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, 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.

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, OpenAI
146Responses, and OpenAI Codex requests. Enabling it while using another provider
147currently returns an error instead of silently changing that provider's request.
148Subagent children inherit the setting from their parent unless their profile
149sets `fastMode` explicitly.
150
151## Local llama.cpp router
152
153The `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.
154
155Install a current llama.cpp build. On macOS:
156
157```bash
158brew install llama.cpp
159# use `brew upgrade llama.cpp` for an existing installation
160```
161
162Start `llama-server` without `--model`, `-m`, or `-hf`. Those flags select one model and disable the router behavior zut expects.
163
164```bash
165mkdir -p ~/llama-models
166
167llama-server \
168  --models-dir ~/llama-models \
169  --no-models-autoload \
170  --jinja \
171  --host 127.0.0.1 \
172  --port 8080 \
173  -ngl 999 \
174  -c 32768
175```
176
177This 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.
178
179Check the management API before opening zut:
180
181```bash
182curl http://127.0.0.1:8080/health
183curl http://127.0.0.1:8080/models
184```
185
186`/models` must return JSON with a `data` array. A 404 indicates the wrong URL, an older server build, or single-model mode.
187
188To 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:
189
190```bash
191export LLAMA_BASE_URL=http://127.0.0.1:8080
192export LLAMA_API_KEY=optional-secret
193```
194
195If 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.
196
197After 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.
198
199Opening `/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.
200
201Ollama 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.
202
203## Cloud providers
204
205### Amazon Bedrock
206
207Bedrock is configured with AWS credentials, not a generic zut API-key entry.
208Use one of these credential sources:
209
210```bash
211# AWS profile
212export AWS_PROFILE=your-profile
213
214# IAM access keys
215export AWS_ACCESS_KEY_ID=AKIA...
216export AWS_SECRET_ACCESS_KEY=...
217export AWS_SESSION_TOKEN=... # only for temporary credentials
218
219# Bedrock API key bearer token
220export AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-...
221
222# Region
223export AWS_REGION=us-east-1
224```
225
226ECS task roles, IRSA, and other AWS SDK credential-chain sources are also
227supported.
228
229Example:
230
231```bash
232AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-... AWS_REGION=us-east-1 \
233  zut --provider amazon-bedrock --model anthropic.claude-sonnet-4-5-20250929-v1:0
234```
235
236Some Bedrock models require regional inference-profile IDs for on-demand
237throughput, such as `us.` or `eu.` prefixed model IDs. zut rewrites known
238families automatically where possible. Claude Opus 5 uses
239`global.anthropic.claude-opus-5`; zut maps the bare foundation-model ID to that
240global profile and supports its adaptive reasoning levels. Explicit profile IDs
241and ARNs are left unchanged.
242
243### Google Vertex AI
244
245Vertex can use a Google API key when available:
246
247```bash
248export GOOGLE_CLOUD_API_KEY=...
249zut --provider google-vertex
250```
251
252For service-account or application-default credentials, set the standard
253Google environment variables used by your deployment.
254
255### Cloudflare AI Gateway
256
257Cloudflare AI Gateway needs a Cloudflare token plus account and gateway IDs:
258
259```bash
260export CLOUDFLARE_API_KEY=...
261export CLOUDFLARE_ACCOUNT_ID=...
262export CLOUDFLARE_GATEWAY_ID=...
263zut --provider cloudflare-ai-gateway
264```
265
266### Cloudflare Workers AI
267
268Workers AI needs a Cloudflare token and account ID:
269
270```bash
271export CLOUDFLARE_API_KEY=...
272export CLOUDFLARE_ACCOUNT_ID=...
273zut --provider cloudflare-workers-ai
274```
275
276### Azure OpenAI Responses
277
278```bash
279export AZURE_OPENAI_API_KEY=...
280export AZURE_OPENAI_BASE_URL=https://your-resource.openai.azure.com
281export AZURE_OPENAI_API_VERSION=v1 # optional, v1 is the default
282zut --provider azure-openai-responses
283```
284
285The provider uses Azure's Responses API. If deployment names differ from zut
286model IDs, map them without changing the catalog:
287
288```bash
289export AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-5.6-luna=luna-preview,gpt-5.6-sol=sol-preview'
290```
291
292## Auth file
293
294Credentials are stored in `$ZUT_HOME/auth.json` with user-only permissions
295when zut creates the file.
296
297Example:
298
299```json
300{
301  "anthropic": { "api_key": "sk-ant-..." },
302  "openai": { "api_key": "sk-..." },
303  "google": { "api_key": "..." },
304  "additional_api_key_creds": {
305    "openrouter": { "api_key": "..." },
306    "mistral": { "api_key": "..." }
307  }
308}
309```
310
311The top-level keys are used for providers with dedicated credential fields.
312Other API-key providers are stored under `additional_api_key_creds`. Prefer
313`/login` so zut writes the correct schema.
314
315## Custom providers and models
316
317Use `$ZUT_HOME/models.json` for private models, deployment aliases, local
318servers, or OpenAI-compatible gateways that are not in the built-in catalog.
319User entries override built-in entries with the same provider and model ID, and
320adding a `models.json` no longer hides the built-in catalog: your entries are
321merged on top of the baked-in and live-discovered models.
322
323A top-level provider key that is not a built-in id defines a custom provider.
324Give it a provider-level `baseUrl` and an `api` wire format (`openai` for
325OpenAI-compatible Chat Completions, the default, `openai-responses` for the
326OpenAI Responses API, or `anthropic` for the Anthropic Messages API). A
327model-level `baseUrl` overrides the provider-level one for that model, and an
328unknown `api` value falls back to `openai` with a warning.
329
330```json
331{
332  "providers": {
333    "my-company": {
334      "baseUrl": "https://llm.mycompany.com/v1",
335      "api": "openai",
336      "models": [
337        { "id": "company-llm-v2", "name": "Company LLM v2" }
338      ]
339    }
340  }
341}
342```
343
344Custom providers are first-class: they appear in `--list-models`, `/model`, and
345`/login`. `models.json` never stores secrets. Supply the key through `/login`,
346`--api-key`, or a derived environment variable in upper snake case, so
347`my-company` reads `MY_COMPANY_API_KEY`. Because many self-hosted gateways do
348not expose a model-list endpoint, custom provider keys are accepted and stored
349without a verification probe; an invalid key surfaces on the first model call.
350
351To retrieve this custom provider's key from a password manager, add a matching
352entry to `$ZUT_HOME/auth.json`:
353
354```json
355{
356  "additional_api_key_creds": {
357    "my-company": {
358      "api_key_command": {
359        "program": "op",
360        "args": ["read", "op://Work/OpenAI/credential"],
361        "timeout_ms": 120000
362      }
363    }
364  }
365}
366```
367
368The provider IDs in `models.json` and `auth.json` must match. Then select the
369custom model directly:
370
371```sh
372zut --provider my-company --model company-llm-v2
373```
374
375## Credential resolution
376
377For each request, zut checks credentials in this order:
378
3791. Explicit CLI key, such as `--api-key`.
3802. Provider-specific environment variables (including derived custom-provider
381   variables such as `MY_COMPANY_API_KEY`).
3823. `$ZUT_HOME/auth.json`, including custom provider keys saved by `/login`.
383
384`models.json` itself never stores credentials; it only describes models and
385their endpoints.
386
387Bedrock 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

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