Modal
Serverless
Modal is an AI infrastructure platform that provides fully managed inference for open-weight models through Shared Endpoints with per-token pricing and OpenAI-compatible APIs. Users can also choose autoscaling Dedicated Endpoints for high performance on dedicated infrastructure.
Features
OpenAI Compatible
Streaming
Batching
Fine-tuning
Embeddings
Vision
Audio
Function Calling
JSON Mode
Compliance
SOC 2
HIPAA
GDPR
Pricing Model
per tokenDetails
Models 10
API Base
https://inference.us-west.modal.direct/v1 GPU CloudLLM Inference
Model Catalog (10)
| Model | Type | Input $/1M | Output $/1M | Context | Speed | Status |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash DeepSeek | llm | $0.300 | $1.20 | 1.0M | — | |
| DeepSeek V4.1 Flash DeepSeek 1017 | llm | $0.250 | $1.00 | 1.0M | — | |
| GLM 5.3 Z.ai | llm | $1.40 | $4.40 | 1.0M | — | |
| GLM 5.3 Flash Z.ai | llm | $0.450 | $1.50 | 1.0M | — | |
| GLM 5.3 Flash Z.ai NVFP4 | llm | $0.150 | $0.500 | 1.0M | — | |
| Inkling Thinking Machines NVFP4 | llm | $1.20 | $5.00 | 1.0M | — | |
| Kimi K3 Moonshot AI | llm | $3.00 | $15.00 | 1.0M | — | |
| Muse Spark Open Meta NVFP4 | llm | $1.25 | $4.25 | 1.0M | — | |
| Qwen3.8 2.4T A95B Alibaba | llm | $2.00 | $6.00 | 262k | — | |
| Qwen3.8 Max VL Alibaba Thinking | llm | $2.00 | $6.00 | 1.0M | — |
Modal API FAQ
Is the Modal API free?
Not as far as we track: Modal has no free API tier on record. The cheapest option we track is GLM 5.3 Flash at $0.15 in / $0.50 out per 1M tokens.
What is the cheapest Modal model?
GLM 5.3 Flash at $0.15 in / $0.50 out per 1M tokens, based on the 10 models we track for Modal.
How many models does Modal offer?
We track 10 Modal models: 10 LLM.
Is the Modal API OpenAI-compatible?
Yes. Modal exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.