From 7d12470f2cf5dad48dad662b9daaf11608b51c32 Mon Sep 17 00:00:00 2001 From: Warp Factory Date: Tue, 8 Sep 2026 05:21:14 +0000 Subject: [PATCH] docs: add GPT-6 Astra, Gemini 3/3.8 Flash, Inkling, and Muse Spark 1.2 to model choice docs QUALITY-2031 --- src/content/docs/agents/inference/model-choice.mdx | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/src/content/docs/agents/inference/model-choice.mdx b/src/content/docs/agents/inference/model-choice.mdx index ded9b89f..398038e1 100644 --- a/src/content/docs/agents/inference/model-choice.mdx +++ b/src/content/docs/agents/inference/model-choice.mdx @@ -33,6 +33,11 @@ All Auto models perform well across all agent workflows and are ideal if you pre | Model | `model_id` | Reasoning Level | | --- | --- | --- | +| GPT-6 Astra | `gpt-6-astra-low` | Low | +| GPT-6 Astra | `gpt-6-astra-medium` | Medium | +| GPT-6 Astra | `gpt-6-astra-high` | High | +| GPT-6 Astra | `gpt-6-astra-xhigh` | Extra High | +| GPT-6 Astra | `gpt-6-astra-max` | Max | | GPT-5.6 Sol | `gpt-5-6-sol-low` | Low | | GPT-5.6 Sol | `gpt-5-6-sol-medium` | Medium | | GPT-5.6 Sol | `gpt-5-6-sol-high` | High | @@ -120,9 +125,11 @@ Anthropic requires data retention for Claude Fable 5 and Claude Fable 5.1 for sa | Model | `model_id` | | --- | --- | | Gemini 3.1 Pro | `gemini-3.1-pro` | +| Gemini 3.8 Flash | `gemini-3.8-flash` | | Gemini 3.7 Flash | `gemini-3.7-flash` | | Gemini 3.6 Flash | `gemini-3.6-flash` | | Gemini 3.5 Flash | `gemini-3.5-flash` | +| Gemini 3 Flash | `gemini-3-flash` | #### xAI @@ -142,6 +149,12 @@ Anthropic requires data retention for Claude Fable 5 and Claude Fable 5.1 for sa You can run Grok models through your own SuperGrok subscription instead of Warp credits by connecting your xAI account. See [SuperGrok subscription](/agents/inference/grok-subscription/). +#### Meta + +| Model | `model_id` | +| --- | --- | +| Muse Spark 1.2 | `muse-spark-1.2` | + #### Hosted models (via [Fireworks AI](https://fireworks.ai)) Warp also supports leading open source models hosted via Fireworks AI, so you can run them from inside Warp without setting up your own inference infrastructure. @@ -156,6 +169,7 @@ Warp also supports leading open source models hosted via Fireworks AI, so you ca | Minimax 3 | `minimax-3-fireworks` | | Qwen 3.8 Max | `qwen-3.8-max-fireworks` | | DeepSeek V4 Pro | `deepseek-v4-pro-fireworks` | +| Inkling | `inkling-fireworks` | ### How to change models