# Which models each coding agent runs on

We checked 30 coding agents against their makers' own pages. 22 run on Claude, 24 run on GPT, 17 run open-weight models and 19 take your own key.

| Product | Claude | GPT | Open models | BYOK | Checked |
| --- | --- | --- | --- | --- | --- |
| [Aider](https://theagentsindex.com/aider) | Yes | Yes | Yes | Yes | 2026-09-30 |
| [Augment Code](https://theagentsindex.com/augment-code) | Yes | Yes | Partly | Partly | 2026-10-22 |
| [Bolt](https://theagentsindex.com/bolt-new) | Not checked | Not checked | No | Partly | 2026-09-11 |
| [Claude Code](https://theagentsindex.com/claude-code) | Yes | No | No | Yes | 2026-09-02 |
| [Cline](https://theagentsindex.com/cline) | Yes | Yes | Yes | Yes | 2026-09-12 |
| [CodeRabbit](https://theagentsindex.com/coderabbit) | Yes | Yes | No | Partly | 2026-09-02 |
| [Codex CLI](https://theagentsindex.com/codex-cli) | No | Yes | Yes | Yes | 2026-09-02 |
| [Cursor](https://theagentsindex.com/cursor) | Yes | Yes | Partly | Yes | 2026-09-02 |
| [Devin](https://theagentsindex.com/devin) | Yes | Yes | Yes | Partly | 2026-09-02 |
| [Devin Desktop](https://theagentsindex.com/windsurf) | Partly | Partly | Partly | No | 2026-09-03 |
| [Factory](https://theagentsindex.com/factory-ai) | Yes | Yes | Yes | Yes | 2026-09-02 |
| [Gemini Code Assist](https://theagentsindex.com/gemini-code-assist) | No | No | No | Partly | 2026-09-02 |
| [GitHub Copilot](https://theagentsindex.com/github-copilot) | Yes | Yes | Yes | Yes | 2026-09-02 |
| [Google Antigravity CLI](https://theagentsindex.com/antigravity-cli) | Partly | Partly | Partly | No | 2026-10-22 |
| [goose](https://theagentsindex.com/goose) | Yes | Yes | Yes | Yes | 2026-10-23 |
| [Juggler](https://theagentsindex.com/juggler) | Yes | Yes | Yes | Yes | 2026-09-17 |
| [Junie](https://theagentsindex.com/junie) | Yes | Yes | Yes | Yes | 2026-09-18 |
| [Kilo Code](https://theagentsindex.com/kilo-code) | Yes | Yes | Yes | Yes | 2026-09-02 |
| [Letta](https://theagentsindex.com/letta) | Yes | Yes | Yes | Yes | 2026-09-02 |
| [Modurian](https://theagentsindex.com/modurian) | Not checked | Yes | Not checked | No | 2026-10-09 |
| [Muse Code](https://theagentsindex.com/muse-code) | No | No | No | Partly | 2026-09-20 |
| [OpenCode](https://theagentsindex.com/opencode) | Yes | Yes | Yes | Yes | 2026-10-21 |
| [OpenHands](https://theagentsindex.com/openhands) | Yes | Yes | Yes | Yes | 2026-09-21 |
| [Orbi](https://theagentsindex.com/orbi) | Partly | Yes | Yes | Yes | 2026-10-14 |
| [Replit Agent](https://theagentsindex.com/replit-agent) | Yes | Yes | Partly | Partly | 2026-09-02 |
| [Warp](https://theagentsindex.com/warp) | Yes | Yes | Yes | Yes | 2026-09-03 |
| [WTAgent](https://theagentsindex.com/wtagent) | Yes | Yes | Partly | Partly | 2026-09-21 |
| [Zed](https://theagentsindex.com/zed) | Yes | Yes | Yes | Yes | 2026-09-29 |
| [Zencoder](https://theagentsindex.com/zencoder) | Yes | Yes | Partly | Yes | 2026-09-09 |
| [zot](https://theagentsindex.com/zot) | Yes | Yes | Yes | Yes | 2026-09-28 |

"Checked" is the oldest answer in the row.

- **Claude**: Runs on Anthropic's Claude models.
- **GPT**: Runs on OpenAI's GPT models.
- **Open models**: Runs open-weight models, hosted by the maker or on your own machine.
- **BYOK**: Takes your own API key, inference or cloud account.

## The "Partly" answers

- **Augment Code, Open models**: Open-weight families appear as vendor-hosted choices through inference providers, but no page documents pointing the product at weights you host yourself. ([source](https://docs.augmentcode.com/models/available-models), 2026-10-22)
- **Augment Code, BYOK**: You can supply your own compute via daemons and encryption keys via CMEK, but inference is resold at provider list price plus a fee, not run on your own model keys. ([source](https://www.augmentcode.com/security), 2026-10-22)
- **Bolt, BYOK**: Bring-your-own-cloud is an Enterprise deployment option; no tier lets you supply your own model API keys or inference provider. ([source](https://bolt.new/enterprise), 2026-09-11)
- **CodeRabbit, BYOK**: Bring-your-own inference exists only in the Enterprise self-hosted deployment, where the agent sends prompts to your own LLM account; hosted plans use CodeRabbit's providers. ([source](https://docs.coderabbit.ai/self-hosted/overview), 2026-09-15)
- **Cursor, Open models**: All inference is hosted: the catalogue includes GLM 5.2 from Z.ai and Kimi K3 from Moonshot, but there is no path to point Cursor at open weights you run. ([source](https://cursor.com/docs/models-and-pricing), 2026-09-02)
- **Devin, BYOK**: Your own AWS KMS key encrypts data at rest, but only on the Enterprise Assured deployment; no bring-your-own-inference is documented. ([source](https://docs.devin.ai/enterprise/security-access/security/customer-managed-keys), 2026-09-02)
- **Devin Desktop, Claude**: Claude is a premium model: the plan table marks premium models absent on Free and present from Pro upward; the model table lists Opus, Sonnet and Haiku variants. ([source](https://devin.ai/pricing), 2026-09-03)
- **Devin Desktop, GPT**: Same gate as Claude: OpenAI frontier models come with Pro and above, while Free is marked "Limited model availability" with premium models crossed out. ([source](https://devin.ai/pricing), 2026-09-03)
- **Devin Desktop, Open models**: Open-weight models are hosted by Cognition and included from Pro; the model cost table carries DeepSeek, Moonshot (Kimi), Z.ai (GLM) and Nvidia entries. You cannot point it at your own weights. ([source](https://devin.ai/pricing), 2026-09-03)
- **Gemini Code Assist, BYOK**: Your key is an overflow path, not the billing model: once the daily agent quota is spent you can set geminicodeassist.geminiApiKey to a Gemini or Vertex AI key. Inference stays on Google. ([source](https://docs.cloud.google.com/gemini/docs/codeassist/use-agentic-chat-pair-programmer), 2026-09-02)
- **Google Antigravity CLI, Claude**: Claude Opus and Sonnet 5.5 are selectable, but only on paid Google AI Pro, Ultra or Enterprise; the free tier's Claude 4.6 entries are flagged for removal. ([source](https://antigravity.google/docs/models), 2026-10-22)
- **Google Antigravity CLI, GPT**: No OpenAI GPT model is offered; the only GPT-named entry is the open-weight GPT-OSS-120b, which the table marks for removal and excludes from Enterprise. ([source](https://antigravity.google/docs/models), 2026-10-22)
- **Google Antigravity CLI, Open models**: One open-weight model, GPT-OSS-120b, is selectable on consumer plans, and the same table dates its removal, leaving no standing open-weight option. ([source](https://antigravity.google/docs/models), 2026-10-22)
- **Muse Code, BYOK**: You supply your own Meta Model API key, including in CI from a secret store, but inference still runs on Meta's hosted endpoint and no third-party key or own-cloud option is documented. ([source](https://dev.meta.ai/docs/muse-code/auth), 2026-09-20)
- **Orbi, Claude**: The vendor states Orbi can wrap Claude Code as the coding engine inside its delivery line, but no Anthropic entry appears in the published provider template catalogue, so it is a claim without a configuration recipe. ([source](https://orbi.build/compare/claude-code/), 2026-10-14)
- **Replit Agent, Open models**: Open-source model providers are a real but second-class category for Agent: they exist as a provider policy and are off unless an admin turns them on. ([source](https://docs.replit.com/features/collaboration/enterprise-model-controls), 2026-09-02)
- **Replit Agent, BYOK**: You can supply provider keys for models your own app calls, but the inference behind Agent itself is fixed to Replit's infrastructure. ([source](https://docs.replit.com/help/agent-and-ai), 2026-09-22)
- **WTAgent, Open models**: Providers include DeepSeek, Kimi and GLM, whose weights are published openly, but WTAgent drives their hosted web chat rather than running any weights locally. ([source](https://github.com/XiXian42/wtagent#quick-start), 2026-09-21)
- **WTAgent, BYOK**: You bring your own inference, but as a signed-in web chat account in a dedicated Chrome profile rather than an API key or your own cloud. ([source](https://xixian42.github.io/wtagent/), 2026-09-21)
- **Zencoder, Open models**: Open-weight models are not sold in the managed catalogue; you reach them by declaring your own Ollama or vLLM endpoint in settings.json and paying for that inference yourself. ([source](https://docs.zencoder.ai/clis/custom-agent), 2026-09-09)

How we check listings: [methodology](https://theagentsindex.com/methodology/).

Source: The Agents Index, https://theagentsindex.com/data/coding-agent-models/