Research Project This is a free AI research project. No warranties, SLAs, or company associations. Learn more
Providers

Seven Providers, Auto-Discovered

Add your API keys and BrainstormRouter auto-discovers every available model. No configuration files, no model lists to maintain.

165
OpenAI
51% of catalog
gpt-4o gpt-4-turbo o1 o3-mini gpt-4o-mini gpt-4.1
68
Google
21% of catalog
gemini-2.5-pro gemini-2.5-flash gemini-2.0-flash gemini-1.5-pro
42
x-AI
13% of catalog
grok-3 grok-3-mini grok-2
26
Anthropic
8% of catalog
claude-opus-4 claude-sonnet-4 claude-haiku-3.5
13
Moonshot
4% of catalog
moonshot-v1-8k moonshot-v1-32k moonshot-v1-128k
5
Perplexity
1.5% of catalog
sonar sonar-pro sonar-reasoning-pro
2
DeepSeek
0.6% of catalog
deepseek-chat deepseek-reasoner

Auto-Routing

Set model="auto" and forget

Thompson sampling learns the optimal model for each task type without manual configuration. Simple tasks route to DeepSeek at $0.000005/req. Complex reasoning routes to Claude Opus at $0.000156/req — a 31x cost difference, chosen automatically.

Variant Strategy Best For
auto Thompson Sampling picks based on learned quality posteriors General workloads
auto:fast Lowest p50 latency model Real-time UX, streaming
auto:floor Cheapest model above quality threshold Bulk processing, classification
auto:best Highest quality regardless of cost Critical reasoning, code review
AUTO-ROUTING 321 models · 7 providers · 4 variants REQUEST model: "auto" THOMPSON SAMPLING UCB1 + posterior Anthropic (26) OpenAI (165) Google (68) COST COMPARISON (Prometheus Test Data) Simple task deepseek-chat $0.000005/req Complex reasoning claude-opus-4 $0.000156/req 31x cost difference VARIANTS auto auto:fast auto:floor auto:best Validated: Project Prometheus stress test · 2026-03-17 · all providers healthy

Observability

Every Response Tells You What Happened

Every response from BrainstormRouter includes intelligence headers that tell you which model was selected, why, what it cost, and whether it came from cache.

HTTP/1.1 200 OK X-BR-Model-Requested: auto X-BR-Model-Resolved: claude-sonnet-4-20250514 X-BR-Provider: anthropic X-BR-Route-Strategy: thompson-sampling X-BR-Estimated-Cost: 0.000042 X-BR-Actual-Cost: 0.000039 X-BR-Efficiency: 1.08 X-BR-Cache-Status: MISS X-BR-Guardian-Status: ok X-BR-Guardian-Overhead-Ms: 0.8

Intelligence

Live Model Leaderboard

Rankings derived from production traffic, updated every 5 minutes. Sort by any dimension to find the right model for your workload.

Provider: Powered by production traffic
Loading rankings...

Optimization

Cost-Quality Frontier

The Pareto frontier shows models where no other option is both cheaper AND higher quality. Points on the line are optimal trade-offs; points below are dominated.

Task:
Loading frontier data...

Try it now

One curl. Auto-routing across 321 models.

curl https://api.brainstormrouter.com/v1/chat/completions \
  -H "Authorization: Bearer br_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Hello"}]
  }'