# Claude Code (/docs/development/developer-tools/claude-code) `Claude Code` connects to BullSequana AI through the Anthropic Messages API endpoint on the `CoreAI API`. Unlike other developer tools, Claude Code uses the Anthropic wire format instead of the OpenAI-compatible path. The backend translates requests and serves them with the models installed on the platform. No Anthropic account or subscription is required. Claude Code keeps running its own tools on your local machine — the backend only handles the model turns. What to use [#what-to-use] Use: * API type: Anthropic Messages API * base URL: `https://llm-backend./anthropic` * token: `sk-bsq-...` API key (sent as `X-Api-Key`) 1\. Install Claude Code [#1-install-claude-code] ```bash npm install -g @anthropic-ai/claude-code claude --version ``` Do not log in to Anthropic when prompted. The environment variables in step 4 replace Anthropic authentication entirely. 2\. Get a platform API key [#2-get-a-platform-api-key] Create one at **Settings → API Keys** in the CoreAI Portal. The full secret is shown only once. It looks like `sk-bsq-v1-…`. See [CoreAI Portal Guide — API Keys](/docs/guides/coreai-portal#api-keys). 3\. Find available models [#3-find-available-models] Query the Anthropic-compatible models endpoint to see which models are available to your account: ```bash export ANTHROPIC_BASE_URL=https://llm-backend./anthropic export ANTHROPIC_API_KEY=sk-bsq-v1-... curl -s -H "x-api-key: $ANTHROPIC_API_KEY" "$ANTHROPIC_BASE_URL/v1/models" \ | jq -r '.data[] | [.id, .display_name] | @tsv' ``` The list is scoped to your account: agent configurations you can access appear first, followed by installed chat models. Pick two ids from the list: * a **main model** for your prompts (e.g. `claude-model-gpt-5.4`) * a **small/fast model** for background chores (e.g. `claude-model-qwen-3.5-9B`) 4\. Set all seven environment variables [#4-set-all-seven-environment-variables] Claude Code has internal model slots for Sonnet, Opus, and Haiku. Any slot left unset defaults to an Anthropic model id that does not exist on this platform and returns a 404. Set all seven variables. Save as `source_env_vars.sh`: ```bash #!/bin/sh export ANTHROPIC_BASE_URL=https://llm-backend./anthropic export ANTHROPIC_API_KEY=sk-bsq-v1-... # The model that answers you. export ANTHROPIC_MODEL=claude-model- # Claude Code fills these on its own. Unset slots default to Anthropic ids that 404 here. export ANTHROPIC_DEFAULT_SONNET_MODEL=$ANTHROPIC_MODEL export ANTHROPIC_DEFAULT_OPUS_MODEL=$ANTHROPIC_MODEL # Background traffic (session titles, classifications). Point at something cheap. export ANTHROPIC_DEFAULT_HAIKU_MODEL=claude-model- export ANTHROPIC_SMALL_FAST_MODEL=$ANTHROPIC_DEFAULT_HAIKU_MODEL ``` ```bash source ./source_env_vars.sh ``` 5\. Check for settings file overrides [#5-check-for-settings-file-overrides] Claude Code merges environment variables from its settings files **over** your shell exports. If a settings file points elsewhere, your shell configuration is silently ignored: ```bash jq '.env' ~/.claude/settings.json ``` If that prints `ANTHROPIC_*` keys, either remove them or move your entire configuration there instead (see [Make the configuration permanent](#make-the-configuration-permanent)). 6\. Run Claude Code [#6-run-claude-code] ```bash claude ``` Verify the platform is serving turns: ``` > what model are you? ``` Inside the session, `/model` should list your configured ids, not Anthropic's built-in model names. Use a custom GPT (agent configuration) [#use-a-custom-gpt-agent-configuration] A custom GPT on the platform can be used as a model in Claude Code. It supplies both the model and prepends its system prompt to every turn. The agent configuration id is a uuid that changes if the agent is recreated. Resolve it by name at startup rather than hardcoding it: ```bash AGENT_NAME="Simplified technical english GPT" AGENT_ID=$(curl -sS -H "x-api-key: $ANTHROPIC_API_KEY" \ "$ANTHROPIC_BASE_URL/v1/models" \ | jq -r --arg n "$AGENT_NAME" '.data[] | select(.display_name == $n) | .id') export ANTHROPIC_MODEL="$AGENT_ID" export ANTHROPIC_DEFAULT_SONNET_MODEL="$AGENT_ID" export ANTHROPIC_DEFAULT_OPUS_MODEL="$AGENT_ID" # Background traffic should NOT use the agent — it has no use for the system prompt. export ANTHROPIC_DEFAULT_HAIKU_MODEL=claude-model- export ANTHROPIC_SMALL_FAST_MODEL=$ANTHROPIC_DEFAULT_HAIKU_MODEL ``` To give the agent a readable name in the `/model` picker: ```bash export ANTHROPIC_CUSTOM_MODEL_OPTION="$AGENT_ID" export ANTHROPIC_CUSTOM_MODEL_OPTION_NAME="$AGENT_NAME" export ANTHROPIC_CUSTOM_MODEL_OPTION_DESCRIPTION="Agent configuration on the platform" ``` Make the configuration permanent [#make-the-configuration-permanent] Shell exports die with the shell. For a permanent setup, put the configuration in the Claude Code settings file: ```json { "env": { "ANTHROPIC_BASE_URL": "https://llm-backend./anthropic", "ANTHROPIC_API_KEY": "sk-bsq-v1-...", "ANTHROPIC_MODEL": "claude-model-", "ANTHROPIC_DEFAULT_SONNET_MODEL": "claude-model-", "ANTHROPIC_DEFAULT_OPUS_MODEL": "claude-model-", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "claude-model-", "ANTHROPIC_SMALL_FAST_MODEL": "claude-model-" } } ``` Save as `~/.claude/settings.json` for global configuration or `.claude/settings.json` inside a repository for per-project overrides. Variable interpolation (`$VAR`) does not work in settings files — spell out every id. Restart `claude` after editing. Call the API directly (SDK or curl) [#call-the-api-directly-sdk-or-curl] The Anthropic-compatible endpoint also works with the official Anthropic SDK and curl, independent of Claude Code: ```python from anthropic import Anthropic client = Anthropic( base_url="https://llm-backend./anthropic", api_key="sk-bsq-v1-...", ) message = client.messages.create( model="claude-model-", max_tokens=4096, messages=[{"role": "user", "content": "Hello"}], ) ``` ```bash curl -s "$ANTHROPIC_BASE_URL/v1/messages" \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "content-type: application/json" \ -d '{"model":"claude-model-","max_tokens":1024, "messages":[{"role":"user","content":"Hello"}]}' ``` Direct SDK and curl callers may also use bare model names (e.g. `gpt-5.4`) without the `claude-model-` prefix. Claude Code requires the prefix. Model id format [#model-id-format] Claude Code silently discards any model id that does not begin with `claude` or `anthropic`. The prefixes are required. | Id format | Resolves to | Effect | | --------------------- | ------------------------------------------- | ------------------------------------------------- | | `claude-agent-` | An agent configuration (permission-checked) | Supplies the model and prepends its system prompt | | `claude-model-` | An installed model on the platform | No system prompt injected | | Bare `` | Same installed model (SDK and curl only) | No system prompt injected | | Anything else | 404 | Including all of Anthropic's own model ids | Reasoning models [#reasoning-models] Reasoning models work through the Anthropic-compatible endpoint. Behavior depends on the model: * Models that stream reasoning (e.g. `qwen3-235b-a22b-thinking-2507`) produce `thinking` blocks that Claude Code renders. * Models that reason internally without streaming (e.g. GPT-5 family) produce no thinking blocks but still bill the reasoning tokens. * Reasoning shares the `max_tokens` budget. Set a generous value for direct SDK callers. * Turns are slower: expect 20+ seconds for short answers on reasoning models, compared to \~2 seconds on non-reasoning models. Endpoints [#endpoints] All endpoints are mounted under `/anthropic` and require `X-Api-Key` or `Authorization: Bearer ` authentication. | Route | Purpose | | ------------------------------------------ | --------------------------------------------------------------- | | `POST /anthropic/v1/messages` | Single turn, streaming or non-streaming | | `POST /anthropic/v1/messages/count_tokens` | Input token estimate without calling a model | | `GET /anthropic/v1/models` | List available models and agent configurations for your account | Troubleshooting [#troubleshooting] | Symptom | Cause and fix | | -------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- | | "There's an issue with the selected model" | A model slot is unset, misspelled, or still pointing to an Anthropic built-in id. Re-run step 3 and set all seven variables. | | Same error on turn one of a fresh install | Claude Code sent its default Anthropic model id before you opened `/model`. The Sonnet or Opus slot is unset. | | `connection refused` or 401 from an unrecognized gateway | `~/.claude/settings.json` has an `env` block overriding your shell. Run `jq '.env' ~/.claude/settings.json`. | | `/model` lists Anthropic names instead of your ids | Unset slots are filled with built-in Anthropic entries. Set all seven variables. | | Agent configuration uuid stopped working | The agent was recreated and received a new uuid. Resolve by name at startup. | | Turns are slow (20+ seconds for short answers) | A reasoning model is selected. This is expected behavior. | Related pages [#related-pages] * [Developer Tools](/docs/development/developer-tools) * [Use local models via API](/docs/development/use-local-models-via-api) * [CoreAI API](/docs/coreai/components/coreai-api) * [API Reference](/docs/api-reference)