feat(providers): add cheapaimodel

README.md

@@ -126,7 +126,7 @@ preview `ollama launch webbrain --model <model>` handoff. Details:
 **Cloud APIs** — OpenAI, Anthropic Claude, Google Gemini, Azure OpenAI, AWS
 Bedrock, Mistral, DeepSeek, xAI Grok, MiniMax, Kimi, Qwen, z.ai GLM, Groq,
 Together, Cloudflare, Nvidia NIM, Hugging Face, Fireworks, OpenRouter, and more.
-The Providers page ships **118 built-in provider cards on Chromium** (117 on Firefox),
+The Providers page ships **119 built-in provider cards on Chromium** (118 on Firefox),
 including an endpoint-free local WebGPU option with the tested LFM2.5 2.6B
 preset and an experimental custom Hugging Face ONNX repository option —
 see the [full catalog](docs/providers-and-models.md#extended-provider-catalog).

docs/providers-and-models.md

@@ -510,16 +510,16 @@ times the standard rate.
 
 ### Extended provider catalog
 
-WebBrain also ships 84 disabled-by-default provider cards. Most are sourced
+WebBrain also ships 85 disabled-by-default provider cards. Most are sourced
 from the OpenCode provider catalog snapshot at commit
 `62e4641235d7847dadc60da37cca8a023dd54fc1`; provider-specific additions use
 their official API documentation. Together with the original cards, the
-Providers page lists **118 built-in providers on Chromium** and **117 on Firefox**; the
+Providers page lists **119 built-in providers on Chromium** and **118 on Firefox**; the
 difference is the Chromium-only in-browser WebGPU runtime.
 
 | IDs                                                                                                                                                                                                                                                                                                                        |
 | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `api-route`, `302ai`, `abacus`, `aihubmix`, `alibaba-coding-plan`, `alibaba-coding-plan-cn`, `atlascloud`, `azure-cognitive-services`, `bailing`, `baseten`, `berget`, `cerebras`, `cheaperinference`, `chutes`, `clarifai`, `cloudferro-sherlock`, `cohere`, `cortecs`, `deepinfra`, `digitalocean`, `dinference`, `drun`, `evroc`, `fastrouter`, `friendli` |
+| `api-route`, `302ai`, `abacus`, `aihubmix`, `alibaba-coding-plan`, `alibaba-coding-plan-cn`, `atlascloud`, `azure-cognitive-services`, `bailing`, `baseten`, `berget`, `cerebras`, `cheapaimodel`, `cheaperinference`, `chutes`, `clarifai`, `cloudferro-sherlock`, `cohere`, `cortecs`, `deepinfra`, `digitalocean`, `dinference`, `drun`, `evroc`, `fastrouter`, `friendli` |
 | `freebuff2api`, `google-vertex`, `google-vertex-anthropic`, `helicone`, `iflowcn`, `inception`, `inference`, `io-net`, `jiekou`, `kilo`, `kimi-for-coding`, `kuae-cloud-coding-plan`, `llama`, `lucidquery`, `meganova`, `minimax-cn-coding-plan`, `minimax-coding-plan`, `moark`, `modelscope`, `morph`                       |
 | `nano-gpt`, `nearai`, `nebius`, `nova`, `novita-ai`, `ollama-cloud`, `opencode`, `opencode-go`, `opper`, `orcarouter`, `ovhcloud`, `perplexity`, `perplexity-agent`, `poe`, `pollinations`, `privatemode-ai`, `qihang-ai`, `qiniu-ai`, `requesty`, `scaleway`, `siliconflow`, `siliconflow-cn`, `stackit`                      |
 | `stepfun`, `submodel`, `synthetic`, `tencent-coding-plan`, `upstage`, `v0`, `venice`, `vercel`, `vivgrid`, `vultr`, `wandb`, `xiaomi`, `zai-coding-plan`, `zenmux`, `zhipuai`, `zhipuai-coding-plan`                                                                                                                       |
@@ -630,6 +630,25 @@ click **Test Connection**. Interactive Ask streaming, tool calls, and vision
 work through the existing OpenAI-compatible path. Vision depends on the model:
 `deepseek-ai/deepseek-v4-flash` and `deepseek-ai/deepseek-v3.2` are text-only.
 
+#### cheapaimodel
+
+[cheapaimodel](https://cheapaimodel.ai) is an OpenAI-compatible, pay-per-token
+gateway for open-weight models (DeepSeek, GLM, Kimi) and Grok at
+`https://api.cheapaimodel.ai/v1`. Model IDs are bare (such as
+`deepseek-v4-1-flash`, `glm-5.3-flash`, `glm-5.3`, and `grok-4.7`); the full
+list is on the [models page](https://cheapaimodel.ai/models). See the
+[docs](https://cheapaimodel.ai/docs).
+
+In WebBrain, open **Providers -> LLM -> cheapaimodel**. Create an API key in the
+[console](https://console.cheapaimodel.ai/keys), paste it into the card, keep
+the default `deepseek-v4-1-flash` model (1000000 tokens), then click **Test
+Connection**. Interactive Ask streaming, tool calls, and vision work through
+the existing OpenAI-compatible path. Vision depends on the model: use
+`deepseek-v4-1-flash` or `grok-4.7`. `glm-5.3` is text-only, and `glm-5.3-flash`
+rejects WebBrain's vision requests because it cannot turn reasoning off (HTTP
+400); both work for text chat and tool calls. `kimi-k3` only accepts a
+temperature of 1 or 0.6, so it is not suggested on this card.
+
 ### Ask response streaming
 
 Providers with `supportsAskStreaming` stream visible text during interactive

src/chrome/icons/providers/SOURCES.md

@@ -21,6 +21,7 @@ Most brand marks come from [Lobe Icons](https://github.com/lobehub/lobe-icons)
 | nearai | WebBrain-authored simple N mark (not an official NEAR brand asset) |
 | cheaperinference | Cheaper Inference logo mark (cheaperinference.com) |
 | opper | Opper official logo mark (opper.ai) |
+| cheapaimodel | cheapaimodel logo mark (cheapaimodel.ai) |
 
 Brand trademarks remain property of their owners; used only for provider identification in the settings UI.
 

src/firefox/icons/providers/SOURCES.md

@@ -21,6 +21,7 @@ Most brand marks come from [Lobe Icons](https://github.com/lobehub/lobe-icons)
 | nearai | WebBrain-authored simple N mark (not an official NEAR brand asset) |
 | cheaperinference | Cheaper Inference logo mark (cheaperinference.com) |
 | opper | Opper official logo mark (opper.ai) |
+| cheapaimodel | cheapaimodel logo mark (cheapaimodel.ai) |
 
 Brand trademarks remain property of their owners; used only for provider identification in the settings UI.
 

test/run.js

@@ -76744,7 +76744,7 @@ test('_defaultConfigs: every entry carries an explicit category', () => {
 test('extended provider catalog is complete, mirrored, safe, and excluded-provider clean', async () => {
   const expectedIds = `
     api-route 302ai abacus aihubmix alibaba-coding-plan alibaba-coding-plan-cn
-    atlascloud azure-cognitive-services bailing baseten berget cerebras cheaperinference chutes clarifai
+    atlascloud azure-cognitive-services bailing baseten berget cerebras cheapaimodel cheaperinference chutes clarifai
     cloudferro-sherlock cohere cortecs deepinfra digitalocean dinference drun
     evroc fastrouter freebuff2api friendli google-vertex google-vertex-anthropic helicone
     iflowcn inception inference io-net jiekou kilo kimi-for-coding
@@ -76758,7 +76758,7 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
   `.trim().split(/\s+/);
   const excluded = ['github-models', 'github-copilot', 'gitlab', 'sap-ai-core'];
 
-  assert.equal(expectedIds.length, 84);
+  assert.equal(expectedIds.length, 85);
   assert.deepEqual(ProviderCatalogCh.ADDITIONAL_PROVIDER_IDS, expectedIds);
   assert.deepEqual(ProviderCatalogFx.ADDITIONAL_PROVIDER_IDS, expectedIds);
   assert.deepEqual(
@@ -76773,8 +76773,8 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
   ]) {
     const defaults = new PM()._defaultConfigs();
     // Includes the sidepanel-only WebBrain Compass XL runtime profile, which is
-    // deliberately omitted from the 118/117 Settings provider cards.
-    const expectedDefaultCount = label === 'chrome' ? 119 : 118;
+    // deliberately omitted from the 119/118 Settings provider cards.
+    const expectedDefaultCount = label === 'chrome' ? 120 : 119;
     assert.equal(
       Object.keys(defaults).length,
       expectedDefaultCount,
@@ -76998,6 +76998,30 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
     ProviderCatalogCh.ADDITIONAL_PROVIDER_UI.atlascloud.suggestions,
     ['qwen/qwen3.7-plus', 'deepseek-ai/deepseek-v4-flash', 'deepseek-ai/deepseek-v3.2', 'moonshotai/kimi-k2.6'],
   );
+  assert.deepEqual(
+    {
+      baseUrl: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheapaimodel.baseUrl,
+      model: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheapaimodel.model,
+      contextWindow: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheapaimodel.contextWindow,
+      supportsVision: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheapaimodel.supportsVision,
+      supportsTools: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheapaimodel.supportsTools,
+      supportsAskStreaming: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheapaimodel.supportsAskStreaming,
+      apiKeyUrl: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheapaimodel.apiKeyUrl,
+    },
+    {
+      baseUrl: 'https://api.cheapaimodel.ai/v1',
+      model: 'deepseek-v4-1-flash',
+      contextWindow: 1000000,
+      supportsVision: true,
+      supportsTools: true,
+      supportsAskStreaming: true,
+      apiKeyUrl: 'https://console.cheapaimodel.ai/keys',
+    },
+  );
+  assert.deepEqual(
+    ProviderCatalogCh.ADDITIONAL_PROVIDER_UI.cheapaimodel.suggestions,
+    ['deepseek-v4-1-flash', 'glm-5.3-flash', 'glm-5.3', 'grok-4.7'],
+  );
   assert.deepEqual(
     ProviderCatalogCh.ADDITIONAL_PROVIDER_UI['kimi-for-coding'].suggestions,
     ['kimi-for-coding', 'kimi-for-coding-highspeed', 'k3'],