Coding Agents

The LithosAI API supports many coding agents, including Codex, Claude Code, and OpenCode. OpenCode connects directly. Codex and Claude Code each require a different protocol, so a local translation proxy is needed.

Agent	Expects	Connects
Codex	Responses API	Through a proxy
Claude Code	Anthropic Messages API	Through a proxy
OpenCode	Chat Completions	Directly

Export your key once, in whichever shell you use to start these tools.

export LITHOSAI_API_KEY="your-key"

LithosAI validates tool schemas strictly. An agent that loads an MCP server whose tool parameters are not a JSON Schema object is rejected with invalid 'parameters' schema. Disable that server or correct its schema.

Codex

Codex no longer speaks Chat Completions. wire_api = "chat" is rejected at startup, and responses is the only accepted value, so Codex reaches LithosAI through a proxy that accepts Responses API requests.

Install LiteLLM

LiteLLM bridges the Responses API to Chat Completions.

pip install 'litellm[proxy]'

Install a current release. LiteLLM 1.82.7 and 1.82.8 were briefly replaced on PyPI in March 2026 by a credential stealer.

Configure the proxy

Give the model the openai/ prefix and set use_chat_completions_api, which bridges incoming /v1/responses requests to LithosAI’s /v1/chat/completions.

codex.litellm.yaml

model_list:
  - model_name: kimi-k3
    litellm_params:
      model: openai/moonshotai/Kimi-K3
      api_base: https://api.lithosai.cloud/v1
      api_key: os.environ/LITHOSAI_API_KEY
      use_chat_completions_api: true

litellm_settings:
  drop_params: true

general_settings:
  master_key: sk-codex-proxy

drop_params discards parameters a model does not accept rather than failing the request. master_key is the token Codex sends to the proxy, not your LithosAI key.

Start the proxy

litellm --config codex.litellm.yaml --port 4000

Leave it running, and confirm it is up. The proxy holds your LithosAI key, so keep it bound to 127.0.0.1 and do not expose it to a network.

curl http://127.0.0.1:4000/health/liveliness

Point Codex at it

~/.codex/config.toml

model = "kimi-k3"
model_provider = "lithosai"

[model_providers.lithosai]
name = "LithosAI"
base_url = "http://127.0.0.1:4000/v1"
env_key = "LITELLM_API_KEY"
wire_api = "responses"
requires_openai_auth = false

env_key names the variable holding the proxy’s master_key, so export that too.

export LITELLM_API_KEY="sk-codex-proxy"
codex

Troubleshooting

Symptom	Cause
`wire_api = "chat"` is no longer supported	`base_url` points at LithosAI directly. Point it at the proxy.
`404` on `/v1/responses`	The model entry uses `hosted_vllm/`. Codex needs `openai/` with `use_chat_completions_api`.
`400` with `No connected db.`	`LITELLM_API_KEY` does not match the proxy’s `master_key`. LiteLLM reports the lookup failure, not an auth error.

Claude Code

Claude Code speaks the Anthropic Messages API, so its proxy needs a different configuration from the one Codex uses. Run it on a second port to use both agents at once.

Install LiteLLM

LiteLLM bridges the Anthropic Messages API to Chat Completions.

pip install 'litellm[proxy]'

Install a current release. LiteLLM 1.82.7 and 1.82.8 were briefly replaced on PyPI in March 2026 by a credential stealer.

Configure the proxy

Give each model the hosted_vllm/ prefix. It routes /v1/messages straight to Chat Completions and maps replies, including reasoning, back into Anthropic content blocks.

claude-code.litellm.yaml

model_list:
  - model_name: kimi-k3
    litellm_params:
      model: hosted_vllm/moonshotai/Kimi-K3
      api_base: https://api.lithosai.cloud/v1
      api_key: os.environ/LITHOSAI_API_KEY
  - model_name: kimi-k3-fast
    litellm_params:
      model: hosted_vllm/moonshotai/Kimi-K3-fast
      api_base: https://api.lithosai.cloud/v1
      api_key: os.environ/LITHOSAI_API_KEY

litellm_settings:
  drop_params: true

general_settings:
  master_key: sk-claude-proxy

Do not reuse the Codex configuration here. An openai/ entry with use_chat_completions_api answers /v1/messages with 200 OK and empty content, so Claude Code appears to hang rather than reporting an error.

Start the proxy

litellm --config claude-code.litellm.yaml --port 4001

Leave it running, and confirm it is up. The proxy holds your LithosAI key, so keep it bound to 127.0.0.1 and do not expose it to a network.

curl http://127.0.0.1:4001/health/liveliness

Point Claude Code at it

export ANTHROPIC_BASE_URL="http://127.0.0.1:4001"
export ANTHROPIC_AUTH_TOKEN="sk-claude-proxy"
export ANTHROPIC_MODEL="kimi-k3"
export ANTHROPIC_SMALL_FAST_MODEL="kimi-k3-fast"
claude

ANTHROPIC_SMALL_FAST_MODEL handles background work such as session titles. Without it, those requests fail against a model the proxy does not serve.

Setting ANTHROPIC_AUTH_TOKEN overrides a Claude.ai login for that shell. Export these in a dedicated shell or profile to keep an existing subscription usable elsewhere.

Claude Code does not recognize LithosAI model names, so it assumes a 200k-token context window and compacts early. Set the real window to avoid that.

export CLAUDE_CODE_MAX_CONTEXT_TOKENS=262144

Check the Models console page for each model’s context window.

Troubleshooting

Symptom	Cause
Empty replies, or the session appears to hang	The model entry uses `openai/` with `use_chat_completions_api`. Claude Code needs `hosted_vllm/`.
Background requests fail while chat works	`ANTHROPIC_SMALL_FAST_MODEL` is unset or names a model the proxy does not serve.
`400` with `No connected db.`	`ANTHROPIC_AUTH_TOKEN` does not match the proxy’s `master_key`. LiteLLM reports the lookup failure, not an auth error.

OpenCode

OpenCode reaches LithosAI directly, with no proxy and nothing to install. Declare the provider in opencode.json, either in a project or at ~/.config/opencode/opencode.json.

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "lithosai": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "LithosAI",
      "options": {
        "baseURL": "https://api.lithosai.cloud/v1",
        "apiKey": "{env:LITHOSAI_API_KEY}"
      },
      "models": {
        "moonshotai/Kimi-K3": { "name": "Kimi K3" },
        "moonshotai/Kimi-K3-fast": { "name": "Kimi K3 fast" }
      }
    }
  },
  "model": "lithosai/moonshotai/Kimi-K3"
}

@ai-sdk/openai-compatible is the package for Chat Completions providers, and OpenCode bundles it. Start OpenCode as usual.

opencode

Getting Started

API Reference

Account

Codex

Troubleshooting

Claude Code

Troubleshooting

OpenCode

​Codex

​Troubleshooting

​Claude Code

​Troubleshooting

​OpenCode

Codex

Troubleshooting

Claude Code

Troubleshooting

OpenCode