Modal
Run generative AI models, large-scale batch jobs, job queues, and much more.
Modal supports deploying and scaling a variety of AI models, including language models like LLaMA 2 and Mistral for text generation, Stable Diffusion models for image generation tasks, and allows for custom fine-tuning of models such as Flan-T5. This positions Modal as a versatile platform for a wide range of AI development needs, from text and image processing to specialized model optimization.
Pricing: Per compute
Choosing a serverless GPU platform right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing a serverless GPU platform right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Modal prices by model
Per 1M tokens, read off Modal's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.30 | $0.03 | $1.20 | 2 Nov 2026 | Shared Endpoints, billed per token |
| GLM 5.3 | $1.40 | $0.26 | $4.40 | 2 Nov 2026 | Shared Endpoints, billed per token |
| GLM 5.3 Flash | $0.45 | $0.09 | $1.50 | 2 Nov 2026 | Shared Endpoints, billed per token |
| Kimi K3 | $3.00 | $0.30 | $15.00 | 2 Nov 2026 | Shared Endpoints, billed per token |
Modal Alternatives
Explore 160 products in the Inference APIs category. View all Modal alternatives.
Beam
Open-source serverless GPU cloud with sub-second cold starts and auto-scaling
Replicate
Run and fine-tune open-source models. Deploy custom models at scale. All with one line of code.
Baseten
AI inference platform for deploying and serving ML models with autoscaling and optimized infrastructure
RunPod
The Cloud Built for AI.
Anthropic Claude
Claude API for building AI applications with Opus, Sonnet, and Haiku models
Cohere
Cohere’s world-class LLMs help enterprises build powerful, secure applications that search, understand meaning and co...
Compare
Also listed in
Work on Modal? Feature it at the top of Inference APIs.
Is your product missing?