1# Configuration
2
3There are various aspects about the Agent Panel that you can customize.
4All of them can be seen by either visiting [the Configuring Zed page](../configuring-zed.md#agent) or by running the `zed: open default settings` action and searching for `"agent"`.
5
6Alternatively, you can also visit the panel's Settings view by running the `agent: open configuration` action or going to the top-right menu and hitting "Settings".
7
8## LLM Providers
9
10Zed supports multiple large language model providers.
11Here's an overview of the supported providers and tool call support:
12
13| Provider | Tool Use Supported |
14| ----------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
15| [Amazon Bedrock](#amazon-bedrock) | Depends on the model |
16| [Anthropic](#anthropic) | ✅ |
17| [DeepSeek](#deepseek) | ✅ |
18| [GitHub Copilot Chat](#github-copilot-chat) | For some models ([link](https://github.com/zed-industries/zed/blob/9e0330ba7d848755c9734bf456c716bddf0973f3/crates/language_models/src/provider/copilot_chat.rs#L189-L198)) |
19| [Google AI](#google-ai) | ✅ |
20| [LM Studio](#lmstudio) | ✅ |
21| [Mistral](#mistral) | ✅ |
22| [Ollama](#ollama) | ✅ |
23| [OpenAI](#openai) | ✅ |
24| [OpenAI API Compatible](#openai-api-compatible) | 🚫 |
25| [OpenRouter](#openrouter) | ✅ |
26
27## Use Your Own Keys {#use-your-own-keys}
28
29While Zed offers hosted versions of models through [our various plans](./plans-and-usage.md), we're always happy to support users wanting to supply their own API keys.
30Below, you can learn how to do that for each provider.
31
32> Using your own API keys is _free_—you do not need to subscribe to a Zed plan to use our AI features with your own keys.
33
34### Amazon Bedrock {#amazon-bedrock}
35
36> ✅ Supports tool use with models that support streaming tool use.
37> More details can be found in the [Amazon Bedrock's Tool Use documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-supported-models-features.html).
38
39To use Amazon Bedrock's models, an AWS authentication is required.
40Ensure your credentials have the following permissions set up:
41
42- `bedrock:InvokeModelWithResponseStream`
43- `bedrock:InvokeModel`
44- `bedrock:ConverseStream`
45
46Your IAM policy should look similar to:
47
48```json
49{
50 "Version": "2012-10-17",
51 "Statement": [
52 {
53 "Effect": "Allow",
54 "Action": [
55 "bedrock:InvokeModel",
56 "bedrock:InvokeModelWithResponseStream",
57 "bedrock:ConverseStream"
58 ],
59 "Resource": "*"
60 }
61 ]
62}
63```
64
65With that done, choose one of the two authentication methods:
66
67#### Authentication via Named Profile (Recommended)
68
691. Ensure you have the AWS CLI installed and configured with a named profile
702. Open your `settings.json` (`zed: open settings`) and include the `bedrock` key under `language_models` with the following settings:
71 ```json
72 {
73 "language_models": {
74 "bedrock": {
75 "authentication_method": "named_profile",
76 "region": "your-aws-region",
77 "profile": "your-profile-name"
78 }
79 }
80 }
81 ```
82
83#### Authentication via Static Credentials
84
85While it's possible to configure through the Agent Panel settings UI by entering your AWS access key and secret directly, we recommend using named profiles instead for better security practices.
86To do this:
87
881. Create an IAM User that you can assume in the [IAM Console](https://us-east-1.console.aws.amazon.com/iam/home?region=us-east-1#/users).
892. Create security credentials for that User, save them and keep them secure.
903. Open the Agent Configuration with (`agent: open configuration`) and go to the Amazon Bedrock section
914. Copy the credentials from Step 2 into the respective **Access Key ID**, **Secret Access Key**, and **Region** fields.
92
93#### Cross-Region Inference
94
95The Zed implementation of Amazon Bedrock uses [Cross-Region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html) for all the models and region combinations that support it.
96With Cross-Region inference, you can distribute traffic across multiple AWS Regions, enabling higher throughput.
97
98For example, if you use `Claude Sonnet 3.7 Thinking` from `us-east-1`, it may be processed across the US regions, namely: `us-east-1`, `us-east-2`, or `us-west-2`.
99Cross-Region inference requests are kept within the AWS Regions that are part of the geography where the data originally resides.
100For example, a request made within the US is kept within the AWS Regions in the US.
101
102Although the data remains stored only in the source Region, your input prompts and output results might move outside of your source Region during cross-Region inference.
103All data will be transmitted encrypted across Amazon's secure network.
104
105We will support Cross-Region inference for each of the models on a best-effort basis, please refer to the [Cross-Region Inference method Code](https://github.com/zed-industries/zed/blob/main/crates/bedrock/src/models.rs#L297).
106
107For the most up-to-date supported regions and models, refer to the [Supported Models and Regions for Cross Region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html).
108
109### Anthropic {#anthropic}
110
111> ✅ Supports tool use
112
113You can use Anthropic models by choosing it via the model dropdown in the Agent Panel.
114
1151. Sign up for Anthropic and [create an API key](https://console.anthropic.com/settings/keys)
1162. Make sure that your Anthropic account has credits
1173. Open the settings view (`agent: open configuration`) and go to the Anthropic section
1184. Enter your Anthropic API key
119
120Even if you pay for Claude Pro, you will still have to [pay for additional credits](https://console.anthropic.com/settings/plans) to use it via the API.
121
122Zed will also use the `ANTHROPIC_API_KEY` environment variable if it's defined.
123
124#### Custom Models {#anthropic-custom-models}
125
126You can add custom models to the Anthropic provider by adding the following to your Zed `settings.json`:
127
128```json
129{
130 "language_models": {
131 "anthropic": {
132 "available_models": [
133 {
134 "name": "claude-3-5-sonnet-20240620",
135 "display_name": "Sonnet 2024-June",
136 "max_tokens": 128000,
137 "max_output_tokens": 2560,
138 "cache_configuration": {
139 "max_cache_anchors": 10,
140 "min_total_token": 10000,
141 "should_speculate": false
142 },
143 "tool_override": "some-model-that-supports-toolcalling"
144 }
145 ]
146 }
147 }
148}
149```
150
151Custom models will be listed in the model dropdown in the Agent Panel.
152
153You can configure a model to use [extended thinking](https://docs.anthropic.com/en/docs/about-claude/models/extended-thinking-models) (if it supports it) by changing the mode in your model's configuration to `thinking`, for example:
154
155```json
156{
157 "name": "claude-sonnet-4-latest",
158 "display_name": "claude-sonnet-4-thinking",
159 "max_tokens": 200000,
160 "mode": {
161 "type": "thinking",
162 "budget_tokens": 4_096
163 }
164}
165```
166
167### DeepSeek {#deepseek}
168
169> ✅ Supports tool use
170
1711. Visit the DeepSeek platform and [create an API key](https://platform.deepseek.com/api_keys)
1722. Open the settings view (`agent: open configuration`) and go to the DeepSeek section
1733. Enter your DeepSeek API key
174
175The DeepSeek API key will be saved in your keychain.
176
177Zed will also use the `DEEPSEEK_API_KEY` environment variable if it's defined.
178
179#### Custom Models {#deepseek-custom-models}
180
181The Zed agent comes pre-configured to use the latest version for common models (DeepSeek Chat, DeepSeek Reasoner).
182If you wish to use alternate models or customize the API endpoint, you can do so by adding the following to your Zed `settings.json`:
183
184```json
185{
186 "language_models": {
187 "deepseek": {
188 "api_url": "https://api.deepseek.com",
189 "available_models": [
190 {
191 "name": "deepseek-chat",
192 "display_name": "DeepSeek Chat",
193 "max_tokens": 64000
194 },
195 {
196 "name": "deepseek-reasoner",
197 "display_name": "DeepSeek Reasoner",
198 "max_tokens": 64000,
199 "max_output_tokens": 4096
200 }
201 ]
202 }
203 }
204}
205```
206
207Custom models will be listed in the model dropdown in the Agent Panel.
208You can also modify the `api_url` to use a custom endpoint if needed.
209
210### GitHub Copilot Chat {#github-copilot-chat}
211
212> ✅ Supports tool use in some cases.
213> Visit [the Copilot Chat code](https://github.com/zed-industries/zed/blob/9e0330ba7d848755c9734bf456c716bddf0973f3/crates/language_models/src/provider/copilot_chat.rs#L189-L198) for the supported subset.
214
215You can use GitHub Copilot Chat with the Zed agent by choosing it via the model dropdown in the Agent Panel.
216
2171. Open the settings view (`agent: open configuration`) and go to the GitHub Copilot Chat section
2182. Click on `Sign in to use GitHub Copilot`, follow the steps shown in the modal.
219
220Alternatively, you can provide an OAuth token via the `GH_COPILOT_TOKEN` environment variable.
221
222> **Note**: If you don't see specific models in the dropdown, you may need to enable them in your [GitHub Copilot settings](https://github.com/settings/copilot/features).
223
224To use Copilot Enterprise with Zed (for both agent and inline completions), you must configure your enterprise endpoint as described in [Configuring GitHub Copilot Enterprise](./edit-prediction.md#github-copilot-enterprise).
225
226### Google AI {#google-ai}
227
228> ✅ Supports tool use
229
230You can use Gemini models with the Zed agent by choosing it via the model dropdown in the Agent Panel.
231
2321. Go to the Google AI Studio site and [create an API key](https://aistudio.google.com/app/apikey).
2332. Open the settings view (`agent: open configuration`) and go to the Google AI section
2343. Enter your Google AI API key and press enter.
235
236The Google AI API key will be saved in your keychain.
237
238Zed will also use the `GOOGLE_AI_API_KEY` environment variable if it's defined.
239
240#### Custom Models {#google-ai-custom-models}
241
242By default, Zed will use `stable` versions of models, but you can use specific versions of models, including [experimental models](https://ai.google.dev/gemini-api/docs/models/experimental-models). You can configure a model to use [thinking mode](https://ai.google.dev/gemini-api/docs/thinking) (if it supports it) by adding a `mode` configuration to your model. This is useful for controlling reasoning token usage and response speed. If not specified, Gemini will automatically choose the thinking budget.
243
244Here is an example of a custom Google AI model you could add to your Zed `settings.json`:
245
246```json
247{
248 "language_models": {
249 "google": {
250 "available_models": [
251 {
252 "name": "gemini-2.5-flash-preview-05-20",
253 "display_name": "Gemini 2.5 Flash (Thinking)",
254 "max_tokens": 1000000,
255 "mode": {
256 "type": "thinking",
257 "budget_tokens": 24000
258 }
259 }
260 ]
261 }
262 }
263}
264```
265
266Custom models will be listed in the model dropdown in the Agent Panel.
267
268### LM Studio {#lmstudio}
269
270> ✅ Supports tool use
271
2721. Download and install [the latest version of LM Studio](https://lmstudio.ai/download)
2732. In the app press `cmd/ctrl-shift-m` and download at least one model (e.g., qwen2.5-coder-7b). Alternatively, you can get models via the LM Studio CLI:
274
275 ```sh
276 lms get qwen2.5-coder-7b
277 ```
278
2793. Make sure the LM Studio API server is running by executing:
280
281 ```sh
282 lms server start
283 ```
284
285Tip: Set [LM Studio as a login item](https://lmstudio.ai/docs/advanced/headless#run-the-llm-service-on-machine-login) to automate running the LM Studio server.
286
287### Mistral {#mistral}
288
289> ✅ Supports tool use
290
2911. Visit the Mistral platform and [create an API key](https://console.mistral.ai/api-keys/)
2922. Open the configuration view (`agent: open configuration`) and navigate to the Mistral section
2933. Enter your Mistral API key
294
295The Mistral API key will be saved in your keychain.
296
297Zed will also use the `MISTRAL_API_KEY` environment variable if it's defined.
298
299#### Custom Models {#mistral-custom-models}
300
301The Zed agent comes pre-configured with several Mistral models (codestral-latest, mistral-large-latest, mistral-medium-latest, mistral-small-latest, open-mistral-nemo, and open-codestral-mamba).
302All the default models support tool use.
303If you wish to use alternate models or customize their parameters, you can do so by adding the following to your Zed `settings.json`:
304
305```json
306{
307 "language_models": {
308 "mistral": {
309 "api_url": "https://api.mistral.ai/v1",
310 "available_models": [
311 {
312 "name": "mistral-tiny-latest",
313 "display_name": "Mistral Tiny",
314 "max_tokens": 32000,
315 "max_output_tokens": 4096,
316 "max_completion_tokens": 1024,
317 "supports_tools": true,
318 "supports_images": false
319 }
320 ]
321 }
322 }
323}
324```
325
326Custom models will be listed in the model dropdown in the Agent Panel.
327
328### Ollama {#ollama}
329
330> ✅ Supports tool use
331
332Download and install Ollama from [ollama.com/download](https://ollama.com/download) (Linux or macOS) and ensure it's running with `ollama --version`.
333
3341. Download one of the [available models](https://ollama.com/models), for example, for `mistral`:
335
336 ```sh
337 ollama pull mistral
338 ```
339
3402. Make sure that the Ollama server is running. You can start it either via running Ollama.app (macOS) or launching:
341
342 ```sh
343 ollama serve
344 ```
345
3463. In the Agent Panel, select one of the Ollama models using the model dropdown.
347
348#### Ollama Context Length {#ollama-context}
349
350Zed has pre-configured maximum context lengths (`max_tokens`) to match the capabilities of common models.
351Zed API requests to Ollama include this as the `num_ctx` parameter, but the default values do not exceed `16384` so users with ~16GB of RAM are able to use most models out of the box.
352
353See [get_max_tokens in ollama.rs](https://github.com/zed-industries/zed/blob/main/crates/ollama/src/ollama.rs) for a complete set of defaults.
354
355> **Note**: Token counts displayed in the Agent Panel are only estimates and will differ from the model's native tokenizer.
356
357Depending on your hardware or use-case you may wish to limit or increase the context length for a specific model via settings.json:
358
359```json
360{
361 "language_models": {
362 "ollama": {
363 "api_url": "http://localhost:11434",
364 "available_models": [
365 {
366 "name": "qwen2.5-coder",
367 "display_name": "qwen 2.5 coder 32K",
368 "max_tokens": 32768,
369 "supports_tools": true,
370 "supports_thinking": true,
371 "supports_images": true
372 }
373 ]
374 }
375 }
376}
377```
378
379If you specify a context length that is too large for your hardware, Ollama will log an error.
380You can watch these logs by running: `tail -f ~/.ollama/logs/ollama.log` (macOS) or `journalctl -u ollama -f` (Linux).
381Depending on the memory available on your machine, you may need to adjust the context length to a smaller value.
382
383You may also optionally specify a value for `keep_alive` for each available model.
384This can be an integer (seconds) or alternatively a string duration like "5m", "10m", "1h", "1d", etc.
385For example, `"keep_alive": "120s"` will allow the remote server to unload the model (freeing up GPU VRAM) after 120 seconds.
386
387The `supports_tools` option controls whether the model will use additional tools.
388If the model is tagged with `tools` in the Ollama catalog, this option should be supplied, and the built-in profiles `Ask` and `Write` can be used.
389If the model is not tagged with `tools` in the Ollama catalog, this option can still be supplied with the value `true`; however, be aware that only the `Minimal` built-in profile will work.
390
391The `supports_thinking` option controls whether the model will perform an explicit "thinking" (reasoning) pass before producing its final answer.
392If the model is tagged with `thinking` in the Ollama catalog, set this option and you can use it in Zed.
393
394The `supports_images` option enables the model's vision capabilities, allowing it to process images included in the conversation context.
395If the model is tagged with `vision` in the Ollama catalog, set this option and you can use it in Zed.
396
397### OpenAI {#openai}
398
399> ✅ Supports tool use
400
4011. Visit the OpenAI platform and [create an API key](https://platform.openai.com/account/api-keys)
4022. Make sure that your OpenAI account has credits
4033. Open the settings view (`agent: open configuration`) and go to the OpenAI section
4044. Enter your OpenAI API key
405
406The OpenAI API key will be saved in your keychain.
407
408Zed will also use the `OPENAI_API_KEY` environment variable if it's defined.
409
410#### Custom Models {#openai-custom-models}
411
412The Zed agent comes pre-configured to use the latest version for common models (GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, GPT-4o, GPT-4o mini).
413To use alternate models, perhaps a preview release or a dated model release, or if you wish to control the request parameters, you can do so by adding the following to your Zed `settings.json`:
414
415```json
416{
417 "language_models": {
418 "openai": {
419 "available_models": [
420 {
421 "name": "gpt-4o-2024-08-06",
422 "display_name": "GPT 4o Summer 2024",
423 "max_tokens": 128000
424 },
425 {
426 "name": "o1-mini",
427 "display_name": "o1-mini",
428 "max_tokens": 128000,
429 "max_completion_tokens": 20000
430 }
431 ],
432 "version": "1"
433 }
434 }
435}
436```
437
438You must provide the model's context window in the `max_tokens` parameter; this can be found in the [OpenAI model documentation](https://platform.openai.com/docs/models).
439
440OpenAI `o1` models should set `max_completion_tokens` as well to avoid incurring high reasoning token costs.
441Custom models will be listed in the model dropdown in the Agent Panel.
442
443### OpenAI API Compatible {#openai-api-compatible}
444
445Zed supports using OpenAI compatible APIs by specifying a custom `endpoint` and `available_models` for the OpenAI provider.
446
447You can add a custom API URL for OpenAI either via the UI or by editing your `settings.json`.
448Here are a few model examples you can plug in by using this feature:
449
450#### X.ai Grok
451
452Example configuration for using X.ai Grok with Zed:
453
454```json
455 "language_models": {
456 "openai": {
457 "api_url": "https://api.x.ai/v1",
458 "available_models": [
459 {
460 "name": "grok-beta",
461 "display_name": "X.ai Grok (Beta)",
462 "max_tokens": 131072
463 }
464 ],
465 "version": "1"
466 },
467 }
468```
469
470### OpenRouter {#openrouter}
471
472> ✅ Supports tool use
473
474OpenRouter provides access to multiple AI models through a single API. It supports tool use for compatible models.
475
4761. Visit [OpenRouter](https://openrouter.ai) and create an account
4772. Generate an API key from your [OpenRouter keys page](https://openrouter.ai/keys)
4783. Open the settings view (`agent: open configuration`) and go to the OpenRouter section
4794. Enter your OpenRouter API key
480
481The OpenRouter API key will be saved in your keychain.
482
483Zed will also use the `OPENROUTER_API_KEY` environment variable if it's defined.
484
485#### Custom Models {#openrouter-custom-models}
486
487You can add custom models to the OpenRouter provider by adding the following to your Zed `settings.json`:
488
489```json
490{
491 "language_models": {
492 "open_router": {
493 "api_url": "https://openrouter.ai/api/v1",
494 "available_models": [
495 {
496 "name": "google/gemini-2.0-flash-thinking-exp",
497 "display_name": "Gemini 2.0 Flash (Thinking)",
498 "max_tokens": 200000,
499 "max_output_tokens": 8192,
500 "supports_tools": true,
501 "supports_images": true,
502 "mode": {
503 "type": "thinking",
504 "budget_tokens": 8000
505 }
506 }
507 ]
508 }
509 }
510}
511```
512
513The available configuration options for each model are:
514
515- `name` (required): The model identifier used by OpenRouter
516- `display_name` (optional): A human-readable name shown in the UI
517- `max_tokens` (required): The model's context window size
518- `max_output_tokens` (optional): Maximum tokens the model can generate
519- `max_completion_tokens` (optional): Maximum completion tokens
520- `supports_tools` (optional): Whether the model supports tool/function calling
521- `supports_images` (optional): Whether the model supports image inputs
522- `mode` (optional): Special mode configuration for thinking models
523
524You can find available models and their specifications on the [OpenRouter models page](https://openrouter.ai/models).
525
526Custom models will be listed in the model dropdown in the Agent Panel.
527
528### Vercel v0
529
530[Vercel v0](https://vercel.com/docs/v0/api) is an expert model for generating full-stack apps, with framework-aware completions optimized for modern stacks like Next.js and Vercel.
531It supports text and image inputs and provides fast streaming responses.
532
533The v0 models are [OpenAI-compatible models](/#openai-api-compatible), but Vercel is listed as first-class provider in the panel's settings view.
534
535To start using it with Zed, ensure you have first created a [v0 API key](https://v0.dev/chat/settings/keys).
536Once you have it, paste it directly into the Vercel provider section in the panel's settings view.
537
538You should then find it as `v0-1.5-md` in the model dropdown in the Agent Panel.
539
540## Advanced Configuration {#advanced-configuration}
541
542### Custom Provider Endpoints {#custom-provider-endpoint}
543
544You can use a custom API endpoint for different providers, as long as it's compatible with the provider's API structure.
545To do so, add the following to your `settings.json`:
546
547```json
548{
549 "language_models": {
550 "some-provider": {
551 "api_url": "http://localhost:11434"
552 }
553 }
554}
555```
556
557Where `some-provider` can be any of the following values: `anthropic`, `google`, `ollama`, `openai`.
558
559### Default Model {#default-model}
560
561Zed's hosted LLM service sets `claude-sonnet-4` as the default model.
562However, you can change it either via the model dropdown in the Agent Panel's bottom-right corner or by manually editing the `default_model` object in your settings:
563
564```json
565{
566 "agent": {
567 "version": "2",
568 "default_model": {
569 "provider": "zed.dev",
570 "model": "gpt-4o"
571 }
572 }
573}
574```
575
576### Feature-specific Models {#feature-specific-models}
577
578If a feature-specific model is not set, it will fall back to using the default model, which is the one you set on the Agent Panel.
579
580You can configure the following feature-specific models:
581
582- Thread summary model: Used for generating thread summaries
583- Inline assistant model: Used for the inline assistant feature
584- Commit message model: Used for generating Git commit messages
585
586Example configuration:
587
588```json
589{
590 "agent": {
591 "version": "2",
592 "default_model": {
593 "provider": "zed.dev",
594 "model": "claude-sonnet-4"
595 },
596 "inline_assistant_model": {
597 "provider": "anthropic",
598 "model": "claude-3-5-sonnet"
599 },
600 "commit_message_model": {
601 "provider": "openai",
602 "model": "gpt-4o-mini"
603 },
604 "thread_summary_model": {
605 "provider": "google",
606 "model": "gemini-2.0-flash"
607 }
608 }
609}
610```
611
612### Alternative Models for Inline Assists {#alternative-assists}
613
614You can configure additional models that will be used to perform inline assists in parallel.
615When you do this, the inline assist UI will surface controls to cycle between the alternatives generated by each model.
616
617The models you specify here are always used in _addition_ to your [default model](#default-model).
618For example, the following configuration will generate two outputs for every assist.
619One with Claude 3.7 Sonnet, and one with GPT-4o.
620
621```json
622{
623 "agent": {
624 "default_model": {
625 "provider": "zed.dev",
626 "model": "claude-sonnet-4"
627 },
628 "inline_alternatives": [
629 {
630 "provider": "zed.dev",
631 "model": "gpt-4o"
632 }
633 ],
634 "version": "2"
635 }
636}
637```
638
639### Default View
640
641Use the `default_view` setting to set change the default view of the Agent Panel.
642You can choose between `thread` (the default) and `text_thread`:
643
644```json
645{
646 "agent": {
647 "default_view": "text_thread"
648 }
649}
650```
651
652### Edit Card
653
654Use the `expand_edit_card` setting to control whether edit cards show the full diff in the Agent Panel.
655It is set to `true` by default, but if set to false, the card's height is capped to a certain number of lines, requiring a click to be expanded.
656
657```json
658{
659 "agent": {
660 "expand_edit_card": "false"
661 }
662}
663```
664
665This setting is currently only available in Preview.
666It should be up in Stable by the next release.
667
668### Terminal Card
669
670Use the `expand_terminal_card` setting to control whether terminal cards show the command output in the Agent Panel.
671It is set to `true` by default, but if set to false, the card will be fully collapsed even while the command is running, requiring a click to be expanded.
672
673```json
674{
675 "agent": {
676 "expand_terminal_card": "false"
677 }
678}
679```
680
681This setting is currently only available in Preview.
682It should be up in Stable by the next release.