Fine-tune and batch open models on GPUs without managing infrastructure
AI infrastructure rebuilt to cost less
Stage
Not given
Not given
Founded
Not given
2023
Based in
Not given
Not given
Pricing model
Paid
Paid
Pricing
Fine-tuning from $0.15 per 1M training tokens (minimum $0.50 per job). Batch inference from $0.029 per 1M input tokens and $0.049 per 1M output tokens (minimum $0.20 per batch). Credit packs: Pack 1 ($10 for 10 credits), Pack 2 ($25 for 25 credits), Pack 3 ($100 for 100 credits). Custom amounts from
AI API pricing is per generation or per token depending on modality. Image generation ranges from $0.003 to multiple dollars per image depending on model and resolution. Video costs from $0.02 to $0.157 per second. LLM pricing ranges from $0.10 to $10.00 per 1M tokens. Audio generation from $0.00000
Key features
Fine-tune open models with LoRA, QLoRA or DPO methods
Run batch inference on base and fine-tuned models
Evaluate models against their base with custom graders
Download fine-tuned model adapters
Export merged weights of fine-tuned models
MCP server integration for Claude and other clients
OpenAI-compatible HTTP API
Real-time cost quotes before job execution
Per-token pricing with job minimums
Unified API for 400K+ models with single auth and billing
Batch multiple modalities in a single request
REST and WebSockets support with per-task webhooks
Serverless GPU compute billed by the second
Reserved GPU capacity on Sonic Pods
Custom model uploads with LoRAs and ControlNets
Sonic Inference Engine for optimized performance
MCP server, CLI and Skills for agent integration
Enterprise features including Zero Data Retention
ISO 27001 and SOC 2 certified with GDPR compliance
What makes it different
No GPU or infrastructure to manage; agents call the same API you would
Cost quotes before execution; no hidden charges beyond the quote
Download fine-tuned adapters; no hosting fees or endpoints to maintain
Works with Claude Code, Claude Desktop and any HTTP client without MCP dependency
Per-token pricing with no subscription or minimum contract
Up to 10x lower cost per generation than market rates
Complete end-to-end infrastructure owned and operated by Runware
Renewable power with zero water consumption in data centers
Models preloaded across regions for instant delivery
Seamless upgrade path from serverless to dedicated clusters