One endpoint.
Live provider scoreboard.
Bring your own keys.
Call Llama, DeepSeek, GPT-OSS, Kimi, and more through a single OpenAI-compatible endpoint. Tesseract routes every request to the fastest and cheapest provider — across the accounts you already pay for. You bring the keys; we bring the routing intelligence.
The routing intelligence behind one endpoint
One OpenAI-compatible endpoint
Point your existing OpenAI client at Tesseract, pick a model, and go. It routes across every provider you have a key for — no per-provider client to maintain.
Bring your own provider keys
Add an API key for Together AI, Groq, Fireworks, Baseten, or OpenRouter. Keys are encrypted at rest, verified with a live test call, and only the last four are ever shown.
A live provider scoreboard
Tesseract benchmarks the same prompt across your connected providers and tracks which is fastest and cheapest per model — the data that powers routing.
Routing on real data
Every request is sent to the best provider under your objective — lowest latency, highest throughput, or lowest cost — using the scoreboard, not a guess.
Test before you integrate
Try any catalog model in the browser playground before you write a line of integration code.
Know when the leaderboard moves
Get notified when a provider degrades or a cheaper one appears for a model you care about.
Bring your keys. Point your client. Ship.
Connect your provider keys
Add an API key for each provider you already pay for. Tesseract encrypts it, verifies it with a live test call, and you only ever see the last four characters.
Point your client at Tesseract
The endpoint is OpenAI-compatible: swap the base URL, pick any catalog model, and your requests route through your own provider keys to the fastest, cheapest backend.
Watch the scoreboard, ship with confidence
Tesseract benchmarks every provider live and routes each request on the result. You pay your providers directly — Tesseract is the $39/mo routing layer on top.
{
"model": "gpt-oss-120b",
"prompt": "Explain gravity in one sentence.",
"results": [
{"provider": "Groq",
"ttft_ms": 89,
"tokens_per_sec": 480,
"cost_per_m": 0.60,
"badges": ["Fastest"]},\n {"provider": "OpenRouter",
"ttft_ms": 145,
"tokens_per_sec": 190,
"cost_per_m": 0.17,
"badges": ["Cheapest"]},\n ]
}One catalog, every serving backend you bring.
Tesseract exposes Llama, DeepSeek, GPT-OSS, Kimi, and Qwen through one OpenAI-compatible endpoint. Connect a key for any provider that serves a model and Tesseract routes to it on your key — benchmarking the same prompt across every backend you have access to. The catalog refreshes nightly from each provider's live model list.
CATALOGUE LAST UPDATED 8h ago · SERVED BY 5/5 PROVIDERS
Llama 3.2 1b Instruct
Llama · 1BLlama 3.2 3b Instruct
Llama · 3BLlama 3.1 8B
Llama · 8BMistral Small 24b Instruct 2501
Mistral · 24BGemma 3 4b It
Google · 4BGPT-OSS 20B
OpenAI · 20BQwen3.5 9B
Qwen · 9BGPT-OSS 120B
OpenAI · 120BDeepSeek V4 Flash
DeepSeek · 671BQwen3 14b
Qwen · 14BQwen3 Coder 30b A3b Instruct
Qwen · 30BQwen3 32b
Qwen · 32BGpt Oss Safeguard 20b
OpenAI · 20BLlama 3.3 70B
Llama · 70BGemma 4 26b A4b It
Google · 26BGemma 4 31b It
Google · 31BQwen 2.5 72B
Qwen · 72BLlama 3.1 70B
Llama · 70BQwen3 Vl 32b Instruct
Qwen · 32BGemma 3 27b It
Google · 27BQwen3 Vl 8b Instruct
Qwen · 8BQwen3 8b
Qwen · 8BQwen3.8 Flash
Qwen · —Qwen3 30b A3b
Qwen · 30BGemma 2 27b It
Google · 27BDeepSeek V3
DeepSeek · 671BQwen2.5 Vl 72b Instruct
Qwen · 72BQwen3 Next 80b A3b Instruct
Qwen · 80BInkling Small
Inkling · —Qwen3 Next 80b A3b Thinking
Qwen · 80BQwen3.5 35b A3b
Qwen · 35BQwen3.7 Plus
Qwen · —Qwen3.6 Plus
Qwen · —Qwen3.6 27b
Qwen · 27BQwen3.8 27b
Qwen · 27BNemotron 3 Ultra 550b A55b
NVIDIA · 550BKimi K2.7 Code
Moonshot · —Qwen3.5 397b A17b
Qwen · 397BKimi K2.6
Moonshot · —Inkling
Inkling · —Qwen3.7 Max
Qwen · —Qwen3.8 2.4t A95b
Qwen · 4TKimi K3
Moonshot · 1TPER-MILLION-TOKEN RATES ARE EACH PROVIDER'S PUBLIC PRICING, SHOWN FOR TRANSPARENCY. YOU PAY YOUR PROVIDERS DIRECTLY; TESSERACT IS A FLAT $39/MO TOOL — NEVER PER-TOKEN METERING.
One tool. One flat monthly price.
Pro is $39/month for the routing and benchmarking tool. You bring your own provider keys and pay your providers directly for usage — Tesseract never marks up inference. Cancel anytime.
Free
Try the routing tool and live scoreboard. No credit card required.
- Connect up to 2 providers with your own keys
- OpenAI-compatible endpoint + routing on real benchmark data
- Live provider scoreboard per model
- Playground to test models
- 1 Tesseract gateway key
- 5 benchmark runs per day
Pro
The routing and benchmarking tool, unlimited. You bring your own provider keys and pay your providers directly for usage.
- Connect unlimited providers with your own keys
- OpenAI-compatible endpoint + routing on real benchmark data
- Live provider scoreboard per model
- Playground to test models
- Up to 5 Tesseract gateway keys
- Unlimited benchmark runs + scheduled benchmarks + alerts
Free tier included. Bring your own provider keys.
Bring your keys. Ship the routing.
Sign up, connect your provider keys, and call any top open model from a single OpenAI-compatible endpoint. Tesseract benchmarks every backend live and routes each request to the fastest, cheapest one — you pay your providers directly.
Get your API key