---
title: "Model Configuration"
description: "Configure AI models in Cody CLI — 9 coding models, 4 free tier, context windows, tool support, and switching methods."
canonical: "https://docs.ainative.studio/docs/cody-cli/model-config"
last-updated: "2026-10-22T17:48:46.689Z"
---

# Model Configuration

Source: https://docs.ainative.studio/docs/cody-cli/model-config

> Configure AI models in Cody CLI — 9 coding models, 4 free tier, context windows, tool support, and switching methods.

# Model Configuration

Cody CLI ships with 9 top coding models via the AINative gateway. All models support tool use (file read/write, bash, search, agents).

## Available Models

| Model ID | Provider | Tier | Context | Benchmark | Pricing |
|----------|----------|------|---------|-----------|---------|
| `deepseek-4-flash` | DigitalOcean | Free | 131K | 79% SWE-Bench | Free |
| `kimi-k2` | DigitalOcean | Free | 131K | 80.2% SWE-Bench | Free |
| `qwen3-coder-flash` | DigitalOcean | Free | 131K | — | Free |
| `llama-3.3-70b-instruct` | Meta | Free | 131K | — | Free |
| `qwen-coder-32b` | Hugging Face | Professional | 131K | — | $0.28/$1.10 per MTok |
| `glm-5` | NVIDIA | Professional | 131K | — | Usage-based |
| `kimi-k2-thinking` | NVIDIA | Professional | 131K | — | Usage-based |
| `claude-sonnet-4.5` | BYOK | Enterprise | 200K | — | $3/$15 per MTok |
| `claude-opus-4` | BYOK | Enterprise | 200K | — | $15/$75 per MTok |

### Defaults

- **Free tier**: `deepseek-4-flash` — best free coding model (79% SWE-Bench)
- **Paid tier**: `kimi-k2` — best open-source coding model (80.2% SWE-Bench)

### BYOK Models

`claude-sonnet-4.5` and `claude-opus-4` require your own API key (Bring Your Own Key). These are routed through the AINative gateway but billed at the upstream provider's rates.

## Selecting a Model

### Command-line flag

```bash
cody --model kimi-k2
```

### Interactive model picker

Run `/model` inside an interactive session to switch models on the fly. Models are filtered by your subscription tier.

### Inline config

```bash
/config model=kimi-k2
```

### Settings file

Add to `~/.cody/settings.json`:

```json
{
  "model": "kimi-k2"
}
```

## Context Windows

Each model has a maximum context window. Cody automatically manages context — when a conversation approaches the limit, older turns are summarized to stay within bounds. You don't need to manage this manually.

| Context Size | Models |
|-------------|--------|
| 131K tokens | deepseek-4-flash, kimi-k2, qwen3-coder-flash, llama-3.3-70b-instruct, qwen-coder-32b, glm-5, kimi-k2-thinking |
| 200K tokens | claude-sonnet-4.5, claude-opus-4 |

## Tool Support

All 9 models in the registry support tool use:

- File read, write, edit
- Bash command execution
- Grep, glob, web search
- Agent spawning (up to 5 levels)
- MCP server tools

## Fast Mode

Toggle fast mode with `/fast` in a session, or launch with:

```bash
cody --fast
```

Fast mode uses the same model with faster output — it does not downgrade to a smaller model.

## Model Registry

The CLI maintains a static fallback registry of 9 models. On startup, the live catalog from `api.ainative.studio` overrides the static list — so new models appear automatically as they're added to the platform, without a CLI update.