Compare AI model costs
Use the same input and output token assumptions across models to find the right cost profile.
Comparison inputs
Estimated input tokens: 15
Cost comparison
| Model | Input | Output | Per request | 10K requests | Context |
|---|---|---|---|---|---|
Baidu Qianfan: CoBuddy (free) baidu/cobuddy:free | $0 | $0 | $0 | $0 | 131,072 |
Baidu: Qianfan-OCR-Fast (free) baidu/qianfan-ocr-fast:free | $0 | $0 | $0 | $0 | 65,536 |
Venice: Uncensored (free) cognitivecomputations/dolphin-mistral-24b-venice-edition:free | $0 | $0 | $0 | $0 | 32,768 |
Google: Gemma 4 26B A4B (free) google/gemma-4-26b-a4b-it:free | $0 | $0 | $0 | $0 | 262,144 |
Google: Gemma 4 31B (free) google/gemma-4-31b-it:free | $0 | $0 | $0 | $0 | 262,144 |
Google: Lyria 3 Clip Preview google/lyria-3-clip-preview | $0 | $0 | $0 | $0 | 1,048,576 |
Google: Lyria 3 Pro Preview google/lyria-3-pro-preview | $0 | $0 | $0 | $0 | 1,048,576 |
inclusionAI: Ling-2.6-1T (free) inclusionai/ling-2.6-1t:free | $0 | $0 | $0 | $0 | 262,144 |
LiquidAI: LFM2.5-1.2B-Instruct (free) liquid/lfm-2.5-1.2b-instruct:free | $0 | $0 | $0 | $0 | 32,768 |
LiquidAI: LFM2.5-1.2B-Thinking (free) liquid/lfm-2.5-1.2b-thinking:free | $0 | $0 | $0 | $0 | 32,768 |
Meta: Llama 3.2 3B Instruct (free) meta-llama/llama-3.2-3b-instruct:free | $0 | $0 | $0 | $0 | 131,072 |
Meta: Llama 3.3 70B Instruct (free) meta-llama/llama-3.3-70b-instruct:free | $0 | $0 | $0 | $0 | 65,536 |
MiniMax: MiniMax M2.5 (free) minimax/minimax-m2.5:free | $0 | $0 | $0 | $0 | 196,608 |
Nous: Hermes 3 405B Instruct (free) nousresearch/hermes-3-llama-3.1-405b:free | $0 | $0 | $0 | $0 | 131,072 |
NVIDIA: Nemotron 3 Nano 30B A3B (free) nvidia/nemotron-3-nano-30b-a3b:free | $0 | $0 | $0 | $0 | 256,000 |
NVIDIA: Nemotron 3 Nano Omni (free) nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | $0 | $0 | $0 | $0 | 256,000 |
NVIDIA: Nemotron 3 Super (free) nvidia/nemotron-3-super-120b-a12b:free | $0 | $0 | $0 | $0 | 262,144 |
NVIDIA: Nemotron Nano 12B 2 VL (free) nvidia/nemotron-nano-12b-v2-vl:free | $0 | $0 | $0 | $0 | 128,000 |
NVIDIA: Nemotron Nano 9B V2 (free) nvidia/nemotron-nano-9b-v2:free | $0 | $0 | $0 | $0 | 128,000 |
OpenAI: gpt-oss-120b (free) openai/gpt-oss-120b:free | $0 | $0 | $0 | $0 | 131,072 |
OpenAI: gpt-oss-20b (free) openai/gpt-oss-20b:free | $0 | $0 | $0 | $0 | 131,072 |
Free Models Router openrouter/free | $0 | $0 | $0 | $0 | 200,000 |
Owl Alpha openrouter/owl-alpha | $0 | $0 | $0 | $0 | 1,048,756 |
Poolside: Laguna M.1 (free) poolside/laguna-m.1:free | $0 | $0 | $0 | $0 | 131,072 |
Poolside: Laguna XS.2 (free) poolside/laguna-xs.2:free | $0 | $0 | $0 | $0 | 131,072 |
Qwen: Qwen3 Coder 480B A35B (free) qwen/qwen3-coder:free | $0 | $0 | $0 | $0 | 262,000 |
Qwen: Qwen3 Next 80B A3B Instruct (free) qwen/qwen3-next-80b-a3b-instruct:free | $0 | $0 | $0 | $0 | 262,144 |
Tencent: Hy3 preview (free) tencent/hy3-preview:free | $0 | $0 | $0 | $0 | 262,144 |
Z.ai: GLM 4.5 Air (free) z-ai/glm-4.5-air:free | $0 | $0 | $0 | $0 | 131,072 |
Mistral: Mistral Nemo mistralai/mistral-nemo | $0.00 | $0.000015 | $0.000015 | $0.153 | 131,072 |
Meta: Llama 3 8B Instruct meta-llama/llama-3-8b-instruct | $0.000001 | $0.00002 | $0.000021 | $0.206 | 8,192 |
Llama Guard 3 8B meta-llama/llama-guard-3-8b | $0.000007 | $0.000015 | $0.000022 | $0.222 | 131,072 |
Meta: Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct | $0.00 | $0.000025 | $0.000025 | $0.253 | 16,384 |
Sao10K: Llama 3 8B Lunaris sao10k/l3-lunaris-8b | $0.000001 | $0.000025 | $0.000026 | $0.256 | 8,192 |
MythoMax 13B gryphe/mythomax-l2-13b | $0.000001 | $0.00003 | $0.000031 | $0.309 | 4,096 |
Google: Gemma 3 4B google/gemma-3-4b-it | $0.000001 | $0.00004 | $0.000041 | $0.406 | 131,072 |
Mistral: Mistral Small 3 mistralai/mistral-small-24b-instruct-2501 | $0.000001 | $0.00004 | $0.000041 | $0.4075 | 32,768 |
Qwen: Qwen2.5 7B Instruct qwen/qwen-2.5-7b-instruct | $0.000001 | $0.00005 | $0.000051 | $0.506 | 32,768 |
IBM: Granite 4.1 8B ibm-granite/granite-4.1-8b | $0.000001 | $0.00005 | $0.000051 | $0.5075 | 131,072 |
Qwen: Qwen3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.000001 | $0.00005 | $0.000051 | $0.5106 | 262,144 |
Mistral: Ministral 3 3B 2512 mistralai/ministral-3b-2512 | $0.000001 | $0.00005 | $0.000052 | $0.515 | 131,072 |
Reka Edge rekaai/reka-edge | $0.000001 | $0.00005 | $0.000052 | $0.515 | 16,384 |
Z.ai: GLM 4 32B z-ai/glm-4-32b | $0.000001 | $0.00005 | $0.000052 | $0.515 | 128,000 |
IBM: Granite 4.0 Micro ibm-granite/granite-4.0-h-micro | $0.00 | $0.000055 | $0.000055 | $0.5526 | 131,000 |
LiquidAI: LFM2-24B-A2B liquid/lfm-2-24b-a2b | $0.00 | $0.00006 | $0.00006 | $0.6045 | 32,768 |
Google: Gemma 3n 4B google/gemma-3n-e4b-it | $0.000001 | $0.00006 | $0.000061 | $0.609 | 32,768 |
Qwen: Qwen-Turbo qwen/qwen-turbo | $0.00 | $0.000065 | $0.000065 | $0.6549 | 131,072 |
Google: Gemma 3 12B google/gemma-3-12b-it | $0.000001 | $0.000065 | $0.000066 | $0.656 | 131,072 |
OpenAI: gpt-oss-20b openai/gpt-oss-20b | $0.00 | $0.00007 | $0.00007 | $0.7045 | 131,072 |
Amazon: Nova Micro 1.0 amazon/nova-micro-v1 | $0.000001 | $0.00007 | $0.000071 | $0.7053 | 128,000 |
Showing 1-50 of 365
1 / 8