--- title: "grok-4.20-non-reasoning - Model Details & Comparison" description: "grok-4.20-non-reasoning from Google Vertex AI: capabilities, context limits, pricing, and side-by-side comparisons with alternative models." url: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/vertex_ai/grok-4.20-non-reasoning" markdown: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/vertex_ai/grok-4.20-non-reasoning.md" --- # grok-4.20-non-reasoning - Model Details & Comparison > grok-4.20-non-reasoning from Google Vertex AI: capabilities, context limits, pricing, and side-by-side comparisons with alternative models. ## Important Links - [View MCP Gateway](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources/mcp-gateway.md) - [Features](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/#features) - [Enterprise](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/enterprise) - [Pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/pricing.md) - [Docs](https://docs.getbifrost.ai) - [GitHub](https://github.com/maximhq/bifrost) - [Book a Demo](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/book-a-demo) ## About grok-4.20-non-reasoning grok-4.20-non-reasoning is a chat model from Vertex AI, one of 112 chat models they offer. It is priced at $2.00 per 1M input tokens and $6.00 per 1M output tokens, ranking 2112 out of 2669 chat models by cost and cheaper than 20% of models in this category. grok-4.20-non-reasoning supports vision, function calling, web search, structured output — one of only 2 chat models with this combination. Its 2,000K-token context window is in the top 1% among chat models. ## Specifications - **Google Vertex AI Provider.** - **Chat Mode.** - **2,000,000 Max Input Tokens.** - **2,000,000 Max Output Tokens.** - **2,000,000 Max Tokens.** - **$2.00 / 1M tokens Input Price.** - **$6.00 / 1M tokens Output Price.** ## Capabilities grok-4.20-non-reasoning supports: Function Calling, Vision, Web Search, Response Schema, Tool Choice. ## grok-4.20-non-reasoning Pricing Overview At $2.00 per 1M input tokens and $6.00 per 1M output tokens, grok-4.20-non-reasoning ranks 2112 out of 2669 chat models by input cost. It is more expensive compared to the median of $0.50 for chat models, and is cheaper than 20% of models in this category. grok-4.20-non-reasoning is one of 112 Vertex AI chat models, one of only 2 chat models combining function calling, structured output, vision, web search. its 2,000K-token context window places it in the top 1% of chat models. ## Models to Compare Alternatives to grok-4.20-non-reasoning with comparable capabilities. | Model | Provider | Input $/1M | Output $/1M | | --- | --- | --- | --- | | claude-sonnet-5 | Anthropic | $2.00 | $10.00 | | gemini-3-pro-preview | Google Gemini | $2.00 | $12.00 | | gemini-3.1-pro-preview | Google Gemini | $2.00 | $12.00 | | gemini-3.1-pro-preview-customtools | Google Gemini | $2.00 | $12.00 | | gpt-4.1 | OpenAI | $2.00 | $8.00 | - [Compare claude-sonnet-5](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/anthropic/claude-sonnet-5.md) - [Compare gemini-3-pro-preview](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/gemini/gemini-3-pro-preview.md) - [Compare gemini-3.1-pro-preview](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/gemini/gemini-3.1-pro-preview.md) - [Compare gemini-3.1-pro-preview-customtools](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/gemini/gemini-3.1-pro-preview-customtools.md) - [Compare gpt-4.1](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/openai/gpt-4.1.md) ## Related Resources - [Calculate grok-4.20-non-reasoning costs](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/vertex_ai/model/grok-4.20-non-reasoning.md) - [All Vertex AI pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/vertex_ai.md) ## FAQ ### Is grok-4.20-non-reasoning cheaper than claude-sonnet-5? No. grok-4.20-non-reasoning costs $2.00 per 1M input tokens while claude-sonnet-5 costs $2.00 per 1M input tokens, making claude-sonnet-5 0% more affordable for input. However, grok-4.20-non-reasoning may offer different capabilities or performance characteristics that justify the price difference. ### How does grok-4.20-non-reasoning pricing compare to the average chat model? grok-4.20-non-reasoning input pricing is $2.00 per 1M tokens, which is 300% above the median of $0.50 for chat models. It ranks 2112 out of 2669 chat models by input cost, making it cheaper than 20% of models in this category. For output, it costs $6.00 per 1M tokens compared to the median of $1.44. ### What makes grok-4.20-non-reasoning different from other Vertex AI models? Among Vertex AI's 112 chat models, grok-4.20-non-reasoning ranks 77 by input cost. Its combination of function calling, structured output, vision, web search is shared by only 1 other chat model. ### What are the best alternatives to grok-4.20-non-reasoning? The most comparable chat models to grok-4.20-non-reasoning are: claude-sonnet-5 from Anthropic ($2.00/1M input tokens); gemini-3-pro-preview from Google Gemini ($2.00/1M input tokens); gemini-3.1-pro-preview from Google Gemini ($2.00/1M input tokens); gemini-3.1-pro-preview-customtools from Google Gemini ($2.00/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library. ### How large is grok-4.20-non-reasoning's context window? grok-4.20-non-reasoning supports up to 2,000,000 input tokens, placing it in the top 1% of chat models by context window size (rank 10 of 2653). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories. ### How do I calculate grok-4.20-non-reasoning costs? grok-4.20-non-reasoning is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $2.00 and generating 1M output tokens costs $6.00. ## Related Resources - [Google Vertex AI models](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/provider/vertex_ai.md) - [Model library](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library.md) - [LLM cost calculator](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator.md) - [Docs: Bifrost docs](https://docs.getbifrost.ai) - [GitHub: maximhq/bifrost](https://github.com/maximhq/bifrost) - [Pricing: Bifrost pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/pricing.md) - [Enterprise: Bifrost enterprise](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/enterprise) - [Book a Demo: Bifrost demo](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/book-a-demo) - [Resources: Bifrost resources](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources.md) --- *This is a markdown version of [https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/vertex_ai/grok-4.20-non-reasoning](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/vertex_ai/grok-4.20-non-reasoning) for AI/LLM consumption.*