Skip to content

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

removed demonroute

Codex release-state test08f56c74e12a
diff --git a/docs/providers-and-models.md b/docs/providers-and-models.md
index 9e32203f9..7fb58bbf6 100644
--- a/docs/providers-and-models.md
+++ b/docs/providers-and-models.md
@@ -247,16 +247,16 @@ class BaseLLMProvider {
### Extended provider catalog
-WebBrain also ships 81 disabled-by-default provider cards. Most are sourced
+WebBrain also ships 80 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, Settings
-contains **114 built-in providers on Chromium** and **113 on Firefox**; the
+contains **113 built-in providers on Chromium** and **112 on Firefox**; the
difference is the Chromium-only in-browser WebGPU runtime.
| IDs |
| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `302ai`, `abacus`, `aihubmix`, `alibaba-coding-plan`, `alibaba-coding-plan-cn`, `azure-cognitive-services`, `bailing`, `baseten`, `berget`, `cerebras`, `chutes`, `clarifai`, `cloudferro-sherlock`, `cohere`, `cortecs`, `deepinfra`, `demonroute`, `digitalocean`, `dinference`, `drun`, `evroc`, `fastrouter`, `friendli` |
+| `302ai`, `abacus`, `aihubmix`, `alibaba-coding-plan`, `alibaba-coding-plan-cn`, `azure-cognitive-services`, `bailing`, `baseten`, `berget`, `cerebras`, `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`, `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` |
@@ -312,21 +312,6 @@ Connection**. If selecting a model with a smaller context window, such as
limit. Interactive Ask streaming, tool calls, and vision work through the
existing OpenAI-compatible path.
-#### DemonRoute
-
-[DemonRoute](https://demonroute.com/) exposes an OpenAI-compatible API at
-`https://api.demonroute.com/v1`. It routes to open-weight and uncensored
-fine-tunes (such as Dolphin and Hermes) behind one key and does not train on
-user content.
-
-In WebBrain, open **Settings -> Providers -> DemonRoute**. Generate an API
-key from [DemonRoute](https://demonroute.com/), paste it into the card, keep
-the default `dphn/Dolphin3.0-Llama3.1-8B` model (131072 tokens), then click
-**Test Connection**. If selecting a model with a smaller context window, such
-as `Gryphe/MythoMax-L2-13b` (4096 tokens), set **Context window** to its
-documented limit. Interactive Ask streaming and tool calls work through the
-existing OpenAI-compatible path.
-
### Ask response streaming
Providers with `supportsAskStreaming` stream visible text during interactive
diff --git a/src/chrome/icons/providers/SOURCES.md b/src/chrome/icons/providers/SOURCES.md
index eecd0ed5e..b7c7f4c08 100644
--- a/src/chrome/icons/providers/SOURCES.md
+++ b/src/chrome/icons/providers/SOURCES.md
@@ -19,6 +19,5 @@ Most brand marks come from [Lobe Icons](https://github.com/lobehub/lobe-icons)
| 302ai, abacus, aihubmix, alibaba-coding-plan, alibaba-coding-plan-cn, azure-cognitive-services, bailing, baseten, berget, cerebras, chutes, clarifai, cloudferro-sherlock, cohere, cortecs, deepinfra, digitalocean, dinference, drun, evroc, fastrouter, friendli, 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, nebius, nova, novita-ai, ollama-cloud, opencode, opencode-go, ovhcloud, perplexity, perplexity-agent, poe, 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 | OpenCode provider icon set at commit `62e4641235d7847dadc60da37cca8a023dd54fc1` (MIT); DInference SVG normalized with a `viewBox` |
| orcarouter | OrcaRouter official docs favicon (`Continuum-AI-Corp/docs`, MIT) |
| nearai | WebBrain-authored simple N mark (not an official NEAR brand asset) |
-| demonroute | WebBrain-authored simple demon mark (not an official DemonRoute brand asset) |
Brand trademarks remain property of their owners; used only for provider identification in the settings UI.
diff --git a/src/chrome/src/providers/provider-catalog.js b/src/chrome/src/providers/provider-catalog.js
index a2014ac2e..cd91b52f2 100644
--- a/src/chrome/src/providers/provider-catalog.js
+++ b/src/chrome/src/providers/provider-catalog.js
@@ -76,7 +76,7 @@ const PROVIDERS = [
provider('cohere', 'Cohere', 'https://api.cohere.ai/compatibility/v1', 'command-a-plus-05-2026', 128000, { category: 'cloud', apiKeyUrl: 'https://dashboard.cohere.com/api-keys', inputCostPerMillionUsd: 2.5, outputCostPerMillionUsd: 10, suggestions: ['command-a-plus-05-2026', 'command-a-03-2025'] }),
provider('cortecs', 'Cortecs', 'https://api.cortecs.ai/v1', 'deepseek-r1-0528', 164000, { apiKeyUrl: 'https://api.cortecs.ai/v1/models', inputCostPerMillionUsd: 0.585, outputCostPerMillionUsd: 2.307 }),
provider('deepinfra', 'DeepInfra', 'https://api.deepinfra.com/v1/openai', 'Qwen/Qwen3.8-27B', 262144, { apiKeyUrl: 'https://deepinfra.com/dash/api_keys', supportsVision: true, inputCostPerMillionUsd: 0.1, outputCostPerMillionUsd: 0.3 }),
- provider('demonroute', 'DemonRoute', 'https://api.demonroute.com/v1', 'dphn/Dolphin3.0-Llama3.1-8B', 131072, { apiKeyUrl: 'https://demonroute.com', inputCostPerMillionUsd: 0.2, outputCostPerMillionUsd: 0.32, suggestions: ['dphn/Dolphin3.0-Llama3.1-8B', 'NousResearch/Hermes-3-Llama-3.1-8B'] }),
+ // provider('demonroute', 'DemonRoute', 'https://api.demonroute.com/v1', 'dphn/Dolphin3.0-Llama3.1-8B', 131072, { apiKeyUrl: 'https://demonroute.com', inputCostPerMillionUsd: 0.2, outputCostPerMillionUsd: 0.32, suggestions: ['dphn/Dolphin3.0-Llama3.1-8B', 'NousResearch/Hermes-3-Llama-3.1-8B'] }),
provider('digitalocean', 'DigitalOcean Gradient AI', 'https://inference.do-ai.run/v1', 'anthropic-claude-haiku-4.5', 200000, { apiKeyUrl: 'https://cloud.digitalocean.com/account/api/tokens', supportsVision: true, inputCostPerMillionUsd: 1, cacheReadCostPerMillionUsd: 1, cacheWriteCostPerMillionUsd: 1.25, outputCostPerMillionUsd: 5, apiKeyPlaceholder: 'Access token' }),
provider('dinference', 'DInference', 'https://api.dinference.com/v1', 'minimax-m2.5', 200000, { apiKeyUrl: 'https://dinference.com', inputCostPerMillionUsd: 0.22, outputCostPerMillionUsd: 0.88 }),
provider('drun', 'D.Run (China)', 'https://chat.d.run/v1', 'public/deepseek-v3', 131072, { apiKeyUrl: 'https://www.d.run', inputCostPerMillionUsd: 0.28, outputCostPerMillionUsd: 1.1 }),
diff --git a/src/firefox/icons/providers/SOURCES.md b/src/firefox/icons/providers/SOURCES.md
index 3904f161f..de092b993 100644
--- a/src/firefox/icons/providers/SOURCES.md
+++ b/src/firefox/icons/providers/SOURCES.md
@@ -19,6 +19,5 @@ Most brand marks come from [Lobe Icons](https://github.com/lobehub/lobe-icons)
| 302ai, abacus, aihubmix, alibaba-coding-plan, alibaba-coding-plan-cn, azure-cognitive-services, bailing, baseten, berget, cerebras, chutes, clarifai, cloudferro-sherlock, cohere, cortecs, deepinfra, digitalocean, dinference, drun, evroc, fastrouter, friendli, 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, nebius, nova, novita-ai, ollama-cloud, opencode, opencode-go, ovhcloud, perplexity, perplexity-agent, poe, 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 | OpenCode provider icon set at commit `62e4641235d7847dadc60da37cca8a023dd54fc1` (MIT); DInference SVG normalized with a `viewBox` |
| orcarouter | OrcaRouter official docs favicon (`Continuum-AI-Corp/docs`, MIT) |
| nearai | WebBrain-authored simple N mark (not an official NEAR brand asset) |
-| demonroute | WebBrain-authored simple demon mark (not an official DemonRoute brand asset) |
Brand trademarks remain property of their owners; used only for provider identification in the settings UI.
diff --git a/src/firefox/src/providers/provider-catalog.js b/src/firefox/src/providers/provider-catalog.js
index a2014ac2e..cd91b52f2 100644
--- a/src/firefox/src/providers/provider-catalog.js
+++ b/src/firefox/src/providers/provider-catalog.js
@@ -76,7 +76,7 @@ const PROVIDERS = [
provider('cohere', 'Cohere', 'https://api.cohere.ai/compatibility/v1', 'command-a-plus-05-2026', 128000, { category: 'cloud', apiKeyUrl: 'https://dashboard.cohere.com/api-keys', inputCostPerMillionUsd: 2.5, outputCostPerMillionUsd: 10, suggestions: ['command-a-plus-05-2026', 'command-a-03-2025'] }),
provider('cortecs', 'Cortecs', 'https://api.cortecs.ai/v1', 'deepseek-r1-0528', 164000, { apiKeyUrl: 'https://api.cortecs.ai/v1/models', inputCostPerMillionUsd: 0.585, outputCostPerMillionUsd: 2.307 }),
provider('deepinfra', 'DeepInfra', 'https://api.deepinfra.com/v1/openai', 'Qwen/Qwen3.8-27B', 262144, { apiKeyUrl: 'https://deepinfra.com/dash/api_keys', supportsVision: true, inputCostPerMillionUsd: 0.1, outputCostPerMillionUsd: 0.3 }),
- provider('demonroute', 'DemonRoute', 'https://api.demonroute.com/v1', 'dphn/Dolphin3.0-Llama3.1-8B', 131072, { apiKeyUrl: 'https://demonroute.com', inputCostPerMillionUsd: 0.2, outputCostPerMillionUsd: 0.32, suggestions: ['dphn/Dolphin3.0-Llama3.1-8B', 'NousResearch/Hermes-3-Llama-3.1-8B'] }),
+ // provider('demonroute', 'DemonRoute', 'https://api.demonroute.com/v1', 'dphn/Dolphin3.0-Llama3.1-8B', 131072, { apiKeyUrl: 'https://demonroute.com', inputCostPerMillionUsd: 0.2, outputCostPerMillionUsd: 0.32, suggestions: ['dphn/Dolphin3.0-Llama3.1-8B', 'NousResearch/Hermes-3-Llama-3.1-8B'] }),
provider('digitalocean', 'DigitalOcean Gradient AI', 'https://inference.do-ai.run/v1', 'anthropic-claude-haiku-4.5', 200000, { apiKeyUrl: 'https://cloud.digitalocean.com/account/api/tokens', supportsVision: true, inputCostPerMillionUsd: 1, cacheReadCostPerMillionUsd: 1, cacheWriteCostPerMillionUsd: 1.25, outputCostPerMillionUsd: 5, apiKeyPlaceholder: 'Access token' }),
provider('dinference', 'DInference', 'https://api.dinference.com/v1', 'minimax-m2.5', 200000, { apiKeyUrl: 'https://dinference.com', inputCostPerMillionUsd: 0.22, outputCostPerMillionUsd: 0.88 }),
provider('drun', 'D.Run (China)', 'https://chat.d.run/v1', 'public/deepseek-v3', 131072, { apiKeyUrl: 'https://www.d.run', inputCostPerMillionUsd: 0.28, outputCostPerMillionUsd: 1.1 }),
diff --git a/test/run.js b/test/run.js
index f4c99fe99..5192bb726 100644
--- a/test/run.js
+++ b/test/run.js
@@ -70866,7 +70866,7 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
const expectedIds = `
302ai abacus aihubmix alibaba-coding-plan alibaba-coding-plan-cn
azure-cognitive-services bailing baseten berget cerebras chutes clarifai
- cloudferro-sherlock cohere cortecs deepinfra demonroute digitalocean dinference drun
+ 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
kuae-cloud-coding-plan llama lucidquery meganova minimax-cn-coding-plan
@@ -70879,7 +70879,7 @@ 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, 81);
+ assert.equal(expectedIds.length, 80);
assert.deepEqual(ProviderCatalogCh.ADDITIONAL_PROVIDER_IDS, expectedIds);
assert.deepEqual(ProviderCatalogFx.ADDITIONAL_PROVIDER_IDS, expectedIds);
assert.deepEqual(
@@ -70893,7 +70893,7 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
['firefox', ProviderManagerFx, 'src/firefox'],
]) {
const defaults = new PM()._defaultConfigs();
- const expectedDefaultCount = label === 'chrome' ? 114 : 113;
+ const expectedDefaultCount = label === 'chrome' ? 113 : 112;
assert.equal(
Object.keys(defaults).length,
expectedDefaultCount,
@@ -71016,30 +71016,30 @@ test('extended provider catalog is complete, mirrored, safe, and excluded-provid
ProviderCatalogCh.ADDITIONAL_PROVIDER_UI.nearai.suggestions,
['z-ai/glm-5.3-flash', 'Qwen/Qwen3.8-27B'],
);
- assert.deepEqual(
- {
- baseUrl: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.baseUrl,
- model: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.model,
- contextWindow: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.contextWindow,
- supportsVision: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.supportsVision,
- supportsTools: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.supportsTools,
- supportsAskStreaming: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.supportsAskStreaming,
- apiKeyUrl: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.apiKeyUrl,
- },
- {
- baseUrl: 'https://api.demonroute.com/v1',
- model: 'dphn/Dolphin3.0-Llama3.1-8B',
- contextWindow: 131072,
- supportsVision: false,
- supportsTools: true,
- supportsAskStreaming: true,
- apiKeyUrl: 'https://demonroute.com',
- },
- );
- assert.deepEqual(
- ProviderCatalogCh.ADDITIONAL_PROVIDER_UI.demonroute.suggestions,
- ['dphn/Dolphin3.0-Llama3.1-8B', 'NousResearch/Hermes-3-Llama-3.1-8B'],
- );
+ // assert.deepEqual(
+ // {
+ // baseUrl: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.baseUrl,
+ // model: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.model,
+ // contextWindow: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.contextWindow,
+ // supportsVision: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.supportsVision,
+ // supportsTools: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.supportsTools,
+ // supportsAskStreaming: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.supportsAskStreaming,
+ // apiKeyUrl: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.demonroute.apiKeyUrl,
+ // },
+ // {
+ // baseUrl: 'https://api.demonroute.com/v1',
+ // model: 'dphn/Dolphin3.0-Llama3.1-8B',
+ // contextWindow: 131072,
+ // supportsVision: false,
+ // supportsTools: true,
+ // supportsAskStreaming: true,
+ // apiKeyUrl: 'https://demonroute.com',
+ // },
+ // );
+ // assert.deepEqual(
+ // ProviderCatalogCh.ADDITIONAL_PROVIDER_UI.demonroute.suggestions,
+ // ['dphn/Dolphin3.0-Llama3.1-8B', 'NousResearch/Hermes-3-Llama-3.1-8B'],
+ // );
assert.deepEqual(
ProviderCatalogCh.ADDITIONAL_PROVIDER_UI['kimi-for-coding'].suggestions,
['kimi-for-coding', 'kimi-for-coding-highspeed', 'k3'],