OSAIM
Open Source AI Models

Cost calculator

Estimate monthly hosted-inference cost across every model + provider we track. Numbers assume the pricing on our verified pricing table — always confirm on the provider's own page before committing.

Cheapest right now
Mistral Nemo 12Bon deepinfra
$15.90 / month($0.53 / day)
ProviderInput $/MOutput $/M
Mistral Nemo 12Bdeepinfra$0.019$0.030$15.90
Mistral Nemo 12Bopenrouter$0.019$0.030$15.90
Mistral Small 3openrouter$0.050$0.080$42.00
Phi-4 14Bopenrouter$0.070$0.140$63.00
Qwen 3 32Bdeepinfra$0.080$0.280$90.00
Qwen 3 32Bopenrouter$0.080$0.280$90.00
Qwen2.5 7B Instructopenrouter$0.100$0.200$90.00
Llama 4 Scout 17B (16E)openrouter$0.100$0.300$105.00
Llama 3.3 70B Instructopenrouter$0.100$0.320$108.00
Qwen 3 8Bopenrouter$0.117$0.455$138.45
Llama 4 Maverick 17B (128E)openrouter$0.188$0.652$210.37
Qwen2.5 72B Instructopenrouter$0.360$0.400$276.00
DeepSeek V3deepinfra$0.320$0.890$325.50
DeepSeek V3openrouter$0.320$0.890$325.50
Gemma 2 27Bopenrouter$0.650$0.650$487.50
Hermes 3 Llama 3.1 70Bopenrouter$0.700$0.700$525.00
Qwen 3 235B (A22B)openrouter$0.455$1.820$546.00
Qwen2.5 Coder 32Bopenrouter$0.660$1.000$546.00
DeepSeek R1 Distill Llama 70Bopenrouter$0.800$0.800$600.00
Kimi K2 Instructopenrouter$0.570$2.300$687.00
Llama 3.3 70B Instructtogether$1.040$1.040$780.00
DeepSeek R1openrouter$0.700$2.500$795.00
Mixtral 8×22B Instructopenrouter$2.000$6.000$2100.00

Self-hosting comparison: at typical utilisation, a single RTX 4090 (~$400/mo amortised) breaks even against hosted 7B pricing around 2B tokens/month, and against hosted 70B pricing around 200M tokens/month. See /hardware.