Use cheaper inference in the apps you already know

Supported: streamed responses, function calls, local Codex tools such as apply_patch, and usage accounting. This configuration applies to new local tasks in the Codex CLI, desktop app, and IDE extension. It does not change Codex cloud chats.

npm install --global @openai/codex
codex --version

export CHEAPER_INFERENCE_API_KEY="ir_live_YOUR_API_KEY"

$env:CHEAPER_INFERENCE_API_KEY = "ir_live_YOUR_API_KEY"

model = "gpt-5.4"
model_provider = "cheaper-inference"

[model_providers.cheaper-inference]
name = "Cheaper Inference"
base_url = "https://api.cheaperinference.com/v1"
env_key = "CHEAPER_INFERENCE_API_KEY"
wire_api = "responses"

read -s "CHEAPER_KEY?Paste your Cheaper Inference API key: "
echo
security add-generic-password -U -a codex -s cheaper-inference-codex -w "$CHEAPER_KEY"
unset CHEAPER_KEY

[model_providers.cheaper-inference.auth]
command = "/usr/bin/security"
args = ["find-generic-password", "-a", "codex", "-s", "cheaper-inference-codex", "-w"]

codex exec --model gpt-5.4 --sandbox read-only "Run pwd without changing files, then tell me the directory."

1. Set CHEAPER_INFERENCE_API_KEY in the environment that starts OpenClaw.
2. Add the provider and model to your OpenClaw configuration.
3. Select the model as cheaper-inference/gpt-5.4.

{
  "env": {
    "CHEAPER_INFERENCE_API_KEY": "ir_live_YOUR_API_KEY"
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "cheaper-inference/gpt-5.4"
      }
    }
  },
  "models": {
    "providers": {
      "cheaper-inference": {
        "baseUrl": "https://api.cheaperinference.com/v1",
        "apiKey": "${CHEAPER_INFERENCE_API_KEY}",
        "api": "openai-completions",
        "models": [
          {
            "id": "gpt-5.4",
            "name": "GPT-5.4 via Cheaper Inference"
          }
        ]
      }
    }
  }
}

Important: keep api set to openai-completions. Add another object to models for each Cheaper Inference model ID you want OpenClaw to expose.

Capability metadata: OpenClaw supplies generic context, output-token, reasoning, and input-modality defaults when optional model fields are omitted. Add explicit values only after verifying them for the exact model you selected.

1. Run hermes model.
2. Choose Custom endpoint (self-hosted / VLLM / etc.).
3. Enter the base URL above, your API key, and an exact model ID such as gpt-5.4.
4. When Hermes asks for the API mode, choose Chat Completions.

For a manual setup, put CHEAPER_INFERENCE_API_KEY=ir_live_YOUR_API_KEY in ~/.hermes/.env, then edit ~/.hermes/config.yaml:

custom_providers:
  - name: cheaper-inference
    base_url: https://api.cheaperinference.com/v1
    key_env: CHEAPER_INFERENCE_API_KEY
    api_mode: chat_completions

model:
  default: gpt-5.4
  provider: custom:cheaper-inference

Recommended: use hermes model so Hermes writes the configuration in its current format. Protect ~/.hermes/.env because it contains your key.

1. Open /connect, choose Other, enter cheaper-inference, and add your API key.
2. Add the provider below to opencode.json, then use /models to select it.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "cheaper-inference": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Cheaper Inference",
      "options": {
        "baseURL": "https://api.cheaperinference.com/v1"
      },
      "models": {
        "gpt-5.4": {
          "name": "GPT-5.4"
        }
      }
    }
  }
}

Important: use @ai-sdk/openai-compatible so OpenCode sends Chat Completions requests. Add more entries under models using exact IDs from the live catalog.

The OpenCode schema is intentional: OpenWork uses OpenCode as its model engine and reads OpenCode provider configuration for each workspace.

1. Open a workspace in OpenWork and create opencode.json in that workspace's root folder.
2. Add the provider configuration below, then reopen or reload the workspace.
3. Open Settings → AI Providers → Connect provider, choose Cheaper Inference, and paste your API key.
4. Select a Cheaper Inference model from OpenWork's model picker and start a task.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "cheaper-inference": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Cheaper Inference",
      "env": ["CHEAPER_INFERENCE_API_KEY"],
      "options": {
        "baseURL": "https://api.cheaperinference.com/v1"
      },
      "models": {
        "gpt-5.6-sol": {
          "name": "GPT-5.6 Sol"
        },
        "gpt-5.6-terra": {
          "name": "GPT-5.6 Terra"
        },
        "deepseek-v4-flash": {
          "name": "DeepSeek V4 Flash"
        }
      }
    }
  }
}

Keep the key out of the file: the env declaration tells OpenWork that this provider accepts an API key; it does not contain the secret. OpenWork stores the key locally through OpenCode after you connect the provider. Add or replace model entries using exact IDs from the live catalog.

If Cheaper Inference does not appear: completely reload the workspace engine after saving the file. If it is still missing, capture the exact error and your OpenWork version before contacting support.

1. Open Admin Settings → Connections → OpenAI.
2. Click Add Connection.
3. Enter https://api.cheaperinference.com/v1 and your API key, then save.
4. Select a discovered model. If needed, add exact IDs under Model IDs (Filter).

Feature scope: chat and model discovery work through the Cheaper Inference connection. Configure a separate provider for Open WebUI features that require embeddings, speech-to-text, or text-to-speech.

1. Open Cline settings and choose OpenAI Compatible as the API provider.
2. Set the Base URL to https://api.cheaperinference.com/v1.
3. Paste your API key and enter an exact model ID such as gpt-5.4.
4. Save, then start a small task and confirm the request appears in Cheaper Inference History.

Advanced model settings: enable image support, computer/tool use, and context or output limits only when the selected model supports them. These settings are model-specific, even when the same OpenAI-compatible connection is reused.

export OPENAI_API_BASE=https://api.cheaperinference.com/v1
export OPENAI_API_KEY=ir_live_YOUR_API_KEY

cd /path/to/your/project
aider --model openai/gpt-5.4

Windows PowerShell:

$env:OPENAI_API_BASE = "https://api.cheaperinference.com/v1"
$env:OPENAI_API_KEY = "ir_live_YOUR_API_KEY"

Set-Location C:\path\to\your\project
aider --model openai/gpt-5.4

Model naming: keep Aider's openai/ prefix, followed by the exact Cheaper Inference model ID. If Aider warns that a newer model is unknown, its official model settings can be used to describe the model's context and edit format.

Add the key to LibreChat's .env:

CHEAPER_INFERENCE_API_KEY=ir_live_YOUR_API_KEY

Add the endpoint to librechat.yaml, then restart LibreChat:

version: 1.3.13
endpoints:
  custom:
    - name: Cheaper Inference
      apiKey: '${CHEAPER_INFERENCE_API_KEY}'
      baseURL: 'https://api.cheaperinference.com/v1'
      models:
        default:
          - gpt-5.4
          - claude-opus-4.6
        fetch: true
      titleConvo: true
      titleModel: gpt-5.4
      modelDisplayLabel: Cheaper Inference

Claude model IDs: keep this as a custom OpenAI-compatible endpoint even when selecting a Claude model. Cheaper Inference translates the common request format to the serving provider.

name: Cheaper Inference
version: 0.0.1
schema: v1

models:
  - name: GPT-5.4 through Cheaper Inference
    provider: openai
    model: gpt-5.4
    apiBase: https://api.cheaperinference.com/v1
    apiKey: ir_live_YOUR_API_KEY
    useResponsesApi: false

Recommended for Continue: keep useResponsesApi: false so Continue uses the broadly compatible Chat Completions path. The Responses endpoint is currently targeted at stateless Codex workloads.