providers.md Raw History Folder

zut providers

zut ships with built-in providers and a model catalog. You can select models with /model, list them with zut --list-models, and add private models in $ZUT_HOME/models.json.

HTTP proxy

Set one global proxy for zut-managed HTTP and HTTPS traffic with the http_proxy key in $ZUT_HOME/config.json:

{
  "http_proxy": "http://127.0.0.1:7890"
}

zut applies this setting at startup. Existing HTTP_PROXY, HTTPS_PROXY, http_proxy, and https_proxy environment variables take precedence for their corresponding protocol. Standard NO_PROXY and no_proxy bypass lists remain effective. Restart zut after changing the setting.

config.json is not a credential store. If the proxy URL contains a username or password, prefer setting the proxy environment variables in a protected shell or service configuration rather than saving those credentials in config.json.

Use /login in interactive mode. Type in either provider picker to filter the list by provider ID or display name.

api key: stores an API key in $ZUT_HOME/auth.json when the provider uses a normal key.
subscription: stores OAuth credentials for subscription-backed providers.

Use /logout to remove stored credentials.

Some providers need more than a single pasted key. For those providers, /login shows setup instructions instead of opening a localhost browser form. This avoids broken browser flows in SSH, containers, and kubectl exec sessions.

Command-backed API keys

A provider can obtain its API key from a password manager or another local program. Configure this directly in $ZUT_HOME/auth.json:

{
  "openai": {
    "api_key_command": {
      "program": "op",
      "args": ["read", "op://Work/OpenAI/credential"],
      "timeout_ms": 120000
    }
  }
}

Custom provider credentials use the same object under additional_api_key_creds:

{
  "additional_api_key_creds": {
    "my-company": {
      "api_key_command": {
        "program": "secret-tool",
        "args": ["read", "my-company-api-key"]
      }
    }
  }
}

The program is started directly rather than through a shell. The timeout defaults to 120 seconds. It must write one non-empty line to stdout, with no more than 64 KiB of output. Trailing CR/LF characters are removed. Successful results stay only in process memory and are reused until zut exits.

Command-backed credentials count as logged in without being executed. zut materializes one only when selecting that provider; background model discovery skips it. /login with a normal key replaces the command, while /logout clears it. Because auth.json can cause program execution, keep it user-writable only and do not use files from untrusted sources.

Setup-instruction providers:

Amazon Bedrock
Google Vertex AI
Cloudflare Workers AI
Cloudflare AI Gateway
Azure OpenAI Responses

Subscription providers

These providers support subscription login:

Provider	Notes
Anthropic	Claude Pro/Max OAuth credentials.
OpenAI Codex	ChatGPT Plus/Pro Codex subscription route. Separate from the OpenAI API-key provider.
Kimi	Kimi subscription login.
xAI	SuperGrok or X Premium device-code login. The browser URL is prefilled with the device code.
GitHub Copilot	GitHub Copilot token flow.

OAuth tokens are stored in $ZUT_HOME/auth.json and refreshed when refresh is available.

API-key providers

These providers can use environment variables. Simple API-key providers can also be configured through /login. Providers that require extra cloud setup show instructions and should be configured with environment variables.

Provider	Environment variable	Stored key
Anthropic	`ANTHROPIC_API_KEY`	`anthropic`
OpenAI	`OPENAI_API_KEY`	`openai`
OpenAI Responses	`OPENAI_API_KEY`	`openai-responses`
Kimi	`KIMI_API_KEY` or `MOONSHOT_API_KEY`	`kimi`
Google Gemini	`GEMINI_API_KEY` or `GOOGLE_API_KEY`	`google`
DeepSeek	`DEEPSEEK_API_KEY`	`deepseek`
Moonshot AI	`MOONSHOT_API_KEY`	`moonshotai`
Moonshot AI China	`MOONSHOT_API_KEY`	`moonshotai-cn`
Groq	`GROQ_API_KEY`	`groq`
xAI	`XAI_API_KEY`	`xai`
Cerebras	`CEREBRAS_API_KEY`	`cerebras`
Together AI	`TOGETHER_API_KEY`	`together`
Hugging Face	`HF_TOKEN`	`huggingface`
OpenRouter	`OPENROUTER_API_KEY`	`openrouter`
Mistral	`MISTRAL_API_KEY`	`mistral`
ZAI	`ZAI_API_KEY`	`zai`
Xiaomi MiMo	`XIAOMI_API_KEY`	`xiaomi`
Xiaomi Token Plan Amsterdam	`XIAOMI_TOKEN_PLAN_AMS_API_KEY`	`xiaomi-token-plan-ams`
Xiaomi Token Plan China	`XIAOMI_TOKEN_PLAN_CN_API_KEY`	`xiaomi-token-plan-cn`
Xiaomi Token Plan Singapore	`XIAOMI_TOKEN_PLAN_SGP_API_KEY`	`xiaomi-token-plan-sgp`
MiniMax	`MINIMAX_API_KEY`	`minimax`
MiniMax China	`MINIMAX_CN_API_KEY` or `MINIMAX_API_KEY`	`minimax-cn`
Fireworks	`FIREWORKS_API_KEY`	`fireworks`
Vercel AI Gateway	`AI_GATEWAY_API_KEY`	`vercel-ai-gateway`
OpenCode Zen	`OPENCODE_API_KEY`	`opencode`
OpenCode Go	`OPENCODE_API_KEY`	`opencode-go`
GitHub Copilot token	`COPILOT_GITHUB_TOKEN` or `GITHUB_COPILOT_TOKEN`	`github-copilot`
Cloudflare Workers AI	`CLOUDFLARE_API_KEY`	`cloudflare-workers-ai`
Cloudflare AI Gateway	`CLOUDFLARE_API_KEY`	`cloudflare-ai-gateway`
Azure OpenAI Responses	`AZURE_OPENAI_API_KEY`	`azure-openai-responses`

Example:

export OPENROUTER_API_KEY=...
zut --provider openrouter

Fast mode

Use /fast or /settings to enable fast mode for subsequent model calls. The setting is off by default and is stored as fast_mode in $ZUT_HOME/config.json.

Fast mode currently requests OpenAI's Fast service tier for OpenAI Chat, OpenAI Responses, and OpenAI Codex requests. Enabling it while using another provider currently returns an error instead of silently changing that provider's request. Subagent children inherit the setting from their parent unless their profile sets fastMode explicitly.

Session identity and caching

zut supplies every provider request with a stable logical session ID and a per-prompt turn ID. They are opaque local correlations; adapters translate them only when their exact provider, model, and endpoint declaration supports it. For example, the OpenAI/Codex Responses route uses the stable session as its prompt_cache_key and, where required by the declared Codex route, its session-id header. A generic OpenAI-compatible endpoint never receives those extensions merely because it accepts an OpenAI-shaped request.

OpenAI Responses WebSocket mode

For the exact public endpoint https://api.openai.com/v1/responses, zut uses the Responses API WebSocket mode for the OpenAI Responses route. It keeps one connection per logical session, sends one response.create at a time, and continues the most recent completed response with previous_response_id plus only new tool or user input. The request uses store:false; its only provider-specific handshake header is Authorization: Bearer ..., never the ChatGPT/Codex account, routing, or session headers.

The capability is deliberately not inherited by --base-url, compatible providers, Azure, or the ChatGPT Codex subscription endpoint. Those clients continue to use their declared HTTP/SSE contracts. A request without a logical session ID, a failed WebSocket setup, an injected nonstandard RoundTripper, or a configured proxy falls back to HTTP/SSE with the same logical session/cache identity. Cancellation closes only the active session socket; a normally completed turn keeps it warm for the next continuation.

Local llama.cpp router

The llama.cpp provider connects to a multi-model router and is separate from the ollama provider. Ollama normally uses http://localhost:11434; entering that URL for llama.cpp management produces a 404 because Ollama does not implement the router endpoints.

Install a current llama.cpp build. On macOS:

brew install llama.cpp
# use `brew upgrade llama.cpp` for an existing installation

Start llama-server without --model, -m, or -hf. Those flags select one model and disable the router behavior zut expects.

mkdir -p ~/llama-models

llama-server \
  --models-dir ~/llama-models \
  --no-models-autoload \
  --jinja \
  --host 127.0.0.1 \
  --port 8080 \
  -ngl 999 \
  -c 32768

This configuration discovers GGUF files below ~/llama-models, leaves model loading under explicit user control, enables chat templates, requests GPU offload, and sets a 32K context. Tune the GPU layers and context size for the available memory.

Check the management API before opening zut:

curl http://127.0.0.1:8080/health
curl http://127.0.0.1:8080/models

/models must return JSON with a data array. A 404 indicates the wrong URL, an older server build, or single-model mode.

To save the connection, run /login, choose api key, and select llama.cpp. Enter http://127.0.0.1:8080, without /v1, followed by an optional bearer key. zut validates the URL and stores both values in $ZUT_HOME/auth.json. Environment variables override the saved connection:

export LLAMA_BASE_URL=http://127.0.0.1:8080
export LLAMA_API_KEY=optional-secret

If a key is configured, start the router with the same --api-key value. A server bound only to 127.0.0.1 normally does not need authentication.

After login, /llama becomes visible. It shows model state, searches Hugging Face for GGUF repositories, offers available quantizations, reports download and load progress, and explicitly loads or unloads models. Press d on a router-downloaded cache model to ask the router to remove it after confirmation. Models discovered through --models-dir or a preset are not removable through the router API and must be deleted from their configured source. Some llama.cpp versions retain shared Hugging Face repository artifacts such as mmproj files after removing the selected GGUF; remove that repository's cache directory manually if those artifacts are no longer needed. HF_TOKEN raises Hugging Face API limits and may be required for repository metadata. For gated files, approve access first and provide the authorized token to the llama-server process because the router performs the download.

Opening /model refreshes the router and displays its loaded models under provider llama.cpp. Unloaded models cannot handle inference and therefore remain exclusive to /llama until loaded. Inference is sent to the router's derived /v1 endpoint.

Ollama downloads are stored in Ollama's internal layout and do not automatically become llama.cpp models. Obtain a GGUF copy through /llama or place GGUF files under ~/llama-models, then restart the router after adding files manually.

Cloud providers

Amazon Bedrock

Bedrock is configured with AWS credentials, not a generic zut API-key entry. Use one of these credential sources:

# AWS profile
export AWS_PROFILE=your-profile

# IAM access keys
export AWS_ACCESS_KEY_ID=AKIA...
export AWS_SECRET_ACCESS_KEY=...
export AWS_SESSION_TOKEN=... # only for temporary credentials

# Bedrock API key bearer token
export AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-...

# Region
export AWS_REGION=us-east-1

ECS task roles, IRSA, and other AWS SDK credential-chain sources are also supported.

Example:

AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-... AWS_REGION=us-east-1 \
  zut --provider amazon-bedrock --model anthropic.claude-sonnet-4-5-20250929-v1:0

Some Bedrock models require regional inference-profile IDs for on-demand throughput, such as us. or eu. prefixed model IDs. zut rewrites known families automatically where possible. Claude Opus 5 uses global.anthropic.claude-opus-5; zut maps the bare foundation-model ID to that global profile and supports its adaptive reasoning levels. Explicit profile IDs and ARNs are left unchanged.

Google Vertex AI

Vertex can use a Google API key when available:

export GOOGLE_CLOUD_API_KEY=...
zut --provider google-vertex

For service-account or application-default credentials, set the standard Google environment variables used by your deployment.

Cloudflare AI Gateway

Cloudflare AI Gateway needs a Cloudflare token plus account and gateway IDs:

export CLOUDFLARE_API_KEY=...
export CLOUDFLARE_ACCOUNT_ID=...
export CLOUDFLARE_GATEWAY_ID=...
zut --provider cloudflare-ai-gateway

Cloudflare Workers AI

Workers AI needs a Cloudflare token and account ID:

export CLOUDFLARE_API_KEY=...
export CLOUDFLARE_ACCOUNT_ID=...
zut --provider cloudflare-workers-ai

Azure OpenAI Responses

export AZURE_OPENAI_API_KEY=...
export AZURE_OPENAI_BASE_URL=https://your-resource.openai.azure.com
export AZURE_OPENAI_API_VERSION=v1 # optional, v1 is the default
zut --provider azure-openai-responses

The provider uses Azure's Responses API. If deployment names differ from zut model IDs, map them without changing the catalog:

export AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-5.6-luna=luna-preview,gpt-5.6-sol=sol-preview'

Auth file

Credentials are stored in $ZUT_HOME/auth.json with user-only permissions when zut creates the file.

Example:

{
  "anthropic": { "api_key": "sk-ant-..." },
  "openai": { "api_key": "sk-..." },
  "google": { "api_key": "..." },
  "additional_api_key_creds": {
    "openrouter": { "api_key": "..." },
    "mistral": { "api_key": "..." }
  }
}

The top-level keys are used for providers with dedicated credential fields. Other API-key providers are stored under additional_api_key_creds. Prefer /login so zut writes the correct schema.

Custom providers and models

Use $ZUT_HOME/models.json for private models, deployment aliases, local servers, or OpenAI-compatible gateways that are not in the built-in catalog. User entries override built-in entries with the same provider and model ID, and adding a models.json no longer hides the built-in catalog: your entries are merged on top of the baked-in and live-discovered models.

A top-level provider key that is not a built-in id defines a custom provider. Give it a provider-level baseUrl and an api wire format (openai for OpenAI-compatible Chat Completions, the default, openai-responses for the OpenAI Responses API, or anthropic for the Anthropic Messages API). A model-level baseUrl overrides the provider-level one for that model, and an unknown api value falls back to openai with a warning.

{
  "providers": {
    "my-company": {
      "baseUrl": "https://llm.mycompany.com/v1",
      "api": "openai",
      "models": [
        { "id": "company-llm-v2", "name": "Company LLM v2" }
      ]
    }
  }
}

Custom providers are first-class: they appear in --list-models, /model, and /login. models.json never stores secrets. Supply the key through /login, --api-key, or a derived environment variable in upper snake case, so my-company reads MY_COMPANY_API_KEY. Because many self-hosted gateways do not expose a model-list endpoint, custom provider keys are accepted and stored without a verification probe; an invalid key surfaces on the first model call.

To retrieve this custom provider's key from a password manager, add a matching entry to $ZUT_HOME/auth.json:

{
  "additional_api_key_creds": {
    "my-company": {
      "api_key_command": {
        "program": "op",
        "args": ["read", "op://Work/OpenAI/credential"],
        "timeout_ms": 120000
      }
    }
  }
}

The provider IDs in models.json and auth.json must match. Then select the custom model directly:

zut --provider my-company --model company-llm-v2

Credential resolution

For each request, zut checks credentials in this order:

Explicit CLI key, such as --api-key.
Provider-specific environment variables (including derived custom-provider variables such as MY_COMPANY_API_KEY).
$ZUT_HOME/auth.json, including custom provider keys saved by /login.

models.json itself never stores credentials; it only describes models and their endpoints.

Bedrock then uses the AWS SDK credential chain for the actual request.

source

1# zut providers
2
3zut ships with built-in providers and a model catalog. You can select models
4with `/model`, list them with `zut --list-models`, and add private models in
5`$ZUT_HOME/models.json`.
6
7## HTTP proxy
8
9Set one global proxy for zut-managed HTTP and HTTPS traffic with the `http_proxy` key in `$ZUT_HOME/config.json`:
10
11```json
12{
13  "http_proxy": "http://127.0.0.1:7890"
14}
15```
16
17zut applies this setting at startup. Existing `HTTP_PROXY`, `HTTPS_PROXY`, `http_proxy`, and `https_proxy` environment variables take precedence for their corresponding protocol. Standard `NO_PROXY` and `no_proxy` bypass lists remain effective. Restart zut after changing the setting.
18
19`config.json` is not a credential store. If the proxy URL contains a username or password, prefer setting the proxy environment variables in a protected shell or service configuration rather than saving those credentials in `config.json`.
20
21## Login methods
22
23Use `/login` in interactive mode. Type in either provider picker to filter the list by provider ID or display name.
24
25- `api key`: stores an API key in `$ZUT_HOME/auth.json` when the provider uses a normal key.
26- `subscription`: stores OAuth credentials for subscription-backed providers.
27
28Use `/logout` to remove stored credentials.
29
30Some providers need more than a single pasted key. For those providers,
31`/login` shows setup instructions instead of opening a localhost browser form.
32This avoids broken browser flows in SSH, containers, and `kubectl exec`
33sessions.
34
35### Command-backed API keys
36
37A provider can obtain its API key from a password manager or another local program. Configure this directly in `$ZUT_HOME/auth.json`:
38
39```json
40{
41  "openai": {
42    "api_key_command": {
43      "program": "op",
44      "args": ["read", "op://Work/OpenAI/credential"],
45      "timeout_ms": 120000
46    }
47  }
48}
49```
50
51Custom provider credentials use the same object under `additional_api_key_creds`:
52
53```json
54{
55  "additional_api_key_creds": {
56    "my-company": {
57      "api_key_command": {
58        "program": "secret-tool",
59        "args": ["read", "my-company-api-key"]
60      }
61    }
62  }
63}
64```
65
66The program is started directly rather than through a shell. The timeout defaults to 120 seconds. It must write one non-empty line to stdout, with no more than 64 KiB of output. Trailing CR/LF characters are removed. Successful results stay only in process memory and are reused until zut exits.
67
68Command-backed credentials count as logged in without being executed. zut materializes one only when selecting that provider; background model discovery skips it. `/login` with a normal key replaces the command, while `/logout` clears it. Because `auth.json` can cause program execution, keep it user-writable only and do not use files from untrusted sources.
69
70Setup-instruction providers:
71
72- Amazon Bedrock
73- Google Vertex AI
74- Cloudflare Workers AI
75- Cloudflare AI Gateway
76- Azure OpenAI Responses
77
78## Subscription providers
79
80These providers support subscription login:
81
82| Provider | Notes |
83| --- | --- |
84| Anthropic | Claude Pro/Max OAuth credentials. |
85| OpenAI Codex | ChatGPT Plus/Pro Codex subscription route. Separate from the OpenAI API-key provider. |
86| Kimi | Kimi subscription login. |
87| xAI | SuperGrok or X Premium device-code login. The browser URL is prefilled with the device code. |
88| GitHub Copilot | GitHub Copilot token flow. |
89
90OAuth tokens are stored in `$ZUT_HOME/auth.json` and refreshed when refresh is
91available.
92
93## API-key providers
94
95These providers can use environment variables. Simple API-key providers can
96also be configured through `/login`. Providers that require extra cloud setup
97show instructions and should be configured with environment variables.
98
99| Provider | Environment variable | Stored key |
100| --- | --- | --- |
101| Anthropic | `ANTHROPIC_API_KEY` | `anthropic` |
102| OpenAI | `OPENAI_API_KEY` | `openai` |
103| OpenAI Responses | `OPENAI_API_KEY` | `openai-responses` |
104| Kimi | `KIMI_API_KEY` or `MOONSHOT_API_KEY` | `kimi` |
105| Google Gemini | `GEMINI_API_KEY` or `GOOGLE_API_KEY` | `google` |
106| DeepSeek | `DEEPSEEK_API_KEY` | `deepseek` |
107| Moonshot AI | `MOONSHOT_API_KEY` | `moonshotai` |
108| Moonshot AI China | `MOONSHOT_API_KEY` | `moonshotai-cn` |
109| Groq | `GROQ_API_KEY` | `groq` |
110| xAI | `XAI_API_KEY` | `xai` |
111| Cerebras | `CEREBRAS_API_KEY` | `cerebras` |
112| Together AI | `TOGETHER_API_KEY` | `together` |
113| Hugging Face | `HF_TOKEN` | `huggingface` |
114| OpenRouter | `OPENROUTER_API_KEY` | `openrouter` |
115| Mistral | `MISTRAL_API_KEY` | `mistral` |
116| ZAI | `ZAI_API_KEY` | `zai` |
117| Xiaomi MiMo | `XIAOMI_API_KEY` | `xiaomi` |
118| Xiaomi Token Plan Amsterdam | `XIAOMI_TOKEN_PLAN_AMS_API_KEY` | `xiaomi-token-plan-ams` |
119| Xiaomi Token Plan China | `XIAOMI_TOKEN_PLAN_CN_API_KEY` | `xiaomi-token-plan-cn` |
120| Xiaomi Token Plan Singapore | `XIAOMI_TOKEN_PLAN_SGP_API_KEY` | `xiaomi-token-plan-sgp` |
121| MiniMax | `MINIMAX_API_KEY` | `minimax` |
122| MiniMax China | `MINIMAX_CN_API_KEY` or `MINIMAX_API_KEY` | `minimax-cn` |
123| Fireworks | `FIREWORKS_API_KEY` | `fireworks` |
124| Vercel AI Gateway | `AI_GATEWAY_API_KEY` | `vercel-ai-gateway` |
125| OpenCode Zen | `OPENCODE_API_KEY` | `opencode` |
126| OpenCode Go | `OPENCODE_API_KEY` | `opencode-go` |
127| GitHub Copilot token | `COPILOT_GITHUB_TOKEN` or `GITHUB_COPILOT_TOKEN` | `github-copilot` |
128| Cloudflare Workers AI | `CLOUDFLARE_API_KEY` | `cloudflare-workers-ai` |
129| Cloudflare AI Gateway | `CLOUDFLARE_API_KEY` | `cloudflare-ai-gateway` |
130| Azure OpenAI Responses | `AZURE_OPENAI_API_KEY` | `azure-openai-responses` |
131
132Example:
133
134```bash
135export OPENROUTER_API_KEY=...
136zut --provider openrouter
137```
138
139## Fast mode
140
141Use `/fast` or `/settings` to enable **fast mode** for subsequent model calls.
142The setting is off by default and is stored as `fast_mode` in
143`$ZUT_HOME/config.json`.
144
145Fast mode currently requests OpenAI's Fast service tier for OpenAI Chat,
146OpenAI Responses, and OpenAI Codex requests. Enabling it while using another
147provider currently returns an error instead of silently changing that provider's
148request. Subagent children inherit the setting from their parent unless their
149profile sets `fastMode` explicitly.
150
151## Session identity and caching
152
153zut supplies every provider request with a stable logical session ID and a
154per-prompt turn ID. They are opaque local correlations; adapters translate them
155only when their exact provider, model, and endpoint declaration supports it.
156For example, the OpenAI/Codex Responses route uses the stable session as its
157`prompt_cache_key` and, where required by the declared Codex route, its
158`session-id` header. A generic OpenAI-compatible endpoint never receives those
159extensions merely because it accepts an OpenAI-shaped request.
160
161### OpenAI Responses WebSocket mode
162
163For the exact public endpoint `https://api.openai.com/v1/responses`, zut uses
164the Responses API WebSocket mode for the OpenAI Responses route. It keeps one
165connection per logical session, sends one `response.create` at a time, and
166continues the most recent completed response with `previous_response_id` plus
167only new tool or user input. The request uses `store:false`; its only
168provider-specific handshake header is `Authorization: Bearer ...`, never the
169ChatGPT/Codex account, routing, or session headers.
170
171The capability is deliberately not inherited by `--base-url`, compatible
172providers, Azure, or the ChatGPT Codex subscription endpoint. Those clients
173continue to use their declared HTTP/SSE contracts. A request without a logical
174session ID, a failed WebSocket setup,
175an injected nonstandard RoundTripper, or a configured proxy falls back to
176HTTP/SSE with the same logical session/cache identity. Cancellation closes
177only the active session socket; a normally completed turn keeps it warm for
178the next continuation.
179
180
181## Local llama.cpp router
182
183The `llama.cpp` provider connects to a multi-model router and is separate from the `ollama` provider. Ollama normally uses `http://localhost:11434`; entering that URL for llama.cpp management produces a 404 because Ollama does not implement the router endpoints.
184
185Install a current llama.cpp build. On macOS:
186
187```bash
188brew install llama.cpp
189# use `brew upgrade llama.cpp` for an existing installation
190```
191
192Start `llama-server` without `--model`, `-m`, or `-hf`. Those flags select one model and disable the router behavior zut expects.
193
194```bash
195mkdir -p ~/llama-models
196
197llama-server \
198  --models-dir ~/llama-models \
199  --no-models-autoload \
200  --jinja \
201  --host 127.0.0.1 \
202  --port 8080 \
203  -ngl 999 \
204  -c 32768
205```
206
207This configuration discovers GGUF files below `~/llama-models`, leaves model loading under explicit user control, enables chat templates, requests GPU offload, and sets a 32K context. Tune the GPU layers and context size for the available memory.
208
209Check the management API before opening zut:
210
211```bash
212curl http://127.0.0.1:8080/health
213curl http://127.0.0.1:8080/models
214```
215
216`/models` must return JSON with a `data` array. A 404 indicates the wrong URL, an older server build, or single-model mode.
217
218To save the connection, run `/login`, choose `api key`, and select `llama.cpp`. Enter `http://127.0.0.1:8080`, without `/v1`, followed by an optional bearer key. zut validates the URL and stores both values in `$ZUT_HOME/auth.json`. Environment variables override the saved connection:
219
220```bash
221export LLAMA_BASE_URL=http://127.0.0.1:8080
222export LLAMA_API_KEY=optional-secret
223```
224
225If a key is configured, start the router with the same `--api-key` value. A server bound only to `127.0.0.1` normally does not need authentication.
226
227After login, `/llama` becomes visible. It shows model state, searches Hugging Face for GGUF repositories, offers available quantizations, reports download and load progress, and explicitly loads or unloads models. Press `d` on a router-downloaded cache model to ask the router to remove it after confirmation. Models discovered through `--models-dir` or a preset are not removable through the router API and must be deleted from their configured source. Some llama.cpp versions retain shared Hugging Face repository artifacts such as `mmproj` files after removing the selected GGUF; remove that repository's cache directory manually if those artifacts are no longer needed. `HF_TOKEN` raises Hugging Face API limits and may be required for repository metadata. For gated files, approve access first and provide the authorized token to the `llama-server` process because the router performs the download.
228
229Opening `/model` refreshes the router and displays its loaded models under provider `llama.cpp`. Unloaded models cannot handle inference and therefore remain exclusive to `/llama` until loaded. Inference is sent to the router's derived `/v1` endpoint.
230
231Ollama downloads are stored in Ollama's internal layout and do not automatically become llama.cpp models. Obtain a GGUF copy through `/llama` or place GGUF files under `~/llama-models`, then restart the router after adding files manually.
232
233## Cloud providers
234
235### Amazon Bedrock
236
237Bedrock is configured with AWS credentials, not a generic zut API-key entry.
238Use one of these credential sources:
239
240```bash
241# AWS profile
242export AWS_PROFILE=your-profile
243
244# IAM access keys
245export AWS_ACCESS_KEY_ID=AKIA...
246export AWS_SECRET_ACCESS_KEY=...
247export AWS_SESSION_TOKEN=... # only for temporary credentials
248
249# Bedrock API key bearer token
250export AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-...
251
252# Region
253export AWS_REGION=us-east-1
254```
255
256ECS task roles, IRSA, and other AWS SDK credential-chain sources are also
257supported.
258
259Example:
260
261```bash
262AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-... AWS_REGION=us-east-1 \
263  zut --provider amazon-bedrock --model anthropic.claude-sonnet-4-5-20250929-v1:0
264```
265
266Some Bedrock models require regional inference-profile IDs for on-demand
267throughput, such as `us.` or `eu.` prefixed model IDs. zut rewrites known
268families automatically where possible. Claude Opus 5 uses
269`global.anthropic.claude-opus-5`; zut maps the bare foundation-model ID to that
270global profile and supports its adaptive reasoning levels. Explicit profile IDs
271and ARNs are left unchanged.
272
273### Google Vertex AI
274
275Vertex can use a Google API key when available:
276
277```bash
278export GOOGLE_CLOUD_API_KEY=...
279zut --provider google-vertex
280```
281
282For service-account or application-default credentials, set the standard
283Google environment variables used by your deployment.
284
285### Cloudflare AI Gateway
286
287Cloudflare AI Gateway needs a Cloudflare token plus account and gateway IDs:
288
289```bash
290export CLOUDFLARE_API_KEY=...
291export CLOUDFLARE_ACCOUNT_ID=...
292export CLOUDFLARE_GATEWAY_ID=...
293zut --provider cloudflare-ai-gateway
294```
295
296### Cloudflare Workers AI
297
298Workers AI needs a Cloudflare token and account ID:
299
300```bash
301export CLOUDFLARE_API_KEY=...
302export CLOUDFLARE_ACCOUNT_ID=...
303zut --provider cloudflare-workers-ai
304```
305
306### Azure OpenAI Responses
307
308```bash
309export AZURE_OPENAI_API_KEY=...
310export AZURE_OPENAI_BASE_URL=https://your-resource.openai.azure.com
311export AZURE_OPENAI_API_VERSION=v1 # optional, v1 is the default
312zut --provider azure-openai-responses
313```
314
315The provider uses Azure's Responses API. If deployment names differ from zut
316model IDs, map them without changing the catalog:
317
318```bash
319export AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-5.6-luna=luna-preview,gpt-5.6-sol=sol-preview'
320```
321
322## Auth file
323
324Credentials are stored in `$ZUT_HOME/auth.json` with user-only permissions
325when zut creates the file.
326
327Example:
328
329```json
330{
331  "anthropic": { "api_key": "sk-ant-..." },
332  "openai": { "api_key": "sk-..." },
333  "google": { "api_key": "..." },
334  "additional_api_key_creds": {
335    "openrouter": { "api_key": "..." },
336    "mistral": { "api_key": "..." }
337  }
338}
339```
340
341The top-level keys are used for providers with dedicated credential fields.
342Other API-key providers are stored under `additional_api_key_creds`. Prefer
343`/login` so zut writes the correct schema.
344
345## Custom providers and models
346
347Use `$ZUT_HOME/models.json` for private models, deployment aliases, local
348servers, or OpenAI-compatible gateways that are not in the built-in catalog.
349User entries override built-in entries with the same provider and model ID, and
350adding a `models.json` no longer hides the built-in catalog: your entries are
351merged on top of the baked-in and live-discovered models.
352
353A top-level provider key that is not a built-in id defines a custom provider.
354Give it a provider-level `baseUrl` and an `api` wire format (`openai` for
355OpenAI-compatible Chat Completions, the default, `openai-responses` for the
356OpenAI Responses API, or `anthropic` for the Anthropic Messages API). A
357model-level `baseUrl` overrides the provider-level one for that model, and an
358unknown `api` value falls back to `openai` with a warning.
359
360```json
361{
362  "providers": {
363    "my-company": {
364      "baseUrl": "https://llm.mycompany.com/v1",
365      "api": "openai",
366      "models": [
367        { "id": "company-llm-v2", "name": "Company LLM v2" }
368      ]
369    }
370  }
371}
372```
373
374Custom providers are first-class: they appear in `--list-models`, `/model`, and
375`/login`. `models.json` never stores secrets. Supply the key through `/login`,
376`--api-key`, or a derived environment variable in upper snake case, so
377`my-company` reads `MY_COMPANY_API_KEY`. Because many self-hosted gateways do
378not expose a model-list endpoint, custom provider keys are accepted and stored
379without a verification probe; an invalid key surfaces on the first model call.
380
381To retrieve this custom provider's key from a password manager, add a matching
382entry to `$ZUT_HOME/auth.json`:
383
384```json
385{
386  "additional_api_key_creds": {
387    "my-company": {
388      "api_key_command": {
389        "program": "op",
390        "args": ["read", "op://Work/OpenAI/credential"],
391        "timeout_ms": 120000
392      }
393    }
394  }
395}
396```
397
398The provider IDs in `models.json` and `auth.json` must match. Then select the
399custom model directly:
400
401```sh
402zut --provider my-company --model company-llm-v2
403```
404
405## Credential resolution
406
407For each request, zut checks credentials in this order:
408
4091. Explicit CLI key, such as `--api-key`.
4102. Provider-specific environment variables (including derived custom-provider
411   variables such as `MY_COMPANY_API_KEY`).
4123. `$ZUT_HOME/auth.json`, including custom provider keys saved by `/login`.
413
414`models.json` itself never stores credentials; it only describes models and
415their endpoints.
416
417Bedrock then uses the AWS SDK credential chain for the actual request.

providers.md RawHistoryFolder

zut providers

HTTP proxy

Login methods

Command-backed API keys

Subscription providers

API-key providers

Fast mode

Session identity and caching

OpenAI Responses WebSocket mode

Local llama.cpp router

Cloud providers

Amazon Bedrock

Google Vertex AI

Cloudflare AI Gateway

Cloudflare Workers AI

Azure OpenAI Responses

Auth file

Custom providers and models

Credential resolution

providers.md Raw History Folder