BerriAI/litellm - GitHub vs Runway
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. | Runway is a creative platform for generating and editing video, images and related media. It is operated by Runway AI, Inc. For an image-to-video experiment, begin with a reference image and a short motion brief, then choose a model available in your account. A generated shot can help explore a scene or campaign direction, but it still needs review for continuity, faces, text and product details before joining a finished sequence. The Free plan provides 125 credits once and 5GB of asset storage. Runway's help page says these deposited credits do not expire, but they do not replenish after spending; a Free account cannot buy additional credits without upgrading. Videos generated on Free carry a watermark. The available free models change, so the initial balance does not guarantee a particular image-to-video model, duration or resolution. Check the current tool selector and the charge shown for the intended generation. Current individual monthly plans are Standard at $15 for 625 credits, Pro at $35 for 2,250 credits and Max at $95 for 9,500 credits. Annual billing displays monthly equivalents of $12, $28 and $76. Standard lists 20GB storage, up to three projects, five parallel video/image generations, no watermarks and 4K upscaling. Pro lists 100GB storage, up to five projects, fifteen parallel generations, a Brand Kit, a custom voice clone and Runway MCP. Max lists 500GB storage, up to ten projects, twenty parallel generations and one-month credit rollover. These are separate plan allowances, not unlimited video-generation promises. The paid model table provides a useful cost example: Gen-4.5 is listed at 60 credits for five seconds. On that setting, ten attempts would use 600 of Standard's 625 monthly credits. That calculation does not measure success rate or include other work, and it does not establish Free access to Gen-4.5. Budget retries and finishing work separately. Model choices and credit prices should be checked again when the project starts. Team and Enterprise have a separate pricing view. Team is shown at $69 per seat per month on monthly billing with a minimum of two users; Enterprise asks customers to contact sales for custom credits and requirements. Compare storage, shared projects, account controls and delivery needs before selecting a team plan. Developer API pricing is also separate from the individual plan comparison. Runway's terms say it does not claim ownership of compliant inputs or outputs and does not restrict commercial use of outputs under the agreement. This does not clear third-party rights or guarantee copyright protection. The terms also describe using content to improve or train models; Enterprise advertises a separate no-training condition, so assess the agreement applicable to your account before submitting confidential assets. We reviewed published product and plan information without benchmarking generated clips. Pika and Vheer offer alternative starting points for short image-to-video experiments with their own credits and export conditions. |
| Category | Developer Tools | Generative Video |
| Rating | No reviews | No reviews |
| Pricing | Open Source | Freemium |
| Starting Price | N/A | Free |
| Plans | — |
|
| Use Cases |
|
|
| Tags | AI gatewayPython SDKLLM routingMCP gatewayvirtual keys | AI video generationimage to videovideo editingcreative productionAI images |
| 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 | ||
| AI video and image generation | ||
| Reference-based image-to-video workflows | ||
| Music, voice and sound effects generation on listed paid plans | ||
| Free tier with 125 one-time credits | ||
| Plan-dependent 4K upscaling and parallel generations | ||
| Shared Team and Enterprise workflows | ||
| Runway MCP on listed Pro and Max plans | ||
| View BerriAI/litellm - GitHub | View Runway | |
Modify This Comparison
Also Compare
Explore more head-to-head comparisons with BerriAI/litellm - GitHub and Runway.