Add Fireworks AI Image Generation supports

Author: mythz

app/(home)/page.tsx

@@ -64,10 +64,10 @@ export default function HomePage() {
           </a>
         </div>
         <p className="text-sm text-muted-foreground">
-          <span className="text-slate-400 dark:text-slate-500">Mar 2, 2026</span>
+          <span className="text-slate-400 dark:text-slate-500">Mar 3, 2026</span>
           {' - '}
           <Link href="/docs/latest" className="text-blue-600 dark:text-blue-400 hover:underline">
-            New Username/Password Credentials Auth Provider →
+            New Fireworks AI Image Generation & GLM-5, Kimi K2.5, MimiMax M2.5 LLMs →
           </Link>
         </p>
 

content/docs/latest.mdx

@@ -11,6 +11,55 @@ After upgrading, it's recommended to also upgrade any external extensions:
 
 <ShellCommand>llms --update all</ShellCommand>
 
+## Mar 3, 2026
+
+### Support for Fireworks Large Language Models
+
+Added support for [Fireworks AI](https://fireworks.ai) as a new provider, a fast inference platform hosting the leading open-source models including **GLM 5**, **Kimi K2.5**, **MiniMax M2.5** and **DeepSeek V3.2** at a market-leading **200 tok/s**.
+
+<Screenshot src="/img/latest/fireworks-models.webp"  />
+
+All text models support **reasoning** and **tool use**, making Fireworks an excellent choice for agentic workflows where speed matters. Here's Kimi K2.5 via Fireworks creating a retro Tetris game with full tool calling support:
+
+<ScreenshotsGallery className="mb-8" gridClass="grid grid-cols-1 md:grid-cols-2 gap-4" images={{
+    'Kimi K2.5 via Fireworks': '/img/latest/fireworks-kimi.webp',
+    'Results at 125 tk/s': '/img/latest/fireworks-kimi-results.webp',
+}} />
+
+### Fireworks Image Generation Models
+
+Fireworks also hosts Black Forest Labs' **FLUX.1** image generation models with fast inference and competitive per-image pricing:
+
+| Model | Cost | Pricing |
+| --- | --- | --- |
+| **FLUX.1 Kontext Max** | $0.08 | per image |
+| **FLUX.1 Kontext Pro** | $0.04 | per image |
+| **FLUX.1 Dev FP8** | $0.0005 | per step |
+| **FLUX.1 Schnell FP8** | $0.00035 | per step |
+
+This can be found in the model selector by selecting the **Image** output filter:
+
+<Screenshot src="/img/image-gen/fireworks-image-models.webp"  />
+
+Here are examples to demonstrate the quality of each of the FLUX.1 models:
+
+<ScreenshotsGallery className="mb-8" gridClass="grid grid-cols-1 md:grid-cols-2 gap-4" images={{
+    'FLUX.1 Kontext Max': '/img/image-gen/flux-kontext-max.webp',
+    'FLUX.1 Kontext Pro': '/img/image-gen/flux-kontext-pro.webp',
+    'FLUX.1 Dev': '/img/image-gen/flux-dev.webp',
+    'FLUX.1 Schnell': '/img/image-gen/flux-schnell.webp',
+}} />
+
+To get started, set your Fireworks API key:
+
+```bash
+export FIREWORKS_API_KEY=your_api_key_here
+```
+
+Then reset your providers configuration to pick up the new Fireworks models in [providers-extra.json](https://github.com/ServiceStack/llms/blob/main/llms/providers-extra.json):
+
+<ShellCommand>llms --reset providers</ShellCommand>
+
 ## Mar 2, 2026
 
 ### Credentials Auth Provider

content/docs/media-generation/image-generation.mdx

@@ -5,14 +5,15 @@ description: Generate images using various LLM providers
 
 Unlike text generation, there's no standard API for image generation across providers - each requires its own custom implementation. Despite the additional effort required, there's now seamless image generation support through both the UI and CLI with built-in integrations for:
 
-| Provider   | Status |
-|------------|--------|
-| Google     | ✅ Supported |
-| OpenAI     | ✅ Supported |
-| OpenRouter | ✅ Supported |
-| Chutes     | ✅ Supported |
-| Z.ai       | ✅ Supported |
-| Nvidia     | ✅ Supported |
+| Provider     | Status |
+|--------------|--------|
+| Google       | ✅ Supported |
+| OpenAI       | ✅ Supported |
+| OpenRouter   | ✅ Supported |
+| Fireworks AI | ✅ Supported |
+| Chutes       | ✅ Supported |
+| Z.ai         | ✅ Supported |
+| Nvidia       | ✅ Supported |
 
 To begin select an image generation model from the Model Selector that supports image generation:
 
@@ -51,4 +52,29 @@ llms -m "gemini-2.5-flash-image" --out image "cat in a hat"
 llms -m "Gemini 2.5 Flash Image" --out image "cat in a hat"
 ```
 
-<Info>📁 All generated images are saved to `~/.llms/cache` using their SHA-256 hash as the filename.</Info>
+<Info>📁 All generated images are saved to `~/.llms/cache` using their SHA-256 hash as the filename.</Info>
+
+### Fireworks Image Generation Models
+
+Fireworks hosts Black Forest Labs' **FLUX.1** image generation models with fast inference and competitive per-image pricing:
+
+| Model | Cost | Pricing |
+| --- | --- | --- |
+| **FLUX.1 Kontext Max** | $0.08 | per image |
+| **FLUX.1 Kontext Pro** | $0.04 | per image |
+| **FLUX.1 Dev FP8** | $0.0005 | per step |
+| **FLUX.1 Schnell FP8** | $0.00035 | per step |
+
+This can be found in the model selector by selecting the **Image** output filter:
+
+<Screenshot src="/img/image-gen/fireworks-image-models.webp"  />
+
+Here are examples to demonstrate the quality of each of the FLUX.1 models:
+
+<ScreenshotsGallery className="mb-8" gridClass="grid grid-cols-1 md:grid-cols-2 gap-4" images={{
+    'FLUX.1 Kontext Max': '/img/image-gen/flux-kontext-max.webp',
+    'FLUX.1 Kontext Pro': '/img/image-gen/flux-kontext-pro.webp',
+    'FLUX.1 Dev': '/img/image-gen/flux-dev.webp',
+    'FLUX.1 Schnell': '/img/image-gen/flux-schnell.webp',
+}} />
+