Try Bifrost Enterprise free for 14 days.
Request access

[ Provider Guide ]

Runway ML Provider on Bifrost

Runway ML provides video generation via an asynchronous task-based API. Bifrost maps the unified video schema to Runway's task API and polls until completion.

Runway provider summary

Video-only provider. Bifrost exposes OpenAI-style /v1/videos endpoints and normalizes task statuses.

Generation modes (auto-detected)

  • Text-to-video: prompt only
  • Image-to-video: prompt + input_reference
  • Video-to-video: prompt + video_uri (gen4_aleph only)

Bifrost statuses: queuedin_progresscompleted / failed. Runway native: PENDING, THROTTLED, RUNNING, SUCCEEDED, FAILED, CANCELLED.

PropertyDetails
DescriptionAsync video generation (text, image, video inputs).
Provider route on Bifrostrunway/<model>
AuthenticationAPI key (RUNWAY_API_KEY)
Bifrost endpointsPOST /v1/videos, GET /v1/videos/{id}, GET /v1/videos/{id}/content, DELETE /v1/videos/{id}

Configuration

Add Runway API keys via provider configuration. See Configuration in Bifrost docs.

curl --location 'http://localhost:8080/api/providers' \
--header 'Content-Type: application/json' \
--data '{
    "provider": "runway",
    "keys": [
        {
            "name": "runway-key-1",
            "value": "env.RUNWAY_API_KEY",
            "models": ["*"],
            "weight": 1.0
        }
    ]
}'

Supported operations

See Supported operations in Bifrost docs.

OperationSupportedUpstream endpoint
Video GenerationYes/v1/text_to_video, /v1/image_to_video, /v1/video_to_video
Video RetrieveYes/v1/tasks/{task_id}
Video DownloadYesvia Retrieve + URL download
Video DeleteYes/v1/tasks/{task_id} (cancel)
Video ListNo-
Video RemixNo-

API reference

1) Video Generation

POST /v1/videos. See Video Generation in Bifrost docs.

ParameterTypeRequiredNotes
modelstringYesRunway model
promptstringYesText description of the video
input_referencestringNoInput image for image-to-video
secondsstringNoDuration in seconds (default: "2")
sizestringNoResolution WxH (e.g. 1280x720); converted to W:H ratio
seedintNoGen models only
audioboolNoEnable audio generation (Veo models only)
video_uristringNoSource video URL for video-to-video (gen4_aleph only)

Extra params

KeyTypeNotes
referencesarrayVideo reference objects [{uri, tag}] for video-to-video
content_moderationobjectContent moderation config
reference_imagesarrayReference image objects for style/asset guidance
curl -X POST http://localhost:8080/v1/videos \
  -H "Content-Type: application/json" \
  -d '{
    "model": "runway/gen4_turbo",
    "prompt": "A cinematic drone shot over mountains at golden hour",
    "seconds": "5",
    "size": "1280x720"
  }'

2) Retrieve, Download, Delete

Poll until status: completed, then download MP4 bytes. DELETE cancels a running task.

OperationEndpointNotes
Get statusGET /v1/videos/{id}Poll until completed
Download contentGET /v1/videos/{id}/contentRaw video bytes (MP4)
Cancel/DeleteDELETE /v1/videos/{id}Cancels running task
# Poll status
curl http://localhost:8080/v1/videos/TASK_ID

# Download MP4
curl http://localhost:8080/v1/videos/TASK_ID/content -o output.mp4

# Cancel task
curl -X DELETE http://localhost:8080/v1/videos/TASK_ID

Unsupported features

FeatureReason
Video listNot offered by Runway API via Bifrost
Video remixNot offered by Runway API via Bifrost

Authoritative references

[ BIFROST FEATURES ]

Open Source & Enterprise

Everything you need to run AI in production, from free open source to enterprise-grade features.

01 Governance

SAML support for SSO and Role-based access control and policy enforcement for team collaboration.

02 Adaptive Load Balancing

Automatically optimizes traffic distribution across provider keys and models based on real-time performance metrics.

03 Cluster Mode

High availability deployment with automatic failover and load balancing. Peer-to-peer clustering where every instance is equal.

04 Alerts

Real-time notifications for budget limits, failures, and performance issues on Email, Slack, PagerDuty, Teams, Webhook and more.

05 Log Exports

Export and analyze request logs, traces, and telemetry data from Bifrost with enterprise-grade data export capabilities for compliance, monitoring, and analytics.

06 Audit Logs

Comprehensive logging and audit trails for compliance and debugging.

07 Vault Support

Secure API key management with HashiCorp Vault, AWS Secrets Manager, Google Secret Manager, and Azure Key Vault integration.

08 VPC Deployment

Deploy Bifrost within your private cloud infrastructure with VPC isolation, custom networking, and enhanced security controls.

09 Guardrails

Automatically detect and block unsafe model outputs with real-time policy enforcement and content moderation across all agents.

[ SHIP RELIABLE AI ]

Try Bifrost Enterprise with a 14-day Free Trial

[quick setup]

Drop-in replacement for any AI SDK

Change just one line of code. Works with OpenAI, Anthropic, Vercel AI SDK, LangChain, and more.

1import os
2from anthropic import Anthropic
3
4anthropic = Anthropic(
5 api_key=os.environ.get("ANTHROPIC_API_KEY"),
6 base_url="https://<bifrost_url>/anthropic",
7)
8
9message = anthropic.messages.create(
10 model="claude-3-5-sonnet-20241022",
11 max_tokens=1024,
12 messages=[
13 {"role": "user", "content": "Hello, Claude"}
14 ]
15)
Drop in once, run everywhere.