Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
Document Gemini 4 Argon hosted pricing (#65707)
Tom Houléd678e7de4d9d
diff --git a/docs/src/account/zed-hosted-models.md b/docs/src/account/zed-hosted-models.mdindex bac64b59988..a2f1e13a793 100644--- a/docs/src/account/zed-hosted-models.md+++ b/docs/src/account/zed-hosted-models.md@@ -1,6 +1,6 @@---title: Zed-Hosted Models - Zed-description: AI models available via Zed Pro including Claude Fable 5.1, Claude Opus 5.5, GPT-6.1 Sol, and Gemini 3. Pricing, context windows, and tool call support.+description: AI models available via Zed Pro including Claude Fable 5.1, Claude Opus 5.5, GPT-6.1 Sol, and Gemini 4 Argon. Pricing, context windows, and tool call support.---# Zed-Hosted Models@@ -116,6 +116,9 @@ Zed's plans offer hosted versions of major LLMs with higher rate limits than dir| GPT-5 nano | OpenAI | Input | $0.05 | $0.055 || | OpenAI | Output | $0.40 | $0.44 || | OpenAI | Cached Input | $0.005 | $0.0055 |+| Gemini 4 Argon | Google | Input | $2.00 | $2.20 |+| | Google | Output | $10.00 | $11.00 |+| | Google | Cached Input | $0.10 | $0.11 || Gemini 3.1 Pro | Google | Input | $2.00 | $2.20 || | Google | Output | $12.00 | $13.20 || Gemini 3.5 Flash | Google | Input | $1.50 | $1.65 |@@ -142,7 +145,7 @@ Zed no longer offers the models below:Any usage of a Zed-hosted model will be billed at the Zed Price (rightmost column above). See [Plans & Pricing](./plans-and-pricing.md) for details on Zed's plans and limits for use of hosted models.-Because Zed-hosted Gemini models do not use Google context caching, Gemini usage is billed only as input and output tokens; there is no separate cached-input price for these models. This preserves zero-data-retention behavior for hosted Gemini requests. For background, see Google's Vertex AI documentation on [context caching](https://cloud.google.com/vertex-ai/generative-ai/docs/context-cache/context-cache-overview) and [zero data retention](https://cloud.google.com/vertex-ai/generative-ai/docs/vertex-ai-zero-data-retention).+Gemini 4 Argon bills implicit cache hits at the cached-input rate above. Gemini 3 models do not use Google context caching and are billed only as input and output tokens, which preserves zero-data-retention behavior for those requests. For background, see Google's Vertex AI documentation on [context caching](https://cloud.google.com/vertex-ai/generative-ai/docs/context-cache/context-cache-overview) and [zero data retention](https://cloud.google.com/vertex-ai/generative-ai/docs/vertex-ai-zero-data-retention).> LLMs can enter unproductive loops that require user intervention. Monitor longer-running tasks and interrupt if needed.@@ -181,6 +184,7 @@ A context window is the maximum span of text and code an LLM can consider at onc| GPT-5.2-Codex | OpenAI | 272k input / 400k total || GPT-5 mini | OpenAI | 272k input / 400k total || GPT-5 nano | OpenAI | 272k input / 400k total |+| Gemini 4 Argon | Google | 1M || Gemini 3.1 Pro | Google | 200k || Gemini 3.5 Flash | Google | 1M || Gemini 3 Flash | Google | 1M |