Take back control of your enterprise AI spend.Run BiOS for enterprise AI training, serverless inference, evaluation, data generation and continuous improvement.
Save up to 70% on AI cost
Build with leading models
Claude Haiku 5.5
DeepSeek V4.1 Flash 1017
Run BiOS AdaptiveCChat LatestClaude Opus 5Claude Opus 5.5Claude Sonnet 5Claude Sonnet 5.5DeepSeek V4 FlashDeepSeek V4 Flash 0731DeepSeek V4 ProDeepSeek V4 Pro 0813DeepSeek V4.1 FlashGGLM-5.2GGLM-5.3GGLM-5.3-Flash
GPT-4.1GPT-4.1 MiniGPT-4.1 nanoGPT-4oGPT-4o MiniGPT-5GPT-5 MiniGPT-5 nanoGPT-5.1GPT-5.4GPT-5.4 MiniGPT-5.4 nanoGPT-5.5GPT-5.6 LunaGPT-5.6 SolGPT-5.6 TerraGPT-6 AstraGPT-6 LunaGPT-6 Sol
Kimi K2.7 CodeKimi K3
MiniMax M3o3o3-minio4-mini
Qwen3.5 397B-A17BQwen3.8 2.4T-A95BZero-Log by Design
We don't retain or store your data. Prompts and responses are processed in memory and discarded the moment the request completes.
Nothing Written Down
Prompts and responses live in memory for the duration of the request. No request logs, no content store, no archive.
Nothing to Leak
We never train on your data, and there is no stored copy to breach, subpoena or misuse. What was never kept cannot be lost.
Metering, Not Logging
We count tokens to bill you accurately. That count is all that exists afterwards -- never what you sent or what came back.
What it costs
See what it costs to run serverless inference on Run BiOS
Choose a model available through Run BiOS
Not sure which model? Run BiOS Adaptive chooses for you
Serverless inference for leading AI models
Run the models available in your Run BiOS console through one compatible API. Current charges and context windows come from the same catalog.
| Model | Context | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|---|
| runbios/bios-adaptive | 1M | $0.44 to $1.25 | $0.14 | $1.32 to $4.00 |
| deepseek/deepseek-v4.1-flash | 1M | $0.30 | $0.03 | $1.20 |
| anthropic/claude-opus-5-5 | 1M | $3.80 | $0.19 | $19.00 |
| anthropic/claude-sonnet-5-5 | 1M | $1.90 | $0.095 | $9.50 |
| anthropic/claude-haiku-5-5 | 1M | $0.095 | $0.0095 | $0.475 |
| z-ai/glm-5.3-flash | 1M | $0.15 | $0.03 | $0.50 |
| z-ai/glm-5.3 | 1M | $1.40 | $0.26 | $4.40 |
| deepseek/deepseek-v4-pro-0813 | 128K | $1.40 | $0.14 | $3.40 |
| anthropic/claude-opus-5 | 1M | $4.75 | $0.475 | $23.75 |
| openai/gpt-6-astra | 266K | $10.00 | $1.00 | $50.00 |
| openai/gpt-6-sol | 266K | $2.00 | $0.20 | $10.00 |
| openai/gpt-6-luna | 266K | $0.10 | $0.01 | $0.50 |
| minimax/minimax-m3 | 128K | $0.30 | $0.03 | $1.20 |
| openai/gpt-5.4-mini | 266K | $0.75 | $0.075 | $4.50 |
| anthropic/claude-sonnet-5 | 1M | $1.90 | $0.19 | $9.50 |
| deepseek/deepseek-v4-flash | 128K | $0.10 | $0.01 | $0.25 |
| deepseek/deepseek-v4-flash-0731 | 128K | $0.10 | $0.01 | $0.25 |
| deepseek/deepseek-v4-pro | 128K | $1.40 | $0.14 | $3.40 |
| moonshotai/kimi-k3 | 1M | $3.00 | $0.30 | $15.00 |
| z-ai/glm-5.2 | 1M | $1.40 | $0.14 | $3.40 |
| qwen/qwen3.5-397b-a17b | 256K | $0.50 | $0.05 | $3.40 |
| moonshotai/kimi-k2.7-code | 128K | $0.80 | $0.08 | $3.40 |
| deepseek/deepseek-v4.1-flash-1017 | 1M | $0.20 | $0.02 | $0.60 |
| openai/gpt-5.6-luna | 266K | $0.20 | $0.02 | $1.20 |
| openai/gpt-5.6-sol | 266K | $4.00 | $0.40 | $20.00 |
| openai/gpt-5.6-terra | 266K | $2.00 | $0.20 | $12.00 |
| openai/gpt-4.1-mini | 1M | $0.40 | $0.10 | $1.60 |
| openai/gpt-4o-mini | 125K | $0.15 | $0.075 | $0.60 |
| openai/gpt-4.1-nano | 1M | $0.10 | $0.025 | $0.40 |
| openai/gpt-5.5 | 266K | $5.00 | $0.50 | $30.00 |
| openai/gpt-4o | 125K | $2.50 | $1.25 | $10.00 |
| openai/gpt-5-mini | 266K | $0.25 | $0.025 | $2.00 |
| openai/gpt-5.4 | 266K | $2.50 | $0.25 | $15.00 |
| openai/gpt-5-nano | 266K | $0.05 | $0.005 | $0.40 |
| openai/gpt-5 | 266K | $1.25 | $0.125 | $10.00 |
| openai/gpt-4.1 | 1M | $2.00 | $0.50 | $8.00 |
| qwen/qwen3.8-2.4t-a95b | 1M | $2.00 | $0.20 | $6.00 |
| openai/chat-latest | 266K | $5.00 | $0.50 | $30.00 |
| openai/gpt-5.1 | 266K | $1.25 | $0.125 | $10.00 |
| openai/gpt-5.4-nano | 266K | $0.20 | $0.02 | $1.25 |
| openai/o3 | 195K | $2.00 | $0.50 | $8.00 |
| openai/o4-mini | 195K | $1.10 | $0.275 | $4.40 |
| openai/o3-mini | 195K | $1.10 | $0.55 | $4.40 |
USD per 1M tokens. Current Run BiOS charges are shown, including valid promotions. Banded charges remain ranges. Catalog read 19/10/2026.
Agent integrations
Works with your agent stack
Run BiOS connects to the frameworks your team already uses through one OpenAI-compatible API and familiar SDKs.
Custom models
Serve a model you trained, on a GPU of its own
Fine-tuning produces weights you own. A finished checkpoint can go straight onto a dedicated endpoint without leaving the platform.
Custom Model Endpoints
Serve trained enterprise models through the same OpenAI-compatible API as the managed catalog. Dedicated endpoints provide isolated capacity and per-second billing.
Adapters serve themselves
A LoRA or QLoRA adapter is served with its base model automatically, with no manual merge step.
The route matches the model
Chat, completion, embedding and reranker models each expose the matching OpenAI route.
Sized to expected traffic
Light traffic uses the minimum capacity for the model. Heavy traffic adds GPUs for concurrency.
Memory is yours to tune
bf16 or fp8, with KV cache compression to fit more concurrent requests on the same card.
Run BiOS Conscious Loop
Enterprise AI that improves with every approved cycle.
The Conscious Loop turns approved production signals into curated data, trains the next model, evaluates it against enterprise goals and promotes it when it performs better. Every cycle runs inside your environment on your schedule.
- Curated enterprise data
- Evaluation before promotion
- You own every version
Run BiOS Adaptive
One endpoint. Every frontier model. Zero model-ops.
Adaptive routes each request to the model that fits while balancing quality, speed and budget on per-token pricing with a published ceiling.
Which one you need
When to fine-tune, and when not to
Fine-tuning costs more than a serverless call and takes longer to get right. Plenty of workloads should start on serverless and stay there. Here is how to tell which side you are on.
Stay on serverless inference
A general-purpose model already fits the work, or the workflow is still being defined.
- You are validating an idea or shipping a first version
- Your prompts still change week to week
- Traffic is spiky, seasonal or low volume
- An open model in the catalog already hits the accuracy you need
- You have no labelled examples of the output you want
Fine-tune your own model
A general-purpose model gets close, but is consistently wrong in a way you can describe.
- You have hundreds or thousands of examples of the output you want
- You need a smaller, efficient model to perform one specialized job well
- Your domain uses specialized legal, financial or internal language
- Format or tone has to be right on every single call
- You need the weights to belong to you
Explore our managed LLM training platform or read our open-source model fine-tuning guides.
Enterprise
Run the complete enterprise AI stack inside your environment.
Deploy enterprise inference, fine-tuning, evaluation, data generation and the Conscious Loop in your cloud or data center. Your data, model weights and operational controls stay within your boundary while the Run BiOS team operates the stack.
Start with either one
Call a production model through the serverless API, or train your own on dedicated GPUs. Two products, one account, no commitment on either.
Serverless per million tokens · Fine-tuning from $0.42/hr · Your weights stay yours