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
$30.00 / month($1.00 / day)
ProviderInput $/MOutput $/M
Llama 3.2 1Bgroq$0.040$0.040$30.00
Llama 3.1 8B Instructgroq$0.050$0.080$42.00
Llama 3.2 3Bgroq$0.060$0.060$45.00
Phi-3 Mini 4K Instructdeepinfra$0.080$0.080$60.00
Qwen2.5 7B Instructdeepinfra$0.080$0.300$93.00
Mistral Nemo 12Bdeepinfra$0.130$0.130$97.50
Qwen 3 32Bdeepinfra$0.100$0.300$105.00
Llama 4 Scout 17B (16E)groq$0.110$0.340$117.00
DeepSeek Coder V2deepinfra$0.140$0.280$126.00
Llama 3.1 8B Instructtogether$0.180$0.180$135.00
Llama 3.2 11B Visiongroq$0.180$0.180$135.00
Gemma 2 9Bgroq$0.200$0.200$150.00
Mistral 7B v0.3together$0.200$0.200$150.00
Mixtral 8×7B Instructgroq$0.240$0.240$180.00
Llama 4 Scout 17B (16E)together$0.180$0.590$196.50
Llama 3.1 70B Instructdeepinfra$0.230$0.400$198.00
Llama 3.3 70B Instructdeepinfra$0.230$0.400$198.00
Llama 4 Maverick 17B (128E)groq$0.200$0.600$210.00
Qwen2.5 32B Instructdeepinfra$0.250$0.400$210.00
Gemma 2 27Btogether$0.300$0.300$225.00
Phi-4 14Btogether$0.300$0.300$225.00
Qwen2.5 14B Instructtogether$0.300$0.300$225.00
Llama 4 Maverick 17B (128E)together$0.270$0.850$289.50
Phi-3 Medium 14Btogether$0.400$0.400$300.00
Qwen 3 32Btogether$0.400$0.400$300.00
DeepSeek V3deepinfra$0.490$0.890$427.50
Mixtral 8×7B Instructtogether$0.600$0.600$450.00
Qwen 3 235B (A22B)together$0.600$0.600$450.00
Qwen 3 235B (A22B)deepinfra$0.400$1.400$450.00
Llama 3.1 70B Instructgroq$0.590$0.790$472.50
Llama 3.3 70B Instructgroq$0.590$0.790$472.50
Command Rtogether$0.500$1.500$525.00
DeepSeek R1 Distill Llama 70Bgroq$0.750$0.990$598.50
Llama 3.1 405B Instructdeepinfra$0.800$0.800$600.00
Mistral Small 3together$0.800$0.800$600.00
Qwen2.5 Coder 32Btogether$0.800$0.800$600.00
Yi 1.5 34B Chattogether$0.800$0.800$600.00
DeepSeek R1deepinfra$0.550$2.190$658.50
Llama 3.1 70B Instructtogether$0.880$0.880$660.00
Llama 3.3 70B Instructtogether$0.880$0.880$660.00
Llama 3.2 90B Visiongroq$0.900$0.900$675.00
Mixtral 8×22B Instructtogether$1.200$1.200$900.00
Qwen2.5 72B Instructtogether$1.200$1.200$900.00
QwQ 32B Previewtogether$1.200$1.200$900.00
DeepSeek V3together$1.250$1.250$937.50
Kimi K2 Instructgroq$1.000$3.000$1050.00
Kimi K2 Instructtogether$1.000$3.000$1050.00
Llama 3.1 405B Instructgroq$2.150$2.150$1612.50
Jamba 1.5 Largetogether$2.000$8.000$2400.00
Llama 3.1 405B Instructtogether$3.500$3.500$2625.00
DeepSeek R1together$3.000$7.000$2850.00
Command R+together$3.000$15.000$4050.00

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.