Choosing a Model

Kepler supports a wide range of language models. Which one you should use depends on your task, budget, and whether you bring your own keys.

Platform Default

If you use Kepler with the platform default (no API key needed), you get DeepSeek V4 Flash — a fast, capable model included with your plan. The platform handles routing, caching, and billing automatically.

The platform also manages sub-agents (explorer and planner) which use cheaper, faster models for read-only passes and dedicated reasoning models for planning.

Tier Ladder: Pro / Plus / Max

Kepler has three paid tiers, each with increasing credits and entitlements.

Credits are consumed per token processed through the platform gateway. Different models cost different credit amounts — faster/cheaper models cost fewer credits per token.

BYOK (Bring Your Own Key) lets you connect your own OpenRouter, Anthropic, or OpenAI API key. When BYOK is active, credits are not consumed — your API key is billed directly by the provider.

Fast Model Quotas

On the platform default, sub-agents (explorer, planner) are automatically routed to the most cost-effective model for each role:

• Explorer (read-only search, grep, file listing) — uses a fast, cheap model with large context (e.g., DeepSeek V4 Flash, Gemini 2.5 Flash)
• Planner (architecture design, reasoning) — uses a capable reasoning model (e.g., Claude Sonnet, DeepSeek V4 Pro)

These sub-agent calls are included in your plan’s credits. You can customize which models are used for each role in Settings.

When to Use BYOK

BYOK makes sense when:

• You already have API keys with Anthropic, OpenAI, or OpenRouter
• You want access to specific models not available on the platform default (e.g., Claude Opus, GPT-4.1, Gemini 2.5 Pro)
• You want to use your own billing — credits are not consumed when BYOK is active
• You need direct provider access for latency, compliance, or data residency reasons

Setting up BYOK

1. Go to Settings → API Keys on bahulam.ai
2. Add your API key for the provider you want to use
3. Select the model you want from the available list

You can also set the key via environment variable:

export OPENROUTER_API_KEY="sk-or-v1-..."
kepler

Available Models

The full model list is available in the Settings page and can be filtered by provider, cost, and capability.

Sub-Agent Model Routing

Kepler uses a multi-agent architecture. When you give it a task:

1. Explorer — reads files, searches code, gathers context
2. Planner — designs the approach, considers tradeoffs
3. Executor — writes code, runs tests, applies edits

Each role can use a different model. By default, Explorer uses a fast/cheap model and Planner uses a more capable reasoning model. You can customize these in Settings → Models.

Recommended combinations: