DeepInfra
DeepInfra
AI
Platform
DeepInfra offers serverless AI inference with a simple API, supporting hundreds of models across text generation, embeddings, and more. Pay-per-token pricing with no upfront commitments.
About DeepInfra
DeepInfra is a cloud inference platform offering cost-effective access to open-source AI models. It provides serverless inference for leading models from Meta, Mistral, Alibaba, and others with competitive token-based pricing.
Available Models(10)
| Model | Input (per 1M) | Output (per 1M) | Type |
|---|---|---|---|
| Qwen2.5 72B Instruct | $23 | $23 | Serverless |
| Qwen2.5 Coder 32B | $20 | $20 | Serverless |
| Qwen2.5 14B Instruct | $10 | $10 | Serverless |
| Qwen2.5 7B Instruct | $3 | $3 | Serverless |
| Qwen2 57B-A14B | $16 | $16 | Serverless |
| Llama 3.1 70B Instruct | $40 | $40 | Serverless |
| DeepSeek V3 | $32 | $89 | Serverless |
| DeepSeek R1 Distill Llama 70B | $70 | $80 | Serverless |
| Mixtral 8x7B | $54 | $54 | Serverless |
| Mistral NeMo Instruct (2407) | $2 | $4 | Serverless |
Company Info
Founded2023
San Francisco, California, United States