Models
The table below lists all available AI models on Coding Plan, including multiplier rates and context windows.Multiplier is the pricing coefficient compared to the base model. For example: A model with 1.8x multiplier will consume 1.8 times more tokens than a 1x model.
Models Table
| Model | Multiplier | Context Window | Original Price | Discounted Price | Discount |
|---|---|---|---|---|---|
| in Subscription | Pay-as-you-go | Pay-as-you-go | |||
| (per 1M tokens) | (per 1M tokens) | ||||
| claude-haiku-4-5-20251001 | 1x | 200K tokens | 5.00 | 1.00 | -80% |
| claude-sonnet-4-5 (no thinking) | 1x | 200K tokens | 15.00 | 3.00 | -80% |
| claude-sonnet-4-5-20250929 | 1x | 200K tokens | 15.00 | 3.00 | -80% |
| claude-opus-4-5-20251101 | 2x | 200K tokens | 25.00 | 5.00 | -80% |
| gemini-3-pro | 0.8x | 1M tokens | 12.00 | 2.40 | -80% |
| gemini-3-flash | 0.5x | 1M tokens | 3.00 | 0.60 | -80% |
| gpt-5-mini | 0x (free-using) | 128K tokens | - | - | - |
| glm-4.6 | 0x (free-using) | 200K tokens | 2.00 | 0.40 | -80% |
| glm-4.7 | 0x (free-using) | 200K tokens | 2.20 | 0.44 | -80% |
Price format: Input / Output
Model Details
Claude Haiku 4.5
Claude Haiku 4.5
- Model ID:
claude-haiku-4-5-20251001 - Multiplier: 1x (base model)
- Context Window: 200K tokens
- Description: Balanced model between performance and cost, suitable for most daily coding tasks.
Claude Sonnet 4.5 (no thinking)
Claude Sonnet 4.5 (no thinking)
- Model ID:
claude-sonnet-4-5 - Multiplier: 1x (base model)
- Context Window: 200K tokens
- Description: Balanced model between performance and cost, suitable for most daily coding tasks.
Claude Sonnet 4.5 Thinking
Claude Sonnet 4.5 Thinking
- Model ID:
claude-sonnet-4-5-20250929 - Multiplier: 1x
- Context Window: 200K tokens
- Description: Sonnet version with extended thinking capability, providing more accurate results for complex problems.
Claude Opus 4.5 Thinking
Claude Opus 4.5 Thinking
- Model ID:
claude-opus-4-5-20251101 - Multiplier: 2x
- Context Window: 200K tokens
- Description: Opus version with extended thinking, the most powerful for complex multi-step reasoning tasks.
Gemini 3 Pro
Gemini 3 Pro
- Model ID:
gemini-3-pro - Multiplier: 0.8x
- Context Window: 1M tokens
- Description: Google’s flagship model with extremely large 1M tokens context window, suitable for processing large codebases.
Gemini 3 Flash
Gemini 3 Flash
- Model ID:
gemini-3-flash - Multiplier: 0.5x
- Context Window: 1M tokens
- Description: Fast and cost-efficient version of Gemini 3, still maintains 1M tokens context window.
GPT-5 Mini
GPT-5 Mini
- Model ID:
gpt-5-mini - Multiplier: 0x (Free-Using with unlimited usage when subscribing to Coding Plan at VibeCodeCheap)
- Context Window: 128K tokens
- Description: Latest model from OpenAI, good balance between performance and cost.
GLM 4.6
GLM 4.6
- Model ID:
glm-4.6 - Multiplier: 0x (Free-Using with unlimited usage when subscribing to Coding Plan at VibeCodeCheap)
- Context Window: 200K tokens
- Description: GLM generation 4.6 model with good coding capabilities, completely free.
GLM 4.7
GLM 4.7
- Model ID:
glm-4.7 - Multiplier: 0x (Free-Using with unlimited usage when subscribing to Coding Plan at VibeCodeCheap)
- Context Window: 200K tokens
- Description: Latest GLM model with significantly improved performance, completely free.
Choosing the Right Model
Cost Saving
Choose claude-haiku-4-5 (0.5x), gemini-3-flash (0.5x), gpt-5-mini (0.6x) or free models glm-4.6/4.7.
High Performance
Choose claude-opus-4-5-20251101 (2x) or claude-opus-4-5 (1.8x) for complex tasks.
Balanced
Choose claude-sonnet-4-5 (1x) or gemini-3-pro (0.8x) for daily tasks.
Large Context
Choose gemini-3-pro or gemini-3-flash (1M tokens) when working with large codebases.