Experience-Based Routing

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

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

Open Console View setup

OneInterface Coding Router

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

Four routing profiles shaped by real coding workflows.

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

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-coder-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

Baseline: claude-sonnet-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