Other Model Provider Setup Guides

This page brings together configuration instructions for eight additional AI platforms. Follow the section for the provider you want to use.

1. DeepSeek

Get an API Key

Create an API Key in the DeepSeek Platform.

Configure the Provider

1. Open Chatbox and click Settings in the bottom-left corner.
2. Select Model Provider in the left sidebar, then find DeepSeek.
3. Paste your DeepSeek API Key into the API Key field.
4. Click Check. When the connection test succeeds, the provider is ready.

Start Using DeepSeek

Select deepseek-v4-pro or deepseek-v4-flash from the model selector. DeepSeek V4 supports a context window of up to 1 million tokens. You can also choose a reasoning level from On, Off, Low, Medium, and High in the input box.

Going Further

After configuration, the provider can also be used in Work Mode, including AI agents, code execution, MCP servers, skills, knowledge bases, and global memory.

2. GLM Coding Plan

Get an API Key

Register or sign in on the Z.AI Open Platform, then create a key in the appropriate plan area:

• Individual plan users: Individual Coding Plan
• Team plan members: Team Coding Plan

Individual and Team keys are not interchangeable. Keep your key private and do not hard-code it in public code.

Configure the Provider

1. Open Chatbox and click Settings in the bottom-left corner.

2. Select Model Provider, click Add, and search for GLM.

3. Select GLM Coding Plan and paste the matching API Key into the API Key field. The API Host is pre-filled, so no change is needed.

4. Click Check and wait for the test to succeed.

Click ESC to leave Settings, then select an available GLM model from the model list to start chatting.

Troubleshooting

Check for extra spaces or line breaks in the key, confirm that the key is valid for your plan, and verify network, firewall, proxy, and Chatbox version settings. For context or model errors, enable Improve Network Compatibility, confirm model availability, and review parameters such as temperature and Maximum Output Tokens.

3. Kimi For Coding

Membership and Model Access

Check your Kimi Code membership before configuring a model. Model access and context limits are controlled by your current plan.

k3-256k delivers the same results within a 256K context and uses about half the quota of k3 with 1M context. It is suitable for everyday Q&A, code completion, routine development, and small file changes. Video input is not supported.

Prepare Your Credentials

1. Create and save an API Key in the Kimi Code Console.
2. Confirm that your membership allows the model you plan to use.

Add the Kimi Provider

1. Open Settings and select Model Provider.
2. Click Add at the bottom of the provider list.
3. Select Add Custom Provider.
4. Enter a name such as Kimi, and select OpenAI API Compatible as the API mode.
5. Return to the provider settings and enter:

Add a Model

Scroll to Models, click New, and enter the Model ID, Display Name, and Context Window. Test the model and save it.

Enable the Kimi For Coding Model

Select the configured model from the model list and send a message to start using it.

Troubleshooting

• For a failed model test, check the API Key, https://api.kimi.com/coding/v1, network access, and your membership permissions.
• For context or model errors, enable Improve Network Compatibility, verify the model and request parameters, or switch from k3 to k3-256k if you do not have 1M access.

4. LongCat

Prepare Your Account

Create an API Key on the LongCat Platform, then check the Usage page to make sure your account has enough token quota.

Configure LongCat

1. Open Settings → Model Provider → Add.

2. Search for and select LongCat.

3. Paste your LongCat API Key into API Key. The API Host is pre-filled and normally does not need changes.

4. Click Check next to the API Key.

5. Select LongCat-2.0 from the model list to start chatting.

5. MiniMax

Add the Provider

1. Open Settings and select Model Provider.

2. Click Add, search for MiniMax, and select MiniMax CN or MiniMax Global according to your account and region.

Enter the Subscription Key

Obtain a Subscription Key from the MiniMax Token Plan. The API Host is pre-filled by the provider. Paste the key into API Key, then click Check.

Select a Model

Select MiniMax-M3 from the provider's model list. If the model list does not load, check the key and account status, then refresh the provider or add the model manually using the current model ID shown by MiniMax.

6. Tencent Hunyuan

Get an API Key

Create a Tencent Hunyuan API Key in the Tencent Cloud API Key Management Console. Keep the key private and do not upload or share it publicly.

Configure the Provider

1. Open Settings → Model Provider → Add.
2. Enter a provider name and select OpenAI API Compatible as the API mode.
3. Set the API Host to https://api.hunyuan.cloud.tencent.com/v1/.
4. Paste your Tencent Hunyuan API Key into API Key and leave the other fields blank.
5. Save the provider.

Select Hy3 from the model list to start a new chat.

7. Xiaomi MiMo

Obtain Credentials

MiMo supports both pay-as-you-go API access and Token Plan subscriptions.

Configure Xiaomi MiMo

1. Open Settings → Model Provider → Add.

2. Search for and select Xiaomi MiMo.

3. For pay-as-you-go access, paste the API Key and leave the API Host unchanged.

4. For Token Plan, replace both the API Key and API Host with the dedicated values shown in the Token Plan console.

5. Click Check next to the API Key. After the test succeeds, select a model from the model list and start chatting or use Work Mode.

8. ZenMux

Add the Provider

1. Open Settings → Model Provider → Add.
2. Select Add Custom Provider.
3. Use ZenMux as the name and select OpenAI API Compatible.

4. Enter the following settings:

Create a key in the ZenMux Console. The API Host must keep its trailing slash.

Add a Model

Scroll to Models, click New, and enter a model supported by ZenMux. For example:

Click Check, save the configuration, and select the new model from the model selector.

Start a Conversation

Select a configured ZenMux model in the model selector to start a conversation. See the ZenMux model list for current model IDs, prices, capabilities, and protocol support.

Troubleshooting

• Confirm the key starts with sk-ai-v1-, is active, and belongs to an account with sufficient balance.
• Confirm the API Host is exactly https://zenmux.ai/api/v1/ and that the selected model supports OpenAI Chat Completions.
• If calls fail, enable Improve Network Compatibility, reduce Maximum Output Tokens, or try another model.