Model Router — AI API Gateway

$ curl https://api.lxg2it.com/v1/chat/completions \
    -H "Authorization: Bearer $KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "standard",
      "prefer": "cheap",
      "messages": [{"role": "user", "content": "Hello"}]
    }'

You pick what matters — the capability tier and the optimisation direction. The router picks the model. When a cheaper option launches or a provider goes down, your requests adapt automatically. No model names to track. No code to change.

You can also pass a specific model name (gpt-4.1, claude-sonnet-4-6) to pin routing and bypass tier selection entirely.

---

Current tiers

economy gemini-2.5-flash · gpt-4.1-mini · o4-mini · claude-haiku-4-5 · grok-3-mini-beta · nvidia.nemotron-nano-3-30b · nvidia.nemotron-nano-9b-v2 · zai.glm-4.7-flash · qwen.qwen3-32b-v1:0 · openai.gpt-oss-120b-1:0 · llama-3.3-70b-versatile · meta-llama/llama-4-scout-17b-16e-instruct · llama3.1-8b · qwen-3-235b-a22b-instruct-2507

standard gemini-2.5-pro · gpt-4.1 · gpt-5.3-chat-latest · gpt-5.3-codex · gpt-5.1-codex-mini · o3 · claude-sonnet-4-6 · grok-3-beta · zai.glm-4.7 · deepseek.v3.2 · mistral.mistral-large-3-675b-instruct · moonshotai.kimi-k2.5 · minimax.minimax-m2.1 · qwen.qwen3-next-80b-a3b · us.meta.llama4-maverick-17b-instruct-v1:0 · us.meta.llama4-scout-17b-instruct-v1:0 · mistral.devstral-2-123b · qwen.qwen3-coder-480b-a35b-v1:0 · nvidia.nemotron-super-3-120b · qwen.qwen3-235b-a22b-2507-v1:0

premium gemini-3.1-pro-preview · claude-opus-4-7 · claude-opus-4-6 · gpt-5.4 · zai.glm-5

Context-window guard: never routes to a model that can't handle your input. Circuit breakers reroute around provider outages automatically.

Available models →

---

Free models, no credit card

Fast models via Groq and Cerebras are routed at no cost — no credits, no card required. Sign up and start making requests immediately. Add credits when you need the full range of premium models.

---

Transparent pricing

A 4% fee on credit deposits. Requests are billed at actual provider market rates — you pay what the model costs, nothing more. Every response includes X-Model-Router-Model and X-Model-Router-Provider headers so you always know exactly what ran and what it cost.

---

Auto-routing

Set model: "auto" and the router analyses your full conversation context — system prompt, code blocks, message history, tool use, reasoning markers — and picks the right tier automatically. No heuristics on individual messages; it reads the whole picture. Every auto-routed response includes X-Model-Router-Auto-Tier and X-Model-Router-Auto-Score headers so you can see exactly why a tier was chosen. How it works →

---

Automatic failover

Circuit breakers detect provider outages and reroute requests in real time. Context-window guards ensure requests never go to a model that can't handle them. Your code doesn't change — routing adapts automatically.

---

You stay in control

Block providers you don't want to fund. Set daily spend limits. Enable auto-recharge so you never hit a wall mid-project. Export request traces to any OTLP backend — Axiom, Grafana, Honeycomb, Datadog.

---

Embeddings included

Same key, same endpoint pattern. embed-small, embed-large, and embed-titan aliases route to the best available embedding model. Batch inputs, optional dimension truncation, billed at input tokens only.

---

Get started

Full documentation →