One API.
100+ LLMs.
Smart Routing.
Built for agents. Cheap when it’s easy, frontier when it’s not. Start free — Pro $99 when you scale.
curl -fsSL https://yieldingbear.com/install.sh | bash100+ LLMs. Smart Routing.
Right model every request — by cost, capability, and speed.
Grizzly 1.0G Lite
$0.15/1M
GPT-4o-mini
$0.15/1M
Gemini 2.0 Flash
$0.10/1M
Claude 3.5 Haiku
$0.80/1M
DeepSeek V3
$0.07/1M
Llama 3.1 8B
$0.04/1M
Every call
routed to the most efficient model
100+
LLMs available through unified API
~200ms
Average response time with smart routing
For OpenClaw & Hermes Agents
Agents that stop overpaying
Hundreds of calls a day. One key. 100+ models. Zero agent refactor.
OpenClaw agents
Discord ops, mobile builds, customer support
One env var. Discord, builds, support, and reviews route automatically.
Hermes agents
Deep research, multi-step investigations, code gen
Point Hermes at our endpoint. Lookups stay cheap; frontier only on hard steps.
How it works for agents
Install the skill
Run install yieldingbear to add the Yielding Bear unified API to any agent session.
Set your API key
Add YIELDINGBEAR_API_KEY — routing is automatic
Save on every call
Simple tasks → Llama 3B. Hard reasoning → Claude 70B. No prompt changes.
* Illustrative example only. Actual costs depend on traffic mix, model selection, and routing tier. Not a guarantee of savings.
Cost Calculator
What-If Cost Comparison
Adjust your monthly volume, the model you're using, and your input/output split. See a blended-rate comparison — not a savings guarantee.
Single Provider
Claude 3.7 Sonnet
$3.00/1M in · $15.00/1M out
$630.00
per month
Yielding Bear Unified API
Smart-routed blended rate
$0.04/1M in · $0.12/1M out
$5.20
per month
Projected monthly delta*
$624.80*
* Indicative what-if comparison only. Yielding Bear's published rate is a blended figure assuming a typical cheap/premium mix; actual results vary with traffic shape, model selection, and routing tier. Not a savings guarantee.
Paths
Start with the API. Services only if you need them.
For Agents
OpenClaw & Hermes. One key.
Auto-route every call. Scale on Grizzly Pro — $99/mo, 25M tokens.
Add to agentAPI & builders
One endpoint. 100+ LLMs.
Drop-in OpenAI-compatible API. Caching, evals, smart routing.
See featuresServices (optional)
Need engineers in the loop?
SMB builds and enterprise FDE — only if you want embedded help.
ServicesReady when you are. Start Free.
Free key for builders and agents. Grizzly Pro $99/mo when you scale. Services only if you need engineers.