BerriAI/litellm - GitHub vs Draw Things
Side-by-side comparison · Updated October 2026
| Description | LiteLLM is an AI gateway and Python SDK from Berrie AI Incorporated, published in the BerriAI GitHub repository. The SDK provides a common interface for model calls inside Python applications. The proxy gateway centralizes access for a team, with virtual keys, model routing, spend tracking, budgets and an administration interface. The official documentation lists support for more than 100 model providers. Supported endpoints and features vary by integration, so verify your model’s streaming, tool-calling, image, audio or embedding requirements. The router supports retries, fallbacks and load balancing; observability integrations can send request data to tools such as Langfuse, LangSmith and OpenTelemetry. LiteLLM also provides an MCP gateway. It can connect upstream servers using Streamable HTTP, SSE or stdio, expose tools through a fixed gateway endpoint, and scope access by key, team or organization. This requires configuring the upstream servers and authentication; the gateway does not automatically grant access to third-party tools. Agent-to-agent integrations are documented separately. The open-source offering has no software license fee for self-hosting. Code outside the enterprise directory is MIT-licensed, while enterprise code has separate terms. Enterprise pricing is quoted by annual gateway request capacity, deployment architecture and support needs, rather than a per-token license charge. Model-provider charges and infrastructure costs still apply. Enterprise adds controls and support such as SSO, SCIM, audit logs and service-level agreements. Compare New API for another self-hosted gateway with provider-channel management and usage accounting. Evaluate a representative workload, inspect request logging and secret handling, test budget and failure behavior, and decide whether SDK integration or a shared gateway best fits your application. | Draw Things is a local AI image and video creation app for iPhone, iPad and Mac. It suits creators who want to choose their models, work with existing images and keep local generation on their own Apple hardware. Its free local workflow does not require a subscription or token allowance. Download the app and the models you need before relying on offline access; optional Cloud Compute is a separate workflow with account and network requirements. Start with a text prompt or an existing image, choose a compatible model and refine the result. The official app listing describes image-to-image, inpainting, outpainting, ControlNet, pose editing and an infinite canvas. You can import community diffusion models and LoRAs, or train LoRAs on-device. The current product also supports image-to-video workflows. These options make it useful for testing visual concepts and editing selected regions, but model choice, available memory and device performance affect what you can practically generate. We have not benchmarked rendering speed or output quality. The provider lists a Free Edition for local compute and a free Community account for Cloud Compute and Lab Hours. Draw Things+ is advertised at US$8.99 per month, with higher cloud limits, custom LoRA uploads and additional cloud features. Numeric cloud quotas are not published on the reviewed pricing page. The US App Store also lists optional Boost Bundles, but check their current in-app entitlements before buying. Enterprise access is available by contacting the provider for organization deployment, on-premise inference and application integration; no public enterprise price is shown. Local and cloud privacy should be considered separately. Draw Things describes local creation as offline and says most creations and data can stay on the device. Its policy documents an optional Apple sign-in identifier for Cloud Compute and subscription transaction information for paid access. Uploaded LoRAs are stored on cloud servers until you delete them or the account. The app release history also mentions Google sign-in, while the policy still describes Apple sign-in; check the current account flow rather than assuming that every sign-in method has identical data handling. The policy says it does not use third-party analytics or advertising frameworks for tracking. Use the official Apple listing for Draw Things, Inc., app ID 6444050820, to distinguish it from similarly named apps. The US listing carries an 18+ age rating. For a first project, use a non-sensitive reference image, confirm the chosen model fits your device and test a modest output before attempting larger images or video. Review imported model, LoRA and source-image licenses before commercial work: free software access does not itself grant rights to every model or generated asset. Draw Things is the stronger fit here when model control and local editing matter; compare a simpler fixed-model generator if you mainly want to turn short text prompts into images. |
| Category | Developer Tools | Art Generator |
| Rating | No reviews | No reviews |
| Pricing | Open Source | Freemium |
| Starting Price | N/A | Free |
| Plans | — |
|
| Use Cases |
|
|
| Tags | AI gatewayPython SDKLLM routingMCP gatewayvirtual keys | local AIimage generationimage-to-imageinpaintingvideo generation |
| Features | ||
| Python SDK for direct application integration | ||
| Shared AI proxy gateway and administration UI | ||
| More than 100 documented model-provider integrations | ||
| Virtual keys, users, teams, budgets and rate limits | ||
| Spend tracking and observability integrations | ||
| Router retries, fallbacks and load balancing | ||
| MCP gateway for Streamable HTTP, SSE and stdio upstreams | ||
| Key, team and organization MCP permissions | ||
| Separate enterprise identity, audit and support features | ||
| Local image generation on iPhone, iPad and Mac | ||
| Offline creation after downloading compatible models | ||
| Image-to-image, inpainting, outpainting and ControlNet | ||
| Infinite canvas and image-to-video workflows | ||
| Imported diffusion models and LoRAs | ||
| On-device LoRA training | ||
| Optional Community and paid Cloud Compute | ||
| View BerriAI/litellm - GitHub | View Draw Things | |
Modify This Comparison
Also Compare
Explore more head-to-head comparisons with BerriAI/litellm - GitHub and Draw Things.