Experience-Based Routing

Pick the task. Use the model teams already reach for.

OneInterface routes coding and chat work to high cost-performance models commonly preferred for that kind of task, with transparent cost and fallback behavior.

Open Console View setup

OneInterface Routing Profiles

Experience-based routing layer, not a black-box router

Claude Code
ANTHROPIC_API_KEY=oi_your_api_key \
ANTHROPIC_BASE_URL=https://api.oneinterface.ai \
  claude --bare --model oi/balanced-coder
OpenAI-compatible
curl https://api.oneinterface.ai/v1/chat/completions \
  -H "Authorization: Bearer oi_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "oi/deep-review",
    "messages": [
      { "role": "user", "content": "Review this diff for bugs." }
    ]
  }'

Task Contexts

Routing profiles shaped by real coding and chat workflows.

Users stay in their existing tools and choose the task context. The routing profile reflects what builders typically prefer for that kind of work.

Coding

Cheap Coder

oi/cheap-coder

For teams that usually pick the lowest-cost capable model for small edits, tests, comments, and background agent work.

Common choice: deepseek-v4-flash

Baseline: claude-sonnet-4

Balanced Coder

oi/balanced-coder

For everyday coding tasks where builders usually want a practical balance of quality, speed, and cost.

Common choice: qwen3.6-plus

Baseline: claude-sonnet-4

Deep Review

oi/deep-review

For review and bug-hunting work where users tend to prefer more deliberate reasoning.

Common choice: deepseek-v4-pro

Baseline: claude-opus-4

Long Context

oi/long-context

For repository analysis, large diffs, logs, and multi-file planning where long context matters most.

Common choice: kimi-k2.6

Baseline: claude-sonnet-4

Chat

General Chat

oi/chat

For everyday assistant and conversational workloads where builders want a practical balance of quality, speed, and cost.

Common choice: kimi-k2.6

Baseline: claude-sonnet-4

Fast Chat

oi/chat-fast

For high-volume, latency-sensitive chat where the lowest-cost capable model is preferred.

Common choice: deepseek-v4-flash

Baseline: claude-sonnet-4

Smart Chat

oi/chat-smart

For chat that needs more deliberate reasoning — complex questions, analysis, and nuanced writing.

Common choice: deepseek-v4-pro

Baseline: claude-opus-4

Agent

Fast Agent

oi/agent-fast

For high-volume, latency-sensitive agent loops where the cheapest capable tool-calling model is preferred.

Common choice: qwen3.6-plus

Baseline: claude-sonnet-4

Balanced Agent

oi/agent

For everyday agentic work where builders want a practical balance of tool-calling quality, speed, and cost.

Common choice: kimi-k2.6

Baseline: claude-sonnet-4

Max Agent

oi/agent-max

For agent work that needs more deliberate reasoning — complex multi-step planning and hard tool orchestration.

Common choice: deepseek-v4-pro

Baseline: claude-opus-4

Why This Wedge

Not another model marketplace.

Model-centric products ask developers to compare dozens of IDs. Experience-based routing starts from the job to be done: small edits, daily coding, deep review, or long-context work.

OpenRouter
Model marketplace
User chooses raw model
Broad model access
LiteLLM
Self-hosted gateway
Team owns routing config
Infra teams
OneInterface
Experience-based routing
User chooses the task context
Claude Code, Cursor, Cline

Transparent routing

Usage rows show requested routing profile, actual model, tokens, cost, and estimated savings.

High cost-performance supply

Routing profiles reflect practical model preferences for each coding workflow.

Compatibility first

Works through OpenAI-compatible APIs and the Anthropic Messages proxy for Claude Code.

Start with the default coding flow.

Use oi/balanced-coder for everyday coding work, then switch only when the task needs lower cost, deeper review, or longer context.

Open Console