Skip to content

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

feat(providers): add Cheaper Inference

aiapienthusiastd820b96f138d
diff --git a/README.md b/README.md
index 14fe80e30..3da16d07e 100644
--- a/README.md
+++ b/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 **114 built-in provider cards on Chromium** (113 on Firefox),
+The Providers page ships **115 built-in provider cards on Chromium** (114 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).
diff --git a/docs/providers-and-models.md b/docs/providers-and-models.md
index 9b7510ca8..dcf1f9410 100644
--- a/docs/providers-and-models.md
+++ b/docs/providers-and-models.md
@@ -504,16 +504,16 @@ times the standard rate.
### Extended provider catalog
-WebBrain also ships 80 disabled-by-default provider cards. Most are sourced
+WebBrain also ships 81 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 **114 built-in providers on Chromium** and **113 on Firefox**; the
+Providers page lists **115 built-in providers on Chromium** and **114 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`, `digitalocean`, `dinference`, `drun`, `evroc`, `fastrouter`, `friendli` |
+| `302ai`, `abacus`, `aihubmix`, `alibaba-coding-plan`, `alibaba-coding-plan-cn`, `azure-cognitive-services`, `bailing`, `baseten`, `berget`, `cerebras`, `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`, `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` |
@@ -569,6 +569,19 @@ 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.
+#### Cheaper Inference
+
+[Cheaper Inference](https://cheaperinference.com) is an OpenAI-compatible LLM
+gateway at `https://api.cheaperinference.com/v1`. One API key gives access to
+models from several labs; model IDs are bare (such as `gpt-5.4-mini`,
+`claude-sonnet-5`, `gemini-3.5-flash`, and `deepseek-v4-flash`). See the
+[docs](https://cheaperinference.com/docs).
+
+In WebBrain, open **Providers -> LLM -> Cheaper Inference**. Paste an API key
+into the card, keep the default `gpt-5.4-mini` model (400000 tokens), then
+click **Test Connection**. Interactive Ask streaming, tool calls, and vision
+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 b7c7f4c08..34c5e3ae8 100644
--- a/src/chrome/icons/providers/SOURCES.md
+++ b/src/chrome/icons/providers/SOURCES.md
@@ -19,5 +19,6 @@ 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) |
+| cheaperinference | Cheaper Inference logo mark (cheaperinference.com) |
Brand trademarks remain property of their owners; used only for provider identification in the settings UI.
diff --git a/src/chrome/icons/providers/cheaperinference.svg b/src/chrome/icons/providers/cheaperinference.svg
new file mode 100644
index 000000000..0a6f5ede8
--- /dev/null
+++ b/src/chrome/icons/providers/cheaperinference.svg
@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Cheaper Inference</title><path fill="currentColor" d="M9.107 2.786H15.429V8.839H9.589a3.213 3.213 0 0 0 0.321 6.375H15.214L9.434 20.994A9.107 9.107 0 1 1 9.107 2.786Z"/><path fill="currentColor" d="M22.179 3.429H22.607a1.286 1.286 0 0 1 1.286 1.286V19.714a1.393 1.393 0 0 1 -1.393 1.393H17.464V8.143Z"/></svg>
diff --git a/src/chrome/src/providers/provider-catalog.js b/src/chrome/src/providers/provider-catalog.js
index aa4f7dab4..df8e45fc8 100644
--- a/src/chrome/src/providers/provider-catalog.js
+++ b/src/chrome/src/providers/provider-catalog.js
@@ -70,6 +70,7 @@ const PROVIDERS = [
provider('baseten', 'Baseten', 'https://inference.baseten.co/v1', 'moonshotai/Kimi-K3', 1048576, { apiKeyUrl: 'https://docs.baseten.co/inference/model-apis/overview', supportsVision: true, inputCostPerMillionUsd: 3, cacheReadCostPerMillionUsd: 0.3, outputCostPerMillionUsd: 15 }),
provider('berget', 'Berget.AI', 'https://api.berget.ai/v1', 'meta-llama/Llama-3.3-70B-Instruct', 128000, { apiKeyUrl: 'https://api.berget.ai', inputCostPerMillionUsd: 0.99, outputCostPerMillionUsd: 0.99 }),
provider('cerebras', 'Cerebras', 'https://api.cerebras.ai/v1', 'gemma-4-31b', 131072, { category: 'cloud', apiKeyUrl: 'https://cloud.cerebras.ai/', supportsVision: true, inputCostPerMillionUsd: 0.99, outputCostPerMillionUsd: 1.49 }),
+ provider('cheaperinference', 'Cheaper Inference', 'https://api.cheaperinference.com/v1', 'gpt-5.4-mini', 400000, { apiKeyUrl: 'https://cheaperinference.com', supportsVision: true, suggestions: ['gpt-5.4-mini', 'claude-sonnet-5', 'gemini-3.5-flash', 'deepseek-v4-flash'] }),
provider('chutes', 'Chutes', 'https://llm.chutes.ai/v1', 'moonshotai/Kimi-K2.6-TEE', 262144, { apiKeyUrl: 'https://chutes.ai/', supportsVision: true, inputCostPerMillionUsd: 0.66, cacheReadCostPerMillionUsd: 0.33, outputCostPerMillionUsd: 3.5 }),
provider('clarifai', 'Clarifai', 'https://api.clarifai.com/v2/ext/openai/v1', 'moonshotai/chat-completion/models/Kimi-K2_6', 262144, { apiKeyUrl: 'https://clarifai.com/settings/security', supportsVision: true, inputCostPerMillionUsd: 0.95, outputCostPerMillionUsd: 4, apiKeyPlaceholder: 'Personal access token' }),
provider('cloudferro-sherlock', 'CloudFerro Sherlock', 'https://api-sherlock.cloudferro.com/openai/v1', 'meta-llama/Llama-3.3-70B-Instruct', 70000, { apiKeyUrl: 'https://docs.sherlock.cloudferro.com/', inputCostPerMillionUsd: 2.92, outputCostPerMillionUsd: 2.92 }),
diff --git a/src/firefox/icons/providers/SOURCES.md b/src/firefox/icons/providers/SOURCES.md
index de092b993..1532a1efa 100644
--- a/src/firefox/icons/providers/SOURCES.md
+++ b/src/firefox/icons/providers/SOURCES.md
@@ -19,5 +19,6 @@ 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) |
+| cheaperinference | Cheaper Inference logo mark (cheaperinference.com) |
Brand trademarks remain property of their owners; used only for provider identification in the settings UI.
diff --git a/src/firefox/icons/providers/cheaperinference.svg b/src/firefox/icons/providers/cheaperinference.svg
new file mode 100644
index 000000000..0a6f5ede8
--- /dev/null
+++ b/src/firefox/icons/providers/cheaperinference.svg
@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><title>Cheaper Inference</title><path fill="currentColor" d="M9.107 2.786H15.429V8.839H9.589a3.213 3.213 0 0 0 0.321 6.375H15.214L9.434 20.994A9.107 9.107 0 1 1 9.107 2.786Z"/><path fill="currentColor" d="M22.179 3.429H22.607a1.286 1.286 0 0 1 1.286 1.286V19.714a1.393 1.393 0 0 1 -1.393 1.393H17.464V8.143Z"/></svg>
diff --git a/src/firefox/src/providers/provider-catalog.js b/src/firefox/src/providers/provider-catalog.js
index aa4f7dab4..df8e45fc8 100644
--- a/src/firefox/src/providers/provider-catalog.js
+++ b/src/firefox/src/providers/provider-catalog.js
@@ -70,6 +70,7 @@ const PROVIDERS = [
provider('baseten', 'Baseten', 'https://inference.baseten.co/v1', 'moonshotai/Kimi-K3', 1048576, { apiKeyUrl: 'https://docs.baseten.co/inference/model-apis/overview', supportsVision: true, inputCostPerMillionUsd: 3, cacheReadCostPerMillionUsd: 0.3, outputCostPerMillionUsd: 15 }),
provider('berget', 'Berget.AI', 'https://api.berget.ai/v1', 'meta-llama/Llama-3.3-70B-Instruct', 128000, { apiKeyUrl: 'https://api.berget.ai', inputCostPerMillionUsd: 0.99, outputCostPerMillionUsd: 0.99 }),
provider('cerebras', 'Cerebras', 'https://api.cerebras.ai/v1', 'gemma-4-31b', 131072, { category: 'cloud', apiKeyUrl: 'https://cloud.cerebras.ai/', supportsVision: true, inputCostPerMillionUsd: 0.99, outputCostPerMillionUsd: 1.49 }),
+ provider('cheaperinference', 'Cheaper Inference', 'https://api.cheaperinference.com/v1', 'gpt-5.4-mini', 400000, { apiKeyUrl: 'https://cheaperinference.com', supportsVision: true, suggestions: ['gpt-5.4-mini', 'claude-sonnet-5', 'gemini-3.5-flash', 'deepseek-v4-flash'] }),
provider('chutes', 'Chutes', 'https://llm.chutes.ai/v1', 'moonshotai/Kimi-K2.6-TEE', 262144, { apiKeyUrl: 'https://chutes.ai/', supportsVision: true, inputCostPerMillionUsd: 0.66, cacheReadCostPerMillionUsd: 0.33, outputCostPerMillionUsd: 3.5 }),
provider('clarifai', 'Clarifai', 'https://api.clarifai.com/v2/ext/openai/v1', 'moonshotai/chat-completion/models/Kimi-K2_6', 262144, { apiKeyUrl: 'https://clarifai.com/settings/security', supportsVision: true, inputCostPerMillionUsd: 0.95, outputCostPerMillionUsd: 4, apiKeyPlaceholder: 'Personal access token' }),
provider('cloudferro-sherlock', 'CloudFerro Sherlock', 'https://api-sherlock.cloudferro.com/openai/v1', 'meta-llama/Llama-3.3-70B-Instruct', 70000, { apiKeyUrl: 'https://docs.sherlock.cloudferro.com/', inputCostPerMillionUsd: 2.92, outputCostPerMillionUsd: 2.92 }),
diff --git a/test/run.js b/test/run.js
index 9ee94dc5a..a16bafa81 100644
--- a/test/run.js
+++ b/test/run.js
@@ -76054,7 +76054,7 @@ test('_defaultConfigs: every entry carries an explicit category', () => {
test('extended provider catalog is complete, mirrored, safe, and excluded-provider clean', async () => {
const expectedIds = `
302ai abacus aihubmix alibaba-coding-plan alibaba-coding-plan-cn
- azure-cognitive-services bailing baseten berget cerebras chutes clarifai
+ azure-cognitive-services bailing baseten berget cerebras 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
@@ -76068,7 +76068,7 @@ 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, 80);
+ assert.equal(expectedIds.length, 81);
assert.deepEqual(ProviderCatalogCh.ADDITIONAL_PROVIDER_IDS, expectedIds);
assert.deepEqual(ProviderCatalogFx.ADDITIONAL_PROVIDER_IDS, expectedIds);
assert.deepEqual(
@@ -76083,8 +76083,8 @@ 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 114/113 Settings provider cards.
- const expectedDefaultCount = label === 'chrome' ? 115 : 114;
+ // deliberately omitted from the 115/114 Settings provider cards.
+ const expectedDefaultCount = label === 'chrome' ? 116 : 115;
assert.equal(
Object.keys(defaults).length,
expectedDefaultCount,
@@ -76207,6 +76207,30 @@ 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.cheaperinference.baseUrl,
+ model: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheaperinference.model,
+ contextWindow: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheaperinference.contextWindow,
+ supportsVision: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheaperinference.supportsVision,
+ supportsTools: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheaperinference.supportsTools,
+ supportsAskStreaming: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheaperinference.supportsAskStreaming,
+ apiKeyUrl: ProviderCatalogCh.ADDITIONAL_PROVIDER_DEFAULTS.cheaperinference.apiKeyUrl,
+ },
+ {
+ baseUrl: 'https://api.cheaperinference.com/v1',
+ model: 'gpt-5.4-mini',
+ contextWindow: 400000,
+ supportsVision: true,
+ supportsTools: true,
+ supportsAskStreaming: true,
+ apiKeyUrl: 'https://cheaperinference.com',
+ },
+ );
+ assert.deepEqual(
+ ProviderCatalogCh.ADDITIONAL_PROVIDER_UI.cheaperinference.suggestions,
+ ['gpt-5.4-mini', 'claude-sonnet-5', 'gemini-3.5-flash', 'deepseek-v4-flash'],
+ );
assert.deepEqual(
ProviderCatalogCh.ADDITIONAL_PROVIDER_UI['kimi-for-coding'].suggestions,
['kimi-for-coding', 'kimi-for-coding-highspeed', 'k3'],