everyais
← All docs

Coding tools

Other OpenAI-compatible tools

Updated

Generate your config

Pick one or more models and press Confirm. The config below is regenerated so every model you picked is ready to use. The first model you pick becomes the default. Context, output limits, and prices come from the model catalog.

Reasoning effort

The initial value is the model's default. Choose Tool default to leave it out of the config.

Tools built on the OpenAI SDK (.env)
OPENAI_BASE_URL=https://api.everyais.com/v1
OPENAI_API_KEY=everyais_your_api_key

Model IDs

DeepSeek V4.1 Flash 1017
everyais/deepseek-v4-1-flash-1017
Zed: ~/.config/zed/settings.json
{
  "language_models": {
    "openai_compatible": {
      "everyais": {
        "api_url": "https://api.everyais.com/v1",
        "available_models": [
          {
            "name": "everyais/deepseek-v4-1-flash-1017",
            "display_name": "DeepSeek V4.1 Flash 1017",
            "max_tokens": 1048000,
            "reasoning_effort": "high",
            "capabilities": {
              "tools": true,
              "images": true,
              "parallel_tool_calls": false,
              "prompt_cache_key": false
            }
          }
        ]
      }
    }
  }
}

Merge the language_models key into your existing settings.json object (or just everyais under openai_compatible if it exists). Provide the key through EVERYAIS_API_KEY or Zed's UI, not in settings.json. Pick the model from the agent panel's model list.

Aider: .aider.conf.yml
openai-api-base: https://api.everyais.com/v1
model: openai/everyais/deepseek-v4-1-flash-1017
weak-model: openai/everyais/deepseek-v4-1-flash-1017
alias:
  - "deepseek-v4-1-flash-1017:openai/everyais/deepseek-v4-1-flash-1017"

Keep the Aider files in your home directory or the git repository root. Switch models in chat with /model and an alias.

Aider: .aider.model.metadata.json
{
  "openai/everyais/deepseek-v4-1-flash-1017": {
    "max_tokens": 1048000,
    "max_input_tokens": 1048000,
    "input_cost_per_token": 7.5e-8,
    "output_cost_per_token": 3e-7,
    "cache_read_input_token_cost": 1.5e-9,
    "cache_creation_input_token_cost": 3e-8,
    "litellm_provider": "openai",
    "mode": "chat",
    "supports_function_calling": true,
    "supports_vision": true,
    "supports_reasoning": true
  }
}

Context and output limits plus per-token prices in USD. Aider uses them to track remaining context and cost.

Aider: .aider.model.settings.yml
- name: "openai/everyais/deepseek-v4-1-flash-1017"
  accepts_settings:
    - reasoning_effort
  extra_params:
    extra_body:
      reasoning_effort: "high"

Sends the reasoning effort per model. You can also change it in chat with /reasoning-effort.

Zed and Aider key variables
export EVERYAIS_API_KEY="everyais_your_api_key"  # Zed
export OPENAI_API_KEY="everyais_your_api_key"    # Aider

Most tools that use the OpenAI format work once you set the provider to OpenAI (or OpenAI Compatible) and enter these values.

FieldValue
Base URLhttps://api.everyais.com/v1 (including /v1)
API Keyeveryais_...
ModelA model ID you picked in "Generate your config" above (e.g. everyais/gemini-3-8-flash)

Tools built on the OpenAI SDK

The official OpenAI SDKs (Python and Node.js) read the OPENAI_BASE_URL and OPENAI_API_KEY environment variables. A tool that uses the SDK as-is sends requests to everyais once you set the two .env lines generated above.

Zed

Merge the generated language_models block into the existing object in ~/.config/zed/settings.json. If openai_compatible already exists, add only everyais under it.

Each model gets its context size, maximum output tokens, reasoning effort (reasoning_effort), and supported features (capabilities) from the catalog. Zed requires a context value, so models with no context in the catalog are left out.

Provide the key through the EVERYAIS_API_KEY environment variable or Zed's settings screen, not in settings.json. Pick a registered model from the agent panel's model list.

Aider

Aider sends a model to an OpenAI-compatible API when its name starts with openai/, so put openai/ in front of the everyais model ID, as in openai/everyais/gemini-3-8-flash. Put the generated files in your home folder or the repository root, and pass the key in the OPENAI_API_KEY environment variable.

FileContents
.aider.conf.ymlThe main model, the weak-model for light work such as commit messages, and model aliases
.aider.model.metadata.jsonContext and output limits, per-token prices, and tool, image, and reasoning support
.aider.model.settings.ymlThe reasoning effort sent for each model. It appears only when you pick a model that accepts reasoning effort

Per-token prices in the metadata are the per-1M price divided by 1,000,000 (for example, $2 → 0.000002). The 1st model becomes the main model and the 2nd becomes the weak-model. In chat, switch models with /model followed by an alias, and change reasoning effort with /reasoning-effort.

Model names

Short names without the everyais/ prefix, such as claude-sonnet-5-5, also work, but use full IDs in config files. The rules are in compatibility features.

Contact support