.93 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.04 | 264 | 0.39 | 9.86 | 7.57 | ||
gpt-oss-120b (high) | 128k | Open | 12 | $0.07 | 261 | 0.21 | 9.78 | 7.66 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.15 | 701 | 1.15 | 4.71 | 2.85 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.06 | 158 | 0.83 | 16.70 | 12.70 | ||
gpt-oss-120b (high) (Base) | 128k | Open | 12 | $0.11 | 271 | 0.96 | 10.19 | 7.38 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.19 | -- | -- | -- | -- | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.11 | 68 | 1.04 | 37.68 | 29.31 | ||
gpt-oss-120b (high) | 131k | Open | 12 | $0.11 | 144 | 0.42 | 17.81 | 13.91 | ||
Mistral Small 4 | 256k | Open | 11 | $0.02 | 162 | 0.71 | 16.14 | 12.34 | ||
Qwen3 Next 80B A3B | 262k | Open | 11* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Open | 11* | -- | 151 | 0.68 | 17.23 | 13.24 | ||
Qwen3 Next 80B A3B | 262k | Open | 11* | -- | 179 | 2.25 | 16.19 | 11.15 | ||
Qwen3 Next 80B A3B | 262k | Open | 11* | -- | -- | -- | -- | -- | ||
Qwen3.5 9B (FP8) | 262k | Open | 11 | $0.16 | 33 | 2.26 | 77.01 | 59.79 | ||
Qwen3.5 9B (FP8) | 262k | Open | 11 | $0.27 | 85 | 0.69 | 30.06 | 23.49 | ||
Nova 2.0 Omni (low) | 1M | Proprietary | 11* | -- | -- | -- | -- | -- | ||
Granite 4.2 8B | 131k | Open | 11 | $0.05 | 103 | 0.72 | 24.98 | 19.41 | ||
Granite 4.2 8B | 131k | Open | 11 | $0.02 | 48 | 0.86 | 53.46 | 42.08 | ||
Ling 3.0 Tiny | 262k | Open | 11 | $0.00 | 58 | 2.63 | 45.69 | 34.45 | ||
G9v3-3B | 131k | Open | 11* | -- | -- | -- | -- | -- | ||
Trinity Large Thinking | 262k | Open | 11 | $0.12 | 337 | 1.21 | 8.64 | 5.94 | ||
Qwen3.5 4B (non-reasoning) FP8 | 262k | Open | 11* | -- | 22 | 0.84 | 23.99 | -- | ||
Nemotron 3 Nano Omni 30B A3B | 262k | Open | 10* | -- | 269 | 0.36 | 9.67 | 7.45 | ||
Nemotron 3 Nano Omni 30B A3B | 65.5k | Open | 10* | -- | 228 | 0.91 | 11.88 | 8.78 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) Base | 128k | Open | 10* | -- | 286 | 0.95 | 9.69 | 6.99 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 729 | 1.17 | 4.60 | 2.74 | ||
gpt-oss-120b (low) Vertex | 131k | Open | 10* | -- | 91 | 1.95 | 29.30 | 21.89 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 261 | 0.40 | 9.98 | 7.67 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 54 | 0.66 | 46.98 | 37.06 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 44 | 1.20 | 58.33 | 45.70 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 1,745 | 0.43 | 1.86 | 1.15 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 384 | 1.00 | 7.51 | 5.21 | ||
gpt-oss-120b (low) | 128k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-120b (low) | 128k | Open | 10* | -- | 251 | 0.21 | 10.17 | 7.97 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 76 | 1.03 | 33.73 | 26.16 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 139 | 0.83 | 18.78 | 14.36 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 136 | 0.42 | 18.85 | 14.75 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 471 | 0.69 | 6.00 | 4.25 | ||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 170 | 0.95 | 15.67 | 11.77 | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 10* | -- | 28 | 1.11 | 19.00 | -- | ||
Llama 4 Maverick (FP8) | 128k | Open | 10* | -- | 345 | 1.45 | 2.90 | -- | ||
Llama 4 Maverick | 128k | Open | 10* | -- | -- | -- | -- | -- | ||
Llama 4 Maverick | 1.05M | Open | 10* | -- | -- | -- | -- | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 10* | -- | 28 | 0.87 | 18.79 | -- | ||
Llama 4 Maverick | 128k | Open | 10* | -- | 14 | 1.03 | 35.90 | -- | ||
Llama 4 Maverick (FP8) | 1.05M | Open | 10* | -- | 72 | 1.27 | 8.17 | -- | ||
Nova 2.0 Pro Preview (non-reasoning) | 256k | Proprietary | 10* | -- | 108 | 1.06 | 5.70 | -- | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | 908 | 0.75 | 3.50 | 2.20 | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | 205 | 0.54 | 12.74 | 9.76 | ||
gpt-oss-20b (low) | 128k | Open | 10* | -- | -- | -- | -- | -- | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | 184 | 7.40 | 20.99 | 10.87 | ||
gpt-oss-20b (low) | 131k | Open | 10* | -- | 167 | 1.22 | 16.17 | 11.96 | ||
gpt-oss-20b (low) Vertex | 131k | Open | 10* | -- | 352 | 0.35 | 7.45 | 5.68 | ||
North Mini Code | 256k | Open | 10 | $0.00 | 66 | 0.45 | 38.51 | 30.45 | ||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | -- | -- | -- | -- | ||
Qwen3 Next 80B A3B Vertex | 262k | Open | 10* | -- | 293 | 0.60 | 2.31 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | 108 | 0.94 | 5.59 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | 164 | 0.73 | 3.78 | -- | ||
Qwen3 Next 80B A3B | 262k | Open | 10* | -- | 117 | 1.43 | 5.69 | -- | ||
Qwen3 Next 80B A3B | 131k | Open | 10* | -- | 179 | 1.83 | 4.62 | -- | ||
Qwen3 Next 80B A3B | 131k | Open | 10* | -- | 175 | 2.17 | 5.02 | -- | ||
Gemma 4 12B (non-reasoning) | 262k | Open | 9* | -- | 113 | 2.40 | 6.82 | -- | ||
Mistral Large 3 | 256k | Open | 9 | $0.10 | 93 | 1.34 | 6.73 | -- | ||
Mistral Large 3 | 256k | Open | 9 | $0.10 | 68 | 1.60 | 8.94 | -- | ||
Mistral Large 3 | 262k | Open | 9 | $0.03 | 78 | 1.03 | 7.48 | -- | ||
Qwen3 Coder Next | 128k | Open | 9 | $0.78 | 89 | 1.64 | 7.26 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 9 | $0.12 | 68 | 1.06 | 8.44 | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 9 | $0.78 | -- | -- | -- | -- | ||
Qwen3 Coder Next (FP8) | 262k | Open | 9 | $0.33 | 170 | 2.79 | 5.73 | -- | ||
Granite 4.2 3B | 131k | Open | 9 | $0.01 | 214 | 0.53 | 12.19 | 9.33 | ||
Mistral Small 4 (non-reasoning) | 262k | Open | 9* | -- | 160 | 0.73 | 3.85 | -- | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | 190 | 0.55 | 13.72 | 10.53 | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | 143 | 46.54 | 64.06 | 14.02 | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | 102 | 0.53 | 25.11 | 19.66 | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 128k | Open | 9 | $0.03 | -- | -- | -- | -- | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.01 | 171 | 1.20 | 15.78 | 11.66 | ||
gpt-oss-20b (high) Vertex | 131k | Open | 9 | $0.01 | 378 | 0.34 | 6.96 | 5.29 | ||
gpt-oss-20b (high) | 131k | Open | 9 | $0.02 | 907 | 0.80 | 3.55 | 2.20 | ||
Gemma 4 E4B | 131k | Open | 9* | -- | 28 | 1.34 | 89.46 | 70.50 | ||
Nemotron 3 Nano | 262k | Open | 9 | $0.02 | 117 | 1.01 | 22.44 | 17.14 | ||
Nemotron 3 Nano (FP4) | 262k | Open | 9 | $0.02 | 273 | 1.04 | 10.18 | 7.31 | ||
Nemotron 3 Nano | 262k | Open | 9 | $0.02 | 19 | 70.53 | 201.06 | 104.42 | ||
Nemotron 3 Nano (FP8) | 262k | Open | 9 | $0.01 | 260 | 0.31 | 9.93 | 7.70 | ||
Sarvam 105B (high) | 128k | Open | 9* | -- | -- | -- | -- | -- | ||
Nova 2.0 Lite (non-reasoning) | 1M | Proprietary | 9* | -- | 169 | 1.10 | 4.07 | -- | ||
Magistral Small 1.2 | 128k | Open | 9* | -- | 78 | 1.60 | 33.53 | 25.54 | ||
LFM2.5-2.6B | 32.8k | Open | 8* | -- | -- | -- | -- | -- | ||
Nova 2.0 Omni (non-reasoning) | 1M | Proprietary | 8* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 131k | Open | 8* | -- | 28 | 0.86 | 18.69 | -- | ||
Llama 4 Scout | 128k | Open | 8* | -- | 117 | 0.80 | 5.09 | -- | ||
Llama 4 Scout Vertex | 1.31M | Open | 8* | -- | 151 | 0.72 | 4.03 | -- | ||
Llama 4 Scout | 131k | Open | 8* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 128k | Open | 8* | -- | -- | -- | -- | -- | ||
Llama 4 Scout | 131k | Open | 8* | -- | 29 | 1.21 | 18.18 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | Open | 8* | -- | 103 | 1.87 | 26.25 | 19.50 | ||
Llama 3.3 70B | 131k | Open | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B Vertex | 128k | Open | 8* | -- | 166 | 0.66 | 3.68 | -- | ||
Llama 3.3 70B | 131k | Open | 8* | -- | 319 | 0.81 | 2.38 | -- | ||
Llama 3.3 70B | 131k | Open | 8* | -- | 43 | 1.81 | 13.39 | -- | ||
Llama 3.3 70B (FP8) | 131k | Open | 8* | -- | 77 | 2.56 | 9.03 | -- | ||
Llama 3.3 70B | 128k | Open | 8* | -- | 278 | 2.08 | 3.88 | -- | ||
Llama 3.3 70B | 128k | Open | 8* | -- | 80 | 0.87 | 7.15 | -- | ||
Llama 3.3 70B Turbo | 131k | Open | 8* | -- | 75 | 1.64 | 8.27 | -- | ||
Llama 3.3 70B | 128k | Open | 8* | -- | 121 | 2.24 | 6.36 | -- | ||
Llama 3.3 70B (Turbo, FP8) | 131k | Open | 8* | -- | 14 | 2.36 | 37.92 | -- | ||
Llama 3.3 70B | 24k | Open | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B | 128k | Open | 8* | -- | -- | -- | -- | -- | ||
Llama 3.3 70B | 100k | Open | 8* | -- | 61 | 1.55 | 9.75 | -- | ||
ERNIE 4.5 300B A47B | 131k | Open | 8* | -- | -- | -- | -- | -- | ||
Hermes 4 405B (FP8) | 128k | Open | 7* | -- | 40 | 2.42 | 65.00 | 50.07 | ||
Gemma 4 E4B (non-reasoning) | 131k | Open | 7* | -- | 30 | 0.79 | 17.71 | -- | ||
NVIDIA Nemotron Nano 9B V2 | 131k | Open | 7* | -- | 20 | 60.50 | 188.02 | 102.02 | ||
Hermes 4 405B (non-reasoning) (FP8) | 128k | Open | 7* | -- | 39 | 2.32 | 15.02 | -- | ||
Ring-flash-2.0 | 131k | Open | 7* | -- | -- | -- | -- | -- | ||
Olmo 3.1 32B Think | 65.5k | Open | 7* | -- | -- | -- | -- | -- | ||
Command A | 288k | Open | 7* | -- | 58 | 1.81 | 10.40 | -- | ||
Command A | 256k | Open | 7* | -- | 42 | 2.95 | 14.93 | -- | ||
Nemotron 3 Nano (non-reasoning) (FP4) | 262k | Open | 7* | -- | 266 | 1.02 | 2.90 | -- | ||
Nemotron 3 Nano (non-reasoning) | 262k | Open | 7* | -- | 23 | 25.70 | 47.63 | -- | ||
Nemotron 3 Nano (non-reasoning) (FP8) | 262k | Open | 7* | -- | 239 | 0.29 | 2.38 | -- | ||
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | 131k | Open | 7* | -- | 21 | 47.34 | 71.20 | -- | ||
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | 131k | Open | 7* | -- | 170 | 1.13 | 4.07 | -- | ||
Sarvam 30B (high) | 64k | Open | 7* | -- | -- | -- | -- | -- | ||
Celeris-1 | 131k | Proprietary | 6 | $0.05 | 1,508 | 0.58 | 0.91 | -- | ||
Phi-4 Mini | 128k | Open | 6* | -- | 46 | 0.84 | 11.82 | -- | ||
Granite 4.0 H Small | 128k | Open | 6* | -- | 9 | 58.38 | 115.40 | -- | ||
Ministral 3 14B | 262k | Open | 6 | $0.02 | 87 | 1.12 | 6.84 | -- | ||
Ministral 3 14B | 256k | Open | 6 | $0.14 | 195 | 1.10 | 3.67 | -- | ||
Ministral 3 14B | 262k | Open | 6 | $0.03 | 37 | 1.00 | 14.34 | -- | ||
Qwen3 Omni 30B A3B | 65.5k | Open | 6* | -- | 96 | 1.87 | 7.08 | -- | ||
Phi-4 | 16.4k | Open | 6* | -- | 40 | 2.50 | 15.02 | -- | ||
Phi-4 | 16.4k | Open | 6* | -- | 75 | 0.96 | 7.63 | -- | ||
Nova Micro | 130k | Proprietary | 6* | -- | 294 | 0.85 | 2.55 | -- | ||
NVIDIA Nemotron Nano 12B v2 VL (non-reasoning) | 128k | Open | 6* | -- | 199 | 1.13 | 3.64 | -- | ||
Phi-4 Multimodal | 4.1k | Open | 6* | -- | -- | -- | -- | -- | ||
Reka Flash 3 | 54k | Open | 6* | -- | 94 | 1.35 | 27.90 | 21.24 | ||
Ministral 3 8B | 256k | Open | 5 | $0.07 | 267 | 1.00 | 2.88 | -- | ||
Ministral 3 8B | 262k | Open | 5 | $0.01 | 101 | 0.71 | 5.67 | -- | ||
Llama 3.2 11B (Vision) | 131k | Open | 5* | -- | 15 | 1.99 | 35.77 | -- | ||
Olmo 3 7B | 65.5k | Open | 5* | -- | -- | -- | -- | -- | ||
Apertus 70B Instruct | 64k | Open | 5* | -- | -- | -- | -- | -- | ||
Ministral 3 3B | 256k | Open | 5 | $0.04 | 431 | 0.96 | 2.12 | -- | ||
Ministral 3 3B | 131k | Open | 5 | $0.01 | 223 | 0.63 | 2.87 | -- | ||
Tiny Aya Global | 8.19k | Open | 5* | -- | -- | -- | -- | -- | ||
Apertus 8B Instruct | 64k | Open | 5* | -- | -- | -- | -- | -- | ||
Cogito v2.1 | 164k | Open | -- | -- | -- | -- | -- | -- | ||