Name: ModelStack API
Author: ModelStack

OpenAI & Anthropic compatible103 models live

70 chat models and 33 image, video and audio models from 11 providers, behind one OpenAI-compatible API. Provider tiers take up to 80% off, and agent teams only pay for a specialist when a request needs one.

No card required
Official rates or lower
Switch models by changing a string

https://api.modelstack.cc/v1Illustrative request

01Request

POST /v1/chat/completions
{
  "model": "claude-sonnet-5",
  "stream": true,
  "messages": [ … ]
}

02Tier routing

Economy0.20×serving
Standard0.50×standby
Premium1.00×standby

03Provider

200 OKEconomy tier

Claude Sonnet 5$0.60/M in

70
chat & reasoning models: 33
image, video & audio models: 11
providers behind one key: 80%
off at the economy tier

Drop-in compatible

Change one line. Keep the rest.

ModelStack speaks the OpenAI and Anthropic request formats, so your SDK, your streaming code and your tool-calling loop keep working. Point the base URL at us and pick any model by id.

OpenAI and Anthropic request shapesUse either SDK as-is. Chat completions and Messages both work.
Streaming and tool calling pass throughAll chat completion parameters are forwarded — nothing to re-implement.
Swap models by changing a stringClaude to GPT to Gemini to DeepSeek: edit the model id, redeploy nothing.

main.py

1from openai import OpenAI
2 
3client = OpenAI(
4    api_key="sk_...",
5    base_url="https://api.modelstack.cc/v1",  # the only change
6)
7 
8response = client.chat.completions.create(
9    model="claude-sonnet-4-6",
10    messages=[{"role": "user", "content": "Hello"}],
11)

Provider tiers

Same models. Three prices.

Every request is routed through provider tiers, cheapest first, with automatic fallback when one is unavailable. The response is identical on every tier — only the rate changes.

$10.00 of provider usage costs you

01 · Tried first0.20×
Economy
Lowest cost. Tried first on every request.
$2.0080% off
Pays with prepaid or bonus balance
02 · Next in line0.50×
Standard
Balanced value. Next in line when economy is unavailable.
$5.0050% off
Pays with prepaid or bonus balance
03 · Final fallback1.00×
Premium
Official provider APIs with the highest uptime. Final fallback.
$10.00Official rate
Pays with prepaid balance only

Tiers are tried economy → standard → premium. Circuit breakers skip unhealthy providers so the request still succeeds.

How tiers and fallback work

Agent teams

One model id, a whole team behind it.

The coordinator answers routine requests and calls a specialist for the hard ones. Each specialist either advises the coordinator or replies to the user directly.

01Build it on a canvasPick a coordinator model, add specialists from the roster, and set each one’s model, fallback and rules in place.
02Choose who writes the replyAdvise sends a specialist’s answer back to the coordinator to combine. Delegate sends it to the user exactly as written.
03Call it like a modelUse the team id as the model. Same request format, same SDK, same streaming. Each agent bills at its own model’s rate.

model: "my-coding-agent"Agent team

Coordinator answers68% of requests
1. Request
2. Coordinator
3. Reply
Senior Architect advises20% of requests
1. Request
2. Coordinator
3. Senior Architect
4. advisesCoordinator
5. Reply
Reviewer delegates12% of requests
1. Request
2. Coordinator
3. Reviewer
4. delegatesReply

Everything to the specialist: $5/M in
Blended with this split: ~$3.64/M in

Illustrative split for a coding workload. Rates are the models' list input prices.

Media generation

Image, video and audio on the same key.

Generation runs as async jobs: submit, poll, collect output URLs. Same API key, same balance — and available to your agents through MCP.

Image

12 models

Text-to-image, editing and upscaling.

Nano Banana 2 · Nano Banana 2 Lite · Nano Banana Pro · GPT Image 2 · +8 more

Video

18 models

Text-to-video and image-to-video.

Veo 3 · Veo 3 Fast · Veo 3 Lite · Kling 2.6 · +14 more

Audio

10 models

Text-to-speech, plus audio-driven video and lip-sync.

ElevenLabs Turbo 2.5 · ElevenLabs Multilingual v2 · Gemini 3.1 Flash TTS · Gemini 2.5 Pro TTS · +6 more

Model catalog

70 chat models from 11 providers.

Official rates or lower, on every tier. Assign any of them to a coordinator, a specialist, or a plain completion call.

Gemini
Google
13
Claude
Anthropic
12
GPT / o-series
OpenAI
11
Qwen
Alibaba
08
DeepSeek
DeepSeek
07
GLM
Zhipu
06
MiniMax
MiniMax
04
Kimi
Moonshot
04
MiMo
Xiaomi
02
Grok
xAI
02
Step
StepFun
01
All 103 models

Ecosystem

Works where you already work.

Any tool that talks to OpenAI or Anthropic talks to ModelStack. Every one below has a setup guide.

MCP server

Or hand your agent the whole toolbox.

One command connects Claude Code, Cursor or any MCP client. Your agent generates media and calls models on its own, billed to the key you already use.

01Generate media mid-taskYour agent creates images, video and audio itself — no context switch, no separate dashboard.
02Delegate to cheaper modelsHand bulk work to a smaller model through one tool call and keep the expensive one for the hard parts.
03Discover models at runtimeLive catalogs of every model, the parameters each accepts and what it costs.

claude mcp add8 tools

claude mcp add --transport http modelstack \
  https://api.modelstack.cc/mcp \
  --header "Authorization: Bearer $KEY"

generate_image
generate_video
generate_audio
get_generation
upload_media
llm_chat
list_models
list_generation_models
generate_image
generate_video
generate_audio
get_generation
upload_media
llm_chat
list_models
list_generation_models

Same key, same balanceno new quota

Free API key · no card

Start with one line.

103 models the moment you sign up.

Every model.One endpoint.