Archived Model Credit Costs
Archived legacy guide for Runcell message-based model credit multipliers
Archived Model Credit Costs
This page is archived for historical reference. Runcell has migrated Ask/Chat and Agent mode from message-based model multipliers to token-based Credits.
For the current Ask/Chat and Agent pricing model, see Token-based Credits.
The legacy model-rate information below may still be useful for understanding older message-based behavior and feature-based rules that have not moved to token-based billing.
Legacy Message-based Calculation
Historically, the credit cost for a request was calculated as:
Credit Cost = Base Credits × Credit Rate
- Base Credits: configured per message or per feature
- Credit Rate: model-specific multiplier
See also
- Token-based Credits: current Ask/Chat and Agent token pricing: Token-based Credits
- Credits Consumption by Feature: current feature-level credit rules: Credits Consumption by Feature
Archived Credit Rate Table
The table below is retained as a legacy reference for message-based model multipliers. It should not be used to estimate current Ask/Chat or Agent costs.
| Model | Credit Rate |
|---|---|
| Anthropic | |
anthropic/claude-sonnet-4-5 | 2.5x |
anthropic/claude-sonnet-4-6 | 2.5x |
anthropic/claude-haiku-4-5 | 0.8x |
anthropic/claude-opus-4-5 | 4.2x |
anthropic/claude-opus-4-6 | 4.2x |
anthropic/claude-opus-4-0 | 12.5x |
anthropic/claude-opus-4-1 | 12.5x |
anthropic/claude-sonnet-4-0 | 2.5x |
anthropic/claude-3-5-haiku | 0.5x |
anthropic/claude-3-5-sonnet-20241022 | 2.5x |
anthropic/claude-3-7-sonnet-20250219 | 2.5x |
| OpenAI | |
openai/gpt-4o | 1.0x |
openai/gpt-4.1 | 0.8x |
openai/gpt-4o-mini | 0.2x |
openai/gpt-5.2-codex | 1.4x |
openai/gpt-5.1 | 1.0x |
openai/gpt-5.2 | 1.4x |
openai/gpt-5 | 1.0x |
openai/o3 | 1.0x |
gemini/gemini-2.5-pro | 1.6x |
google/gemini-3-pro-preview | 1.0x |
google/gemini-3.1-pro-preview | 1.0x |
google/gemini-3-flash-preview | 0.4x |
| Other Providers | |
moonshotai/kimi-k2-0905 | 0.5x |
moonshotai/kimi-k2.5 | 0.5x |
minimax/minimax-m2.1 | 0.3x |
minimax/minimax-m2.5 | 0.3x |
z-ai/glm-4.7 | 0.4x |
z-ai/glm-5 | 0.8x |
deepseek/deepseek-v3.2-exp | 0.2x |
qwen/qwen3-coder-plus | 0.8x |
x-ai/grok-code-fast-1 | 0.2x |