diff --git a/docs/src/account/zed-hosted-models.md b/docs/src/account/zed-hosted-models.md index a2f1e13a793..c6b058bd7bc 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 4 Argon. Pricing, context windows, and tool call support. +description: AI models available via Zed Pro including Claude Fable 5.2, Claude Opus 5.5, GPT-6.1 Sol, and Gemini 4 Argon. Pricing, context windows, and tool call support. --- # Zed-Hosted Models @@ -11,6 +11,10 @@ Zed's plans offer hosted versions of major LLMs with higher rate limits than dir | Model | Provider | Token Type | Provider Price per 1M tokens | Zed Price per 1M tokens | | ----------------- | --------- | ------------------- | ---------------------------- | ----------------------- | +| Claude Fable 5.2 | Anthropic | Input | $8.00 | $8.80 | +| | Anthropic | Output | $40.00 | $44.00 | +| | Anthropic | Input - Cache Write | $10.00 | $11.00 | +| | Anthropic | Input - Cache Read | $0.20 | $0.22 | | Claude Fable 5.1 | Anthropic | Input | $10.00 | $11.00 | | | Anthropic | Output | $50.00 | $55.00 | | | Anthropic | Input - Cache Write | $12.50 | $13.75 | @@ -126,7 +130,7 @@ Zed's plans offer hosted versions of major LLMs with higher rate limits than dir | Gemini 3 Flash | Google | Input | $0.50 | $0.55 | | | Google | Output | $3.00 | $3.30 | -> **Warn:** Anthropic retains prompts and outputs sent to Claude Fable 5.1 and Claude Fable 5 for at least 30 days for trust and safety purposes. The no-training commitment still applies, and Zed does not retain your prompts or outputs. See [Provider Safety Retention for Designated Models](../ai/privacy-and-security.md#provider-safety-retention). +> **Warn:** Anthropic retains prompts and outputs sent to Claude Fable 5.2, Claude Fable 5.1, and Claude Fable 5 for at least 30 days for trust and safety purposes. The no-training commitment still applies, and Zed does not retain your prompts or outputs. See [Provider Safety Retention for Designated Models](../ai/privacy-and-security.md#provider-safety-retention). ## Recent Model Retirements {#recent-model-retirements} @@ -145,6 +149,8 @@ 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. +For Claude Fable 5.2, the cache-write rate above is for the 5-minute cache. The 1-hour cache costs $16.00 per 1M tokens from Anthropic, or $17.60 through Zed. Fast mode doubles all Fable 5.2 token rates, including cache writes and reads. + 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. @@ -155,6 +161,7 @@ A context window is the maximum span of text and code an LLM can consider at onc | Model | Provider | Zed-Hosted Context Window | | ----------------- | --------- | ------------------------- | +| Claude Fable 5.2 | Anthropic | 1M | | Claude Fable 5.1 | Anthropic | 1M | | Claude Fable 5 | Anthropic | 1M | | Claude Opus 5.5 | Anthropic | 1M |