RunCell LogoRuncell

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This page is archived for historical reference.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

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.

ModelCredit Rate
AnthropicAnthropic
Anthropicanthropic/claude-sonnet-4-52.5x
Anthropicanthropic/claude-sonnet-4-62.5x
Anthropicanthropic/claude-haiku-4-50.8x
Anthropicanthropic/claude-opus-4-54.2x
Anthropicanthropic/claude-opus-4-64.2x
Anthropicanthropic/claude-opus-4-012.5x
Anthropicanthropic/claude-opus-4-112.5x
Anthropicanthropic/claude-sonnet-4-02.5x
Anthropicanthropic/claude-3-5-haiku0.5x
Anthropicanthropic/claude-3-5-sonnet-202410222.5x
Anthropicanthropic/claude-3-7-sonnet-202502192.5x
OpenAIOpenAI
OpenAIopenai/gpt-4o1.0x
OpenAIopenai/gpt-4.10.8x
OpenAIopenai/gpt-4o-mini0.2x
OpenAIopenai/gpt-5.2-codex1.4x
OpenAIopenai/gpt-5.11.0x
OpenAIopenai/gpt-5.21.4x
OpenAIopenai/gpt-51.0x
OpenAIopenai/o31.0x
GeminiGoogle
Geminigemini/gemini-2.5-pro1.6x
Geminigoogle/gemini-3-pro-preview1.0x
Geminigoogle/gemini-3.1-pro-preview1.0x
Geminigoogle/gemini-3-flash-preview0.4x
Other Providers
Kimimoonshotai/kimi-k2-09050.5x
Kimimoonshotai/kimi-k2.50.5x
Minimaxminimax/minimax-m2.10.3x
Minimaxminimax/minimax-m2.50.3x
Z.aiz-ai/glm-4.70.4x
Z.aiz-ai/glm-50.8x
DeepSeekdeepseek/deepseek-v3.2-exp0.2x
Qwenqwen/qwen3-coder-plus0.8x
Grokx-ai/grok-code-fast-10.2x