BUILT ON OPEN WEIGHTS

Run AI Models, One API

One inference layer for open-weight AI models — LLMs, diffusion, speech, and vision. Run Qwen, Llama, DeepSeek, Gemma, Flux, Whisper, and other open models through one consistent API.

Start free Browse models →

Run agents anywhere. Route inference to any available GPU. Powered by Grid

Volunteer PCsShare idle compute

Home GPUsPower from home

RTX WorkstationsPro power, shared

Community NodesStronger together

Agent AppsVertical AI · RAG

Developer ServicesAPI · SDK · Playground

Model inference

Edge GPU Network

LLM

Embedding

Rerank

STT

TTS

Image

Video

Vision

Every modality served from a distributed GPU farm.

Volunteer PCsShare idle compute

Home GPUsPower from home

RTX WorkstationsPro power, shared

Community NodesStronger together

Agent AppsVertical AI · RAG

Developer ServicesAPI · SDK · Playground

Model inference

Edge GPU Network

LLM

Embedding

Rerank

STT

TTS

Image

Video

Vision

Every modality served from a distributed GPU farm.

DESKTOP CLIENT

Put your idle GPU on the Grid.

Install OpenAlchemy Engine Desktop and your idle GPU joins Grid — use the API for free, or earn credits at 70% revenue share every time someone else's job runs on your machine. Your call. The dashboard shows live GPU status, loaded models, queue, and logs.

OpenAlchemy Engine — v0.3.0

Dashboard — live GPU status, model, queue, and logsSystem info — GPU / CPU / memory / disk

Download for WindowsmacOS ・ Coming soon

OpenAlchemy Engine ・ v0.3.0

PLAYGROUND

Try every modality. One API.

LLMEmbeddingRerankSTTTTSImageVideoVision

LLM (Chat / Instruct)

Chat · Summarize · Code

Standard chat completions endpoint — for chat, summarization, code generation, and tool use.

Read docs →

# 1) discover an online chat model — Grid's set changes constantly,
#    don't hardcode an id in your code.
MODEL=$(curl -s https://api.openalchemy.io/v1/models \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  | jq -r '.data[] | select(.online and .endpoint_type=="chat") | .id' \
  | head -1)

# 2) chat
curl https://api.openalchemy.io/v1/chat/completions \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "X-Project-Id: $YOUR_PROJECT_ID" \
  -H "Content-Type: application/json" \
  -d "{
    \"model\": \"$MODEL\",
    \"messages\": [
      {\"role\": \"user\", \"content\": \"Hello, OpenAlchemy.\"}
    ]
  }"

try it

Try a chat

Type a prompt to try the preview.

Embedding

Search · Similarity · RAG

Turn text into vectors for semantic search, similarity, and RAG pipelines.

Read docs →

curl https://api.openalchemy.io/v1/embeddings \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "X-Project-Id: $YOUR_PROJECT_ID" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "embedding-large-v1",
    "input": "Where is the best ramen in Tokyo?"
  }'

try it

Generate embedding

Enter text to see its embedding vector.

Reranker

Reorder · Relevance scoring

Reorder search results by relevance and lift top-K precision.

Read docs →

curl https://api.openalchemy.io/v1/rerank \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "X-Project-Id: $YOUR_PROJECT_ID" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "reranker-large-v1",
    "query": "Where is the best ramen in Tokyo?",
    "documents": [
      "Ichiran has 24-hour shops in Shibuya.",
      "Tsuta in Sugamo holds a Michelin star.",
      "The Tsukiji market is famous for sushi.",
      "Afuri serves yuzu shio ramen in Ebisu."
    ],
    "top_n": 4
  }'

try it

Try rerank

Query

Ichiran has 24-hour ramen shops in Shibuya, served in solo booths.0.000

Tsuta in Sugamo holds a Michelin star for its soy-based ramen broth.0.000

The Tsukiji outer market is famous for fresh sushi breakfasts.0.000

Afuri serves a light yuzu shio ramen popular in Ebisu and Roppongi.0.000

STT (Speech → Text)

Transcripts · Captions · Notes

Convert speech to text — for transcripts, captions, call analytics, and voice input.

Read docs →

curl

curl https://api.openalchemy.io/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "X-Project-Id: $YOUR_PROJECT_ID" \
  -F "model=stt-large-v3" \
  -F "file=@meeting.m4a" \
  -F "response_format=json"

try it

Try speech recognition

Press Record and speak.

TTS (Text → Speech)

Narration · Readout · Voice agents

Render text as natural-sounding audio — for narration, readouts, and voice agents.

Read docs →

curl https://api.openalchemy.io/v1/audio/speech \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1.0",
    "voice": "alice",
    "input": "OpenAlchemy turns idle GPUs into an open AI inference grid. Run a node on a 4090 or 5090 and earn credits, or call our APIs and pay per token. Open weights, distributed compute."
  }' \
  --output openalchemy_pitch.wav

try it

Try voice synthesis

Text

Voice: Maya

Image (gen / edit)

Generate · Edit · Restyle

Create new images from text or images, and edit or restyle existing ones.

Read docs →

curl

curl https://api.openalchemy.io/v1/images/generations \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "X-Project-Id: $YOUR_PROJECT_ID" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "image-gen-1",
    "prompt": "A neon-lit Tokyo alley at dusk, photorealistic.",
    "size": "1024x1024",
    "n": 1
  }'

try it

Coming soon

Video (gen)

Video gen · Motion synthesis

Generate video clips from text or images — from short social cuts to long-form output.

Read docs →

curl

curl https://api.openalchemy.io/v1/videos/generations \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "X-Project-Id: $YOUR_PROJECT_ID" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "video-gen-1",
    "prompt": "A drone shot flying over Mt. Fuji at sunrise.",
    "duration_seconds": 6,
    "resolution": "1080p"
  }'

try it

Coming soon

Vision (VLM / OCR)

Image understanding · OCR · Docs

Multimodal chat that accepts images, plus document OCR and table extraction.

Read docs →

curl

curl https://api.openalchemy.io/v1/chat/completions \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "X-Project-Id: $YOUR_PROJECT_ID" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vlm-7b",
    "messages": [
      {"role": "user", "content": [
        {"type": "text", "text": "What is in this image?"},
        {"type": "image_url", "image_url": {"url": "https://example.com/receipt.jpg"}}
      ]}
    ]
  }'

try it

Try a chat

Image URL

Prompt

Type a prompt to try the preview.

WHY OPENALCHEMY

Why an API, not local inference?

Anywhere

Your agent runs anywhere, not just on the GPU box

Local runtimes tie inference to one machine. The OpenAlchemy API frees your agent to live on a phone, a Lambda, a cron, a browser — call from anywhere over HTTPS. The GPU stays on Grid.

Cost

Idle GPUs, woken up

Pay for time on aggregated idle capacity from a global pool instead of holding dedicated cloud GPUs. Same throughput, lower unit cost.

Compatibility

Standard API, zero-cost migration

Familiar /v1/chat/completions, /v1/embeddings endpoints — existing SDKs work as-is. Swap the base URL and the API key — that's it.

FOUNDATION

A foundation that holds in production

Industry-standard REST API
Per-project billing and quotas
Per-domain rate limits and access control
Auditable request logs, visible only to project owners

START TODAY

Ready to turn inference cost into something closer to alchemy?

The free tier lets you spin up one project and run your first 1,000 requests with no credit card.

Get started free See pricing

Sign up for updates

Hear about new releases, features, and updates from the OpenAlchemy team.