◆ModelRadar
...

Cost Simulator

Estimate your monthly API costs across all models and providers.

Simulation Parameters

= 10M total tokens/month

70% input30% output

Typical chat: 70% in / 30% out

Disabled

336 offers found

ModelProviderInput costOutput costCache savingsTotal/mo
Whisper Large V3Groq$0.00/mo$0.00/mo—$0.00/mo
Whisper Large V3 TurboGroq$0.00/mo$0.00/mo—$0.00/mo
Gemma 3 27BGoogle AI$0.00/mo$0.00/mo—$0.00/mo
Llama 3.3 70B InstructFree tierOpenRouter$0.00/mo$0.00/mo—$0.00/mo
Devstral 2 123B Instruct 2512NVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
Ministral 14B Instruct 2512NVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
Mistral Large 3 675B Instruct 2512NVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
DeepSeek V3.1 TerminusNVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
Step 3.5 FlashNVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
GLM-4.5ModelScope$0.00/mo$0.00/mo—$0.00/mo
GLM-4.6ModelScope$0.00/mo$0.00/mo—$0.00/mo
Qwen3 30B A3B Thinking 2507ModelScope$0.00/mo$0.00/mo—$0.00/mo
Qwen3 Coder 30B A3B InstructModelScope$0.00/mo$0.00/mo—$0.00/mo
Nova 2 LiteAmazon Nova$0.00/mo$0.00/mo—$0.00/mo
Nova 2 ProAmazon Nova$0.00/mo$0.00/mo—$0.00/mo
FLUX.1-devNVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
Cosmos Nemotron 34BNVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
Llama 3.1 Nemotron 51B InstructNVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
Llama 3.1 Nemotron 70B InstructNVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
Llama 3.1 Nemotron Ultra 253B V1NVIDIA NIM$0.00/mo$0.00/mo—$0.00/mo
Showing 20 of 336 offers