Supported LLMs
AI Assistant provides access to a variety of cloud-based LLMs through the JetBrains AI service and supports locally hosted models. You can also use your own API keys (BYOK) to access third-party models through your existing provider subscriptions.
This flexibility allows you to choose the most suitable model for your tasks – for example, large models for complex codebase operations, smaller models for quick responses, or local models if you prefer to keep your data private.
Cloud-based models
The table below lists models available for selection in AI Assistant:
– these models have reasoning capabilities, meaning they are better suited for tasks that require logical thinking, structured output, or deeper contextual understanding.
– these models can process images, allowing you to add visual context to your request.
Model | Capabilities | Model context window |
|---|---|---|
|
| 200k |
|
| 200k |
|
| 200k |
|
| 200k |
|
| 200k |
|
| 200k |
|
| 1M |
|
| 1M |
|
| 1M |
|
| 1M |
|
| 1M |
|
| 1M |
|
| 400k |
|
| 400k |
|
| 400k |
|
| 400k |
|
| 400k |
|
| 400k |
|
| 400k |
|
| 400k |
|
| 400k |
|
| 1M |
|
| 1M |
|
| 1M |
|
| 128k |
|
| 200k |
|
| 200k |
|
| 200k |
|
| 200k |
|
| 2M |
|
| 2M |
|
| 256k |
| 256k |
- Supported models history
The following table lists AI models supported by AI Assistant, along with the IDE versions in which they became available and, where applicable, the versions in which they were removed.
Model
Available in IDEs starting from version
Removed in version
Claude 4.5 Opus2025.2.x
–
Claude 4.5 Sonnet2025.2.x
–
Claude 4.5 Haiku2025.1.x
–
Claude 4.1 Opus2025.2.x
–
Claude 4 Sonnet2025.1.x
–
Claude 3.7 Sonnet2024.3.x
–
Claude 3.5 Sonnet2024.3.x
2025.3
Claude 3.5 Haiku2024.3.x
2025.3
Gemini 3 Pro2025.1.x
–
Gemini 3 Flash2025.1.x
–
Gemini 2.5 Pro2025.1.x
–
Gemini 2.5 Flash2025.1.x
–
Gemini 2.5 Flash-Lite2025.1.x
–
Gemini 2.0 Flash2024.3.x
–
Gemini 1.5 Pro2024.3.x
2025.1
Gemini 1.5 Flash2024.3.x
2025.1
GPT-5.22025.2.x
–
GPT-5.1-Codex-Max2025.3.x
–
GPT-5.1-Codex2025.3.x
–
GPT-5.1-Codex-Mini2025.3.x
–
GPT-5.12025.1.x
–
GPT-5-Codex2025.3.x
–
GPT-52025.1.x
–
GPT-5 mini2025.1.x
–
GPT-5 nano2025.1.x
–
GPT-4.12025.1.x
–
GPT-4.1 mini2025.1.x
–
GPT-4.1 nano2025.1.x
–
GPT-4o2024.2.x
–
o4-mini2025.1.x
–
o32025.1.x
–
o3-mini2024.3.x
–
o12024.3.x
–
o1-mini2024.3.x
2025.1
Grok-4.1 Fast2025.1.x
–
Grok-4.1 Fast (Non-Reasoning)2025.1.x
–
Grok-42025.1.x
–
Grok Code Fast 12025.1.x
–
Local models
AI Assistant supports a selection of models available through Ollama, LM Studio, and other OpenAI-compatible endpoints like llama.cpp or LiteLLM. These models are optimized for local use, enabling powerful AI capabilities without the need for cloud access.
The default model context window for local models is set to 64 000 tokens. If needed, you can adjust this value in the settings.
For more information about setting up local models, refer to Use custom models.
Bring Your Own Key (BYOK)
AI Assistant supports the Bring Your Own Key approach, so if you already have an account with a specific AI provider and want to use its models, you can configure the connection in .
For more information, refer to Use custom models.