| 1 | inclusionAI: Ling-2.6-flash | 0.01 | 0.03 | 262.1k | — | |
| 2 | DeepSeek: DeepSeek V4 Flash Latest | 0.0128 | 0.768 | 1.0M | — | |
| 3 | DeepSeek: DeepSeek V4 Flash 0731 | 0.016 | 0.64 | 1.0M | — | |
| 4 | IBM: Granite 4.0 Micro | 0.017 | 0.112 | 131.0k | — | |
| 5 | OpenAI: gpt-oss-20b | 0.018 | 0.09 | 131.1k | 36.3B | |
| 6 | inclusionAI: Ling 3.0 Flash | 0.021 | 0.063 | 262.1k | — | |
| 7 | inclusionAI: Ling 3.0 Flash VL | 0.021 | 0.0616 | 262.1k | — | |
| 8 | OpenAI: gpt-oss-20b (batch) | 0.024 | 0.112 | 131.1k | — | |
| 9 | nex-agi/nex-n2-mini | 0.025 | 0.1 | 262.1k | 29.6B | |
| 10 | OpenAI: GPT-5 Nano (batch) | 0.025 | 0.2 | 400.0k | — | |
| 11 | Nex AGI: Nex-N2.5-Mini | 0.025 | 0.1 | 262.1k | — | |
| 12 | Meta: Llama 3.2 1B Instruct | 0.027 | 0.201 | 60.0k | — | |
| 13 | mistralai/mistral-nemo | 0.029 | 0.03 | 131.1k | 46.5B | |
| 14 | OpenAI: gpt-oss-120b (batch) | 0.0296 | 0.136 | 131.1k | — | |
| 15 | DeepSeek: DeepSeek V4 Flash 0423 | 0.03 | 1.28 | 1.0M | — | |
| 16 | Qwen: Qwen3.7 Flash | 0.03 | 0.13 | 1.0M | — | |
| 17 | Inference.net: Schematron V2 Turbo | 0.03 | 0.15 | 128.0k | — | |
| 18 | Z.ai: GLM Flash Latest | 0.032 | 1.2 | 1.0M | — | |
| 19 | DeepSeek: DeepSeek Flash Latest | 0.0336 | 1.188 | 1.0M | — | |
| 20 | Amazon: Nova Micro 1.0 | 0.035 | 0.14 | 128.0k | — | |
| 21 | openai/gpt-oss-120b | 0.037 | 0.17 | 131.1k | 48.4B | |
| 22 | Cohere: Command R7B (12-2024) | 0.0375 | 0.15 | 128.0k | — | |
| 23 | Sao10K: Llama 3 8B Lunaris | 0.04 | 0.05 | 8.2k | — | |
| 24 | Qwen: Qwen3.8 27B | 0.04 | 2.3 | 1.0M | — | |
| 25 | Inception: Mercury 2.5 Preview | 0.04 | 0.15 | 260.0k | — | |
| 26 | Inception: Mercury 2.5 | 0.04 | 0.15 | 260.0k | — | |
| 27 | Google: Gemma 4 26B A4B | 0.042 | 0.22 | 262.1k | — | |
| 28 | inclusionAI: Ling 3.0 Flash Fin | 0.042 | 0.1232 | 262.1k | — | |
| 29 | inclusionAI: Ling 3.0 Flash Sante | 0.042 | 0.1232 | 262.1k | — | |
| 30 | Tencent: Hy-MT2-1.8B | 0.044 | 0.177 | 8.2k | — | |
| 31 | IBM: Granite 4.1 8B | 0.05 | 0.1 | 131.1k | — | |
| 32 | OpenAI: GPT-5 Nano | 0.05 | 0.4 | 400.0k | — | |
| 33 | Google: Gemma 3 4B | 0.05 | 0.1 | 131.1k | — | |
| 34 | Google: Gemma 3 12B | 0.05 | 0.15 | 131.1k | — | |
| 35 | Mistral: Mistral Small 3 | 0.05 | 0.08 | 32.8k | — | |
| 36 | Meta: Llama 3.2 3B Instruct | 0.05 | 0.33 | 131.1k | — | |
| 37 | Meta: Llama 3.1 8B Instruct | 0.05 | 0.08 | 131.1k | 11.3B | |
| 38 | Google: Gemini 2.5 Flash Lite (batch) | 0.05 | 0.2 | 1.0M | — | |
| 39 | OpenAI: GPT-4.1 Nano (batch) | 0.05 | 0.2 | 1.0M | — | |
| 40 | Inference.net: Schematron V2 Small | 0.05 | 0.23 | 128.0k | — | |