Skip to main content
Firebender supports the most powerful coding models:
IDNameContext Supported
gpt-5.2GPT-5.2400K Frontier
gpt-5.1-codex-maxGPT-5.1-Codex-Max400K Frontier
claude-sonnet-4-5-20250929Claude Sonnet 4.5200K Frontier
gpt-5.1GPT-5.1400K Frontier
zai-glm-4.6GLM 4.6131K Frontier
gpt-5.2-proGPT-5.2 Pro400K Frontier
claude-opus-4-5Claude Opus 4.5200K Frontier
gemini-3-pro-previewGemini 3 Pro Preview200K Frontier
claude-haiku-4-5-20251001Claude Haiku 4.5200K Frontier
claude-sonnet-4-20250514Claude Sonnet 4200K Frontier
claude-opus-4-1-20250805Claude Opus 4.1200K Frontier
claude-opus-4-20250514Claude Opus 4200K Frontier
gpt-5.1-lowGPT-5.1 (Low Reasoning)400K Frontier
gpt-5.1-highGPT-5.1 (High Reasoning)400K Frontier
gpt-5.1-fastGPT-5.1 (Priority)400K Frontier
gpt-5.1-low-fastGPT-5.1 (Low Reasoning, Priority)400K Frontier
gpt-5.1-high-fastGPT-5.1 (High Reasoning, Priority)400K Frontier
gpt-5.1-codexGPT-5.1 Codex400K Frontier
gpt-5.1-codex-lowGPT-5.1 Codex (Low Reasoning)400K Frontier
gpt-5.1-codex-highGPT-5.1 Codex (High Reasoning)400K Frontier
gpt-5-codexGPT-5 Codex400K Frontier
gpt-5-proGPT-5 Pro400K Frontier
gpt-5GPT-5400K Frontier
gpt-5-fastGPT-5 (Priority)400K Frontier
gpt-5-lowGPT-5 (Low Reasoning)400K Frontier
gpt-5-low-fastGPT-5 (Low Reasoning, Priority)400K Frontier
gpt-5-highGPT-5 (High Reasoning)400K Frontier
gpt-5-high-fastGPT-5 (High Reasoning, Priority)400K Frontier
gpt-5-codex-lowGPT-5 Codex (Low Reasoning)400K Frontier
gpt-5-codex-highGPT-5 Codex (High Reasoning)400K Frontier
claude-sonnet-4-5-1mClaude Sonnet 4.5 (1M)1.0M Frontier
claude-sonnet-4-1mClaude Sonnet 4 (1M)1.0M Frontier
gpt-5-miniGPT-5-mini400K General
gpt-oss-120bGPT-OSS-120b131K General
gpt-4.1GPT-4.11.0M General
claude-3.7-sonnetClaude-3.7 Sonnet200K General
claude-3.5-sonnetClaude-3.5 Sonnet200K General
gemini-2.5-proGemini 2.5 Pro1.0M General
o3OpenAI-o3200K General
o4-miniOpenAI-o4-mini200K General
o3-miniOpenAI-o3-mini200K General
gpt-4oGPT-4o128K General
grok-3Grok-3131K General
deepseekv3Deepseek v3128K General
deepseekr1Deepseek r1164K General
grok-4Grok 4256K General
grok-code-fast-1Grok Code Fast 1256K General
grok-4-fastGrok 4 Fast2.0M General

​
Changing models

Select model with dropdown: Screenshot showing the model picker dropdown in the chat interface
Models can misreport their name and version at runtime. This is because they are often trained on data generated by previous versions of themself or other models.

​
Context Windows

A context window is the maximum span of tokens (text and code) a model can consider at once. The more prompts, files, and responses in a session, the more context is consumed. Firebender intelligently summarizes and shifts context around to balance speed and accuracy. An estimate of tokens used is provided: Screenshot showing the context window usage estimate at the bottom of the chat interface

​
Default Model

Default Model: Firebender attempts to select the best model for each task based on request complexity, model availability, rate limits.

​
Custom model controls and restriction

jetbrains://idea/firebender/chat?model=claude-haiku-4-5-20251001 Read more: Deep Links

​
Commands

Configure in firebender.json with "model": "claude-haiku-4-5-20251001". Read more: Commands

​
Organization restrictions

Companies may not want to support certain models or providers, and can restrict what models their team has access to. Team admins will need to add later models to the list when new models are released by providers. Get started: Model restrictions