| Llama 3.1 8B Instruct fp8 Meta-Llama-3-1-8B-Instruct-FP8 | Meta | $0.02 | $0.03 | 128,000 | open weights |
| Manta Flash 1.0 meganova-ai/manta-flash-1.0 | Independent | $0.02 | $0.16 | 16,384 | |
| Manta Mini 1.0 meganova-ai/manta-mini-1.0 | Independent | $0.02 | $0.16 | 8,192 | |
| Qwen3.7 Flash qwen/qwen3.7-flash | Alibaba | $0.03 | $0.13 | 991,808 | reasoning |
| Inference.net: Schematron V2 Turbo inference-net/schematron-v2-turbo | Independent | $0.03 | $0.15 | 128,000 | |
| Upstage: Solar Pro 4 upstage/solar-pro4 | Independent | $0.03 | $0.12 | 524,288 | reasoning |
| Llama 3.2 3B Instruct meta-llama/llama-3.2-3b-instruct | Meta | $0.03 | $0.05 | 131,072 | open weights |
| Doubao Seed 1.6 Flash doubao-seed-1-6-flash-250615 | Independent | $0.04 | $0.37 | 256,000 | |
| Mercury 2.5 Preview inception/mercury-2.5-preview | Independent | $0.04 | $0.15 | 260,000 | reasoning |
| Doubao Seed 2.0 Mini doubao-seed-2-0-mini-260215 | Independent | $0.05 | $0.48 | 256,000 | |
| Qwen Turbo qwen/qwen-turbo | Alibaba | $0.05 | $0.20 | 1,000,000 | reasoning |
| Agnes 3.0 Flash agnes-3.0-flash | Independent | $0.05 | $0.15 | 524,288 | reasoning |
| DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | DeepSeek | $0.05 | $0.16 | 1,000,000 | reasoningopen weights |
| DeepSeek V4 Flash Latest deepseek/deepseek-v4-flash-latest | DeepSeek | $0.05 | $0.16 | 1,048,576 | reasoningopen weights |
| Gemma 4 12B Instruct gemma-4-12b-it | Google | $0.05 | $0.25 | 131,072 | open weights |
| Gemma 4 12B Semancer gemma-4-12b-it-semancer | Google | $0.05 | $0.25 | 131,072 | reasoningopen weights |
| Gemma 4 12B StationKeeper gemma-4-12b-it-station-keeper | Google | $0.05 | $0.25 | 131,072 | reasoningopen weights |
| GPT-5 Nano openai/gpt-5-nano | OpenAI | $0.05 | $0.40 | 400,000 | reasoning |
| Llama-3.3-70B-Instruct meta-llama/llama-3.3-70b-instruct | Meta | $0.05 | $0.23 | 131,072 | open weights |
| Nemotron 3.5 Lightning 30B A3B nvidia/nemotron-3.5-lightning | NVIDIA | $0.05 | $0.20 | 1,000,000 | reasoningopen weights |
| Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b | NVIDIA | $0.05 | $0.25 | 262,144 | reasoningopen weights |
| Qwen3.5 9B qwen/qwen3.5-9b | Alibaba | $0.05 | $0.15 | 256,000 | reasoningopen weights |
| Inference.net: Schematron V2 Small inference-net/schematron-v2-small | Independent | $0.05 | $0.23 | 128,000 | |
| Sarvam-105B sarvam-105b | Sarvam | $0.05 | $0.21 | 131,072 | reasoningopen weights |
| Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct | Meta | $0.05 | $0.09 | 131,072 | open weights |
| nova-lite-v1 amazon/nova-lite-v1 | Independent | $0.06 | $0.24 | 300,000 | reasoning |
| Devstral Small 2505 mistralai/devstral-small-2505 | Mistral | $0.06 | $0.06 | 32,768 | open weights |
| inclusionAI: Ling 3.0 Flash VL inclusionai/ling-3.0-flash-vl | Independent | $0.06 | $0.18 | 262,144 | reasoning |
| Manta Pro 1.0 meganova-ai/manta-pro-1.0 | Independent | $0.06 | $0.50 | 65,536 | |
| Hy3 tencent/hy3 | Tencent | $0.07 | $0.26 | 262,144 | reasoningopen weights |
| GLM-4.7-Flash z-ai/glm-4.7-flash | Zhipu AI | $0.07 | $0.40 | 200,000 | reasoningopen weights |
| GLM 4.7 Flash Original z-ai/glm-4.7-flash-original | Zhipu AI | $0.07 | $0.40 | 200,000 | reasoningopen weights |
| Phi 4 Multimodal phi-4-multimodal-instruct | NVIDIA | $0.07 | $0.11 | 128,000 | |
| GPT OSS Safeguard 20B openai/gpt-oss-safeguard-20b | OpenAI | $0.07 | $0.30 | 128,000 | reasoningopen weights |
| inclusionAI: Ling 3.0 Flash inclusionai/ling-3.0-flash | Independent | $0.07 | $0.22 | 262,144 | reasoning |
| Qwen3 14B qwen/qwen3-14b | Alibaba | $0.08 | $0.24 | 41,000 | reasoningopen weights |
| Meta Llama 4 Scout 17B 16E meta-llama/llama-4-scout | Meta | $0.09 | $0.46 | 328,000 | |
| TheDrummer/Artemis v1.1 TheDrummer/Artemis-v1.1 | Independent | $0.10 | $0.45 | 262,144 | reasoningopen weights |
| DeepSeek Chat deepseek-chat | DeepSeek | $0.10 | $0.42 | 128,000 | open weights |
| DeepSeek V3/Chat Cheaper deepseek-chat-cheaper | DeepSeek | $0.10 | $0.42 | 128,000 | open weights |