BerriAI/litellm - GitHub vs Recraft
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. | Recraft is a browser workspace for generating images, editing existing visuals and working with raster or vector graphics. It combines a canvas, style controls and a selection of image models. Start with the kind of change you need: a new composition from a reference, a local correction, a background adjustment or a scalable graphic for a layout. For natural-language reference editing, select an image on the canvas and choose Edit image, or attach a reference in Create and describe the change. The current documentation ties reference support to selected external models, which are included on paid plans. Model limits vary, so inspect the picker before combining several references. Treat consistent subjects and legible text as things to check in the output, not guaranteed results. The live Free plan lists three generations per style per day, three daily uploads and up to two images per generation. It includes basic editing and Recraft models only. Free outputs are public, owned by Recraft and restricted to personal use. The photo-editor marketing page separately advertises up to 30 generations and edits daily; that figure should not replace the specific plan and model limits. Basic costs $12 monthly or $120 billed annually and includes 1,000 credits each month. Pro starts at $20 monthly or $192 annually for 2,000 monthly credits. Teams starts at $22 per seat monthly for 2,000 credits per seat. Prices exclude VAT. Paid plans provide private generations and stated ownership and commercial rights for images made while subscribed. Subscription credits reset each billing cycle; unused subscription credits do not roll over. API units are purchased separately. Private generation describes gallery visibility. The current Terms permit training on inputs and assets by default and provide an account-profile opt-out. Review that preference before uploading confidential work. Keep an authorized original, compare it with the edited result and check the export at the intended size. For scalable artwork, use the vector workflow and verify that the delivered file contains the paths you need; a file extension alone does not establish print readiness. |
| Category | Developer Tools | Image Generation |
| Rating | No reviews | No reviews |
| Pricing | Open Source | Freemium |
| Starting Price | N/A | Free |
| Plans | — |
|
| Use Cases |
|
|
| Tags | AI gatewayPython SDKLLM routingMCP gatewayvirtual keys | image-to-imageimage editingreference imagesinpaintingoutpainting |
| 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 | ||
| Canvas image editing | ||
| Paid natural-language reference edits | ||
| Raster and vector generation | ||
| Reusable styles | ||
| Image upscaling | ||
| Background removal | ||
| Image vectorization | ||
| Separate image API | ||
| View BerriAI/litellm - GitHub | View Recraft | |
Modify This Comparison
Also Compare
Explore more head-to-head comparisons with BerriAI/litellm - GitHub and Recraft.