Models

Firebender supports the most powerful coding models:

Name	Context
GPT-5.6 Sol gpt-5.6-sol	400K
GPT-5.6 Terra gpt-5.6-terra	400K
GPT-5.6 Luna gpt-5.6-luna	400K
GPT-5.5 gpt-5.5	400K
GPT-5.4 gpt-5.4	400K
GPT-5.4 (Extra High Reasoning) gpt-5.4-xhigh	400K
GPT-5.4 mini gpt-5.4-mini	400K
GPT-5.4 nano gpt-5.4-nano	400K
GPT-5.3-Codex gpt-5.3-codex	400K
GPT-5.3-Codex (Low Reasoning) gpt-5.3-codex-low	400K
GPT-5.3-Codex (Extra High Reasoning) gpt-5.3-codex-extra-high	400K
Claude Sonnet 5 claude-sonnet-5	1.0M
GLM 5.2 glm-5.2	1.0M
Muse Spark 1.1 muse-spark-1.1	128K
Kimi K2.7 Code kimi-k2.7-code	262K
Claude Sonnet 4.6 claude-sonnet-4-6	200K
GPT-5.2-Codex gpt-5.2-codex	400K
Claude Sonnet 4.5 claude-sonnet-4-5-20250929	200K
Claude Opus 4.8 claude-opus-4-8	1.0M
Claude Opus 4.7 claude-opus-4-7	200K
Claude Opus 4.6 claude-opus-4-6	200K
Claude Haiku 4.5 claude-haiku-4-5-20251001	200K
GLM 5.1 glm-5.1	203K
DeepSeek V4 Pro deepseek-v4-pro	1.0M
Qwen3.6 Plus qwen3.6-plus	200K
Gemini 3.1 Pro Preview gemini-3.1-pro-preview	200K
Gemini 3.1 Flash-Lite Preview gemini-3.1-flash-lite-preview	1.0M
Qwen3.7 Plus qwen3.7-plus	131K
MiniMax M2.5 minimax-m2p5	192K
MiniMax M2.7 minimax-m2p7	197K
MiniMax M3 minimax-m3	524K
GLM 5 glm-5	200K
Kimi K2.5 kimi-k2.5	131K
Kimi K2.6 kimi-k2.6	262K
GPT-5.4 (High Reasoning) gpt-5.4-high	400K
GPT-5.3-Codex (High Reasoning) gpt-5.3-codex-high	400K
GLM 4.7 zai-glm-4.7	198K
GLM 4.7 Fast zai-glm-4.7-fast	131K
GLM 4.6 zai-glm-4.6	131K
Gemini 3 Flash Preview gemini-3-flash-preview	1.0M
Claude Sonnet 4 claude-sonnet-4-20250514	200K
Gemini 2.5 Pro gemini-2.5-pro	1.0M
Grok 4.5 grok-4.5	500K
Grok 4.20 grok-4.20	2.0M
Grok 4.3 grok-4.3	1.0M
GPT-5.2 gpt-5.2	400K
GPT-5.2 Codex (High Reasoning) gpt-5.2-codex-high	400K

Scroll to bottom ↓

Changing models

Select model with dropdown:

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:

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

Deep Links

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

Model Pricing

Firebender plans include usage at model provider API rates. For example, $30 of included usage on the Developer plan will be consumed based on your model selection and its price.

Usage limits are shown in editor based on your current consumption. All prices are per million tokens.

Name	Input	Cache Read	Cache Write	Output
GPT-5.6 Sol	$5.00 / $10.00	$0.50 / $1.00	$6.25 / $12.50	$30.00 / $45.00
GPT-5.6 Terra	$2.50 / $5.00	$0.25 / $0.50	$3.12 / $6.25	$15.00 / $22.50
GPT-5.6 Luna	$1.00 / $2.00	$0.10 / $0.20	$1.25 / $2.50	$6.00 / $9.00
GPT-5.5	$5.00 / $10.00	$0.50 / $0.50	—	$30.00 / $45.00
GPT-5.4	$2.50 / $5.00	$0.25 / $0.25	—	$15.00 / $22.50
GPT-5.4 (Extra High Reasoning)	$2.50 / $5.00	$0.25 / $0.25	—	$15.00 / $22.50
GPT-5.4 mini	$0.75	$0.07	—	$4.50
GPT-5.4 nano	$0.20	$0.02	—	$1.25
GPT-5.3-Codex	$1.75	$0.17	—	$14.00
GPT-5.3-Codex (Low Reasoning)	$1.75	$0.17	—	$14.00
GPT-5.3-Codex (Extra High Reasoning)	$1.75	$0.17	—	$14.00
Claude Sonnet 5	$2.00	$0.20	$2.50	$10.00
GLM 5.2	$1.40	$0.26	—	$4.40
Muse Spark 1.1	—	—	—	—
Kimi K2.7 Code	$0.95	$0.19	—	$4.00
Claude Sonnet 4.6	$3.00	$0.30	$3.75	$15.00
GPT-5.2-Codex	$1.75	$0.17	—	$14.00
Claude Sonnet 4.5	$3.00	$0.30	$3.75	$15.00
Claude Opus 4.8	$5.00	$0.50	$6.25	$25.00
Claude Opus 4.7	$5.00	$0.50	$6.25	$25.00
Claude Opus 4.6	$5.00	$0.50	$6.25	$25.00
Claude Haiku 4.5	$1.00	$0.10	$1.25	$5.00
GLM 5.1	$1.40	$0.27	—	$4.40
DeepSeek V4 Pro	$1.74	$0.15	—	$3.48
Qwen3.6 Plus	$0.50	$0.11	—	$3.00
Gemini 3.1 Pro Preview	$2.00 / $4.00	$0.20 / $0.40	—	$12.00 / $18.00
Gemini 3.1 Flash-Lite Preview	$0.25 / $0.25	$0.03 / $0.03	—	$1.50 / $1.50
Qwen3.7 Plus	$0.40	$0.08	—	$1.60
MiniMax M2.5	$0.30	$0.04	—	$1.20
MiniMax M2.7	$0.30	$0.06	—	$1.20
MiniMax M3	$0.30	$0.06	—	$1.20
GLM 5	$1.00	$0.21	—	$3.20
Kimi K2.5	$0.60	$0.11	—	$3.00
Kimi K2.6	$0.95	$0.17	—	$4.00
GPT-5.4 (High Reasoning)	$2.50 / $5.00	$0.25 / $0.25	—	$15.00 / $22.50
GPT-5.3-Codex (High Reasoning)	$1.75	$0.17	—	$14.00
GLM 4.7	$0.60	$0.31	—	$2.20
GLM 4.7 Fast	$2.25	—	—	$2.75
GLM 4.6	$2.25	—	—	$2.75
Gemini 3 Flash Preview	$0.50	$0.05	—	$3.00
Claude Sonnet 4	$3.00	$0.30	$3.75	$15.00
Gemini 2.5 Pro	$1.25	—	—	$10.00
Grok 4.5	$2.00	$0.50	—	$6.00
Grok 4.20	$2.00 / $4.00	$0.20 / $0.40	—	$6.00 / $12.00
Grok 4.3	$1.25 / $2.50	$0.20 / $0.40	—	$2.50 / $5.00
GPT-5.2	$1.75	$0.17	—	$14.00
GPT-5.2 Codex (High Reasoning)	$1.75	$0.17	—	$14.00