ai-chat
Access 50+ LLM models through a unified OpenAI-compatible API via AceDataCloud. Use when you need chat completions from GPT, Claude, Gemini, DeepSeek, Grok, or other models through a single endpoint.
SKILL.mdskills/ai-chat/SKILL.md
GitHubAI Chat — Unified LLM Gateway
AceDataCloud exposes the following documented chat surfaces:
| Endpoint | Use For |
|---|---|
POST /aichat2/conversations |
Recommended stateful / multimodal / agentic conversations |
POST /aichat/conversations |
Legacy conversation endpoint |
POST /openai/chat/completions (public alias /v1/chat/completions) |
OpenAI-compatible stateless chat completions |
POST /openai/responses (public alias /v1/responses) |
OpenAI-compatible responses API |
POST /v1/messages (alias /claude/messages) |
Native Claude Messages, including thinking and tool calls |
POST /v1/messages/count_tokens (alias /claude/messages/count_tokens) |
Count native Claude input tokens without generating output |
POST /v1beta/models/{model}:generateContent |
Native Gemini content generation, including audio input |
POST /v1beta/models/{model}:streamGenerateContent?alt=sse |
Native Gemini SSE streaming |
First-time setup
- Install the official Skill with
clawhub install @acedatacloud/ai-chat. Check that the ClawHub publisher is @acedatacloud. - Sign in at AceDataCloud → Applications, open General application, and check AI Chat access, balance, and current pricing. Copy its API key, or select Manage Keys → Create for a separate key. Copy the key value without
Bearer; aplatform-...management token is not a service API key. - If you enable Allowed APIs restrictions, include
/aichat2/conversationsfor the first example; other chat routes need their own access. Advanced workflows below may call additional routes. - On the OpenClaw Gateway host, put
ACEDATACLOUD_API_TOKEN=your_api_key_herein~/.openclaw/.env, then restart the Gateway and start a new session. For a direct terminal test, runexport ACEDATACLOUD_API_TOKEN="your_api_key_here"in that shell. Never put the key in a prompt or commit an.envfile. - Run the Quick Start below. If this workflow returns a task ID, query that same task until it finishes; do not submit the same billable request again just to check progress.
Illustrated key setup, first run, and troubleshooting · Token details
Quick Start
Recommended: stateful conversations
curl -X POST https://api.acedata.cloud/aichat2/conversations \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-4.1","question":"Summarize the latest release notes.","stateful":true}'
OpenAI-compatible SDK
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ACEDATACLOUD_API_TOKEN"],
base_url="https://api.acedata.cloud/openai"
)
response = client.chat.completions.create(
model="gpt-5.5",
messages=[{"role": "user", "content": "Explain quantum computing"}]
)
print(response.choices[0].message.content)
Dify: OpenAI-API-compatible provider
Set Base URL to https://api.acedata.cloud/v1, API Key to your AceDataCloud service token, model to gpt-5.5 (or another supported chat model), and model type to LLM. Select conversation type Chat and API type Chat Completions. Dify appends /chat/completions itself; do not use /openai/v1 or include the full endpoint in Base URL. Test the connection before selecting the model in a Workflow / Chatflow LLM node.
Currently Documented Model Families
The OpenAPI specs expose a broad, fast-moving model catalog. Representative current models include:
| Family | Current examples |
|---|---|
| OpenAI / reasoning | gpt-6-astra, gpt-6.1-sol, gpt-6-sol, gpt-6-luna, gpt-5.6-luna, gpt-5.6-terra, gpt-5.6-sol-fast, gpt-5.6-sol, gpt-5.5, gpt-5.5-pro, gpt-5.4, gpt-5.4-pro, gpt-5.2, gpt-5.1, gpt-5, gpt-5-mini, gpt-5-nano, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-4o, gpt-4o-mini, o1, o3, o4-mini |
| OpenAI free-tier chat-completions | gpt-5.5:free, gpt-5:free, gpt-4.1:free, gpt-4o:free, gpt-4o-mini:free, gpt-oss:free |
| Claude | claude-opus-5-5 and claude-sonnet-5-5 (Messages only), claude-fable-5-1, claude-fable-5, claude-opus-5, claude-sonnet-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-opus-4-5-20251101, claude-sonnet-4-6, claude-sonnet-4-5-20250929, claude-sonnet-4-20250514, claude-haiku-4-5-20251001, claude-3-7-sonnet-20250219 |
| Gemini | gemini-3.8-flash, gemini-3.6-flash, gemini-3.5-flash, gemini-3.1-pro, gemini-3.1-pro-preview, gemini-3.1-flash-lite-preview, gemini-3-pro-preview, gemini-2.5-flash-lite, gemini-2.0-flash-lite |
| Grok | grok-4.7, grok-4.5, grok-4, grok-4-0709, grok-3, grok-3-fast |
| DeepSeek | deepseek-v4.1-flash, deepseek-v4-pro, deepseek-v4-flash, deepseek-r1, deepseek-r1-0528, deepseek-v3, deepseek-v3-250324, deepseek-v3.2-exp |
| Kimi | kimi-k3, kimi-k2.6, kimi-k2.5, kimi-k2-thinking-turbo, kimi-k2-thinking |
| GLM | glm-5.2, glm-5.1, glm-5, glm-5-turbo, glm-4.7, glm-4.6, glm-4.5, glm-4.5v, glm-3-turbo |
When the user asks for a recommended model, read the current public GET https://platform.acedata.cloud/api/v1/models/ response and prefer suitable entries with recommended=true. This is an editorial preference, not an access grant or a new API capability; recommended=false does not retire a model. Check the selected model's supported route and current pricing before calling it, and do not silently replace a model the user explicitly selected.
To select gpt-5.6-sol-fast, send that exact public model ID on Chat Completions, Responses, Messages, or either conversation endpoint above. It is listed in the public model/pricing catalog with vision capability, but has no public model introduction. Check account eligibility and current pricing before requesting it; catalog visibility does not guarantee access. Its pricing rules use a higher tier when recorded prompt_tokens exceeds 272,000 (not at exactly 272,000). Do not silently substitute gpt-5.6-sol after an access or parameter error; protocol-specific features remain model-dependent.
gpt-6.1-sol supports low, medium, high, xhigh, and max reasoning effort; do not send none or minimal. During its first week, access requires verified ACE T1+ holdings or an access grant. Check the platform access response for the opening time.
claude-opus-5-5 and claude-sonnet-5-5 are available only through the dedicated Claude Messages API; do not send it to /openai/chat/completions or /aichat2/conversations.
/aichat2/conversations also accepts model_group values
chatgpt, claude, gemini, grok, kimi, glm, and deepseek.
Image-generating models are not chat models. Names ending in
-image(e.g.gemini-*-image,gpt-4o-image) are image-generation models; they do not work on the OpenAI-compatible chat, Claude Messages, or conversation routes. Generate images through the dedicated endpoints instead — Gemini viaPOST /v1beta/models/{model}:generateContent, or/nano-banana/images.
OpenAI-Compatible Chat
POST /openai/chat/completions
{
"model": "gpt-4.1",
"messages": [{"role": "user", "content": "Write a haiku about observability."}],
"stream": true,
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"parameters": {"type": "object", "properties": {"location": {"type": "string"}}}
}
}
]
}
Common parameters:
| Parameter | Type | Description |
|---|---|---|
model |
string | One of the documented OpenAI-compatible models |
messages |
array | Standard OpenAI chat message list |
temperature / top_p |
number | Sampling controls |
max_tokens |
integer | Output cap |
stream |
boolean | Enable SSE streaming |
tools / tool_choice |
array / string-object | Function-calling controls |
service_tier |
string | Processing tier (auto, default, flex, scale, priority) |
Native Gemini Generate Content
Use the native Gemini routes for audio analysis with the same AceDataCloud Bearer token. Confirm Gemini API access, current pricing, the selected public model, and any Allowed APIs restrictions before submitting. These routes use contents and parts, not OpenAI messages.
- Put the prompt and audio in a user content item's
parts. UseinlineDatawithmimeTypeand base64-encodeddata, orfileDatawithmimeTypeandfileUri. Text, image and video inputs, thinking configuration and custom function declarations are also accepted on this native surface; this is not a promise of support on OpenAI-compatible or conversation routes. - For
fileData.fileUri, use a file directly accessible over HTTPS without login. A signed URL must remain valid for the entire request. ReplaceHTTPS_AUDIO_URLbelow with the real file URL and set the actual audio MIME type; the example assumes WAV. - Set the client's total request timeout for the file size and workload. Non-streaming audio analysis returns only after model processing completes and may exceed 90 seconds; 90 seconds is not a server processing limit. If the client disconnects, the server may still be processing: do not automatically resubmit a potentially billable request.
- Submit the native request below. For Gemini 3.x Flash thinking models, keep
generationConfig.maxOutputTokensat least 512 so reasoning does not consume the entire output budget.
POST /v1beta/models/gemini-3.5-flash:generateContent
{
"contents": [
{
"role": "user",
"parts": [
{"text": "Summarize this audio."},
{"fileData": {"mimeType": "audio/wav", "fileUri": "HTTPS_AUDIO_URL"}}
]
}
],
"generationConfig": {"maxOutputTokens": 1024}
}
For streaming, send the same native body to POST /v1beta/models/{model}:streamGenerateContent?alt=sse and consume SSE events. Audio output, built-in tools (codeExecution, googleSearch, urlContext) and explicit context caching (cachedContent) have no uniform availability guarantee: use the selected model's actual response and surface errors rather than promising support or assuming those fields always return 400.
OpenAI Embeddings
Use POST /openai/embeddings (public alias /v1/embeddings) with the same AceDataCloud Bearer token for semantic search or RAG, not chat generation. Choose text-embedding-3-small or text-embedding-3-large; model and input are required.
POST /openai/embeddings
{
"model": "text-embedding-3-small",
"input": "Hello!"
}
text-embedding-ada-002 is retired; do not send new requests with that model. Rebuild existing indexes with the selected supported model before querying them; do not mix vectors from different models in one index or silently switch models for an existing index.
Native Claude Messages
Use POST /v1/messages (public alias /claude/messages) for native Claude calls, including Messages-only models. Authenticate with the same AceDataCloud Bearer token. Required fields are model, messages, and max_tokens; use top-level system for system instructions.
curl -X POST https://api.acedata.cloud/v1/messages \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model":"claude-sonnet-5-5",
"messages":[{"role":"user","content":"Review this implementation plan."}],
"max_tokens":8192,
"thinking":{"type":"adaptive"},
"output_config":{"effort":"high"}
}'
- Send
thinking,output_config, effort, sampling parameters, and extension fields unchanged. The platform does not enforce a frozen per-model enum or rewrite thinking modes; the selected model decides which values and combinations it accepts and its parameter errors are returned to the caller. Pass-through is not a promise of feature support across models or protocols. - Common
thinking.typevalues areadaptive,enabled, anddisabled; newer modes such asbetween_tools, fixedbudget_tokens, and whether thinking can be disabled depend on the model. Common effort values includelow,medium,high,xhigh, andmax, but are not a closed enum. thinking.display="summarized"returns a readable summary, not raw reasoning.omittedhides the thinking text while retaining its opaquesignature. Betaupdatesrequests short progress updates between tool calls with hidden reasoning; sendanthropic-beta: thinking-display-updates-2026-08-18andthinking.display="updates". The value and beta header are forwarded, not rewritten tosummarized; actual support and output depend on the selected model.- Thinking shares the
max_tokensbudget with final text. Display settings do not disable thinking or reduce its token billing. Increase the budget or lower supported effort if the final answer is empty or truncated. - In multi-turn/tool-use conversations, return complete assistant thinking blocks and signatures unchanged. Never invent or edit a signature. Cross-protocol handling of
redacted_thinkingdepends on the model service; surface errors instead of dropping blocks or silently changing the request.
To estimate input size, send the native input to POST /v1/messages/count_tokens (alias /claude/messages/count_tokens) with the same model, messages, and applicable system/tools/thinking fields. Read input_tokens; this endpoint generates no model output and consumes no quota. Its thinking configuration is extensible too; do not substitute a locally hard-coded model validator.
Stateful / Agentic Conversations
POST /aichat2/conversations generalizes the legacy conversation API with
multimodal user content, CRUD-style actions, and server-side conversation state.
POST /aichat2/conversations
{
"action": "chat",
"model": "claude-sonnet-4-6",
"message": [
{"type": "text", "text": "Describe this image."},
{"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
],
"stateful": true,
"allowed_skills": ["google-search"],
"allowed_mcp_servers": ["mcp-google-search"]
}
Useful parameters:
| Parameter | Type | Description |
|---|---|---|
action |
string | chat, retrieve, retrieve_batch, update, delete |
model |
string | Model name |
question |
string | Simple text prompt |
message |
string or array | Multimodal content using text, image_url, or file_url items |
stateful |
boolean | Keep conversation history server-side |
references |
array | Extra context documents |
preset |
string | Preset/system prompt |
max_turns |
integer | Agent iterations per request: 1–500, default 500; not retained history |
allowed_skills / allowed_mcp_servers |
array | Restrict tool-use scope |
unattended_policy |
object | Tool-use permission policy |
tool_results |
array | Return results for previously requested tool calls |
model_group |
string | Family selector (chatgpt, claude, gemini, grok, kimi, glm, deepseek) |
offset / limit |
integer | Pagination for retrieval actions |
callback_url / async |
string / boolean | Async execution |
Set max_turns deliberately for the expected tool chain. Each iteration is a model call, not a history-retention setting; max_turns: 1 requests a single answer without tool calls. Omitting it allows up to 500 iterations, not a guarantee that all will run.
Scheduled Agent Tasks
Use POST /aichat2/scheduled-tasks on https://api.acedata.cloud with the same service Bearer token and aichat API access. All operations use POST with an action; this is not a platform-management-token endpoint.
- Confirm the prompt, model, accounts, permitted tools, schedule, IANA timezone and spending scope before creating or enabling a task. Runs are billable and unattended: finish third-party authorization interactively first and remove ambiguities that would require a follow-up question. Use the unattended confirmation guard for supported write helpers; scheduling is not blanket permission to publish or send.
- Choose
schedule.type:cronrequires a five-fieldcronexpression andtz;intervalrequiresinterval_secondsandtz;oncerequires a Unix-secondsatandtz. Use an IANA zone such asUTC, notUTC+8. The saved timezone governs Cron wall-clock time even if the device timezone changes. - Put the conversation prompt/model in
template. Optionaltemplate.max_turnsis 1–500, default 500, and caps iterations per run, not schedule frequency. Each model call is billed by actual usage; a run can end earlier due to timeout, authorization or other execution conditions. A run lasts at most 15 minutes. Set an explicit Unix-secondsends_atwhen needed; otherwise tasks stop three months after creation. - After creation, retain the returned task
id. List withaction="retrieve_batch"; inspect executions withaction="retrieve_runs"and thatid, oraction="retrieve_runs_batch"for all tasks (optionalstatus,offset,limit). Read each run'sstatus,error_codeandconversation_id; retrieve the conversation through/aichat2/conversationsfor the full result. Taskstate="enabled"(shown as “running” in the list) is not evidence of a successful run. - Consecutive AI execution failures do not auto-pause the task: the next scheduled run still attempts execution. Auto-pause occurs after five consecutive handoff failures to the execution service, not five failed AI runs. Insufficient balance fails a run; a request for user input/consent fails with
awaiting_user_input. Diagnose the run history, fix balance/authorization/prompt issues, and explicitly pause recurring failures to prevent further attempts. - Pause with
action="update", the taskidandstate="disabled"; resume withstate="enabled"only after confirmation. Delete withaction="delete"andidonly after confirming permanent removal.
Creation payload (preview locally and obtain confirmation before sending):
POST /aichat2/scheduled-tasks
{
"action": "create",
"name": "Daily AI news summary",
"schedule": {"type": "cron", "cron": "0 9 * * *", "tz": "UTC"},
"template": {
"model": "gpt-4o-mini",
"question": "Today is {{date}}. Search and summarize the three most important AI news items. Do not publish or send messages.",
"max_turns": 5
}
}
POST /aichat2/scheduled-tasks
{"action": "retrieve_runs", "id": "TASK_ID"}
POST /aichat2/scheduled-tasks
{"action": "update", "id": "TASK_ID", "state": "disabled"}
Gotchas
- OpenAI-compatible routes under
/openai/*retain public aliases/v1/chat/completions,/v1/responses, and/v1/embeddings. For clients that append/chat/completions, use Base URLhttps://api.acedata.cloud/v1(not/openai/v1); the SDK example above keeps the existing/openaibase. POST /aichat2/conversationsis the recommended stateful endpoint;POST /aichat/conversationsremains for legacy clients.messageon/aichat2/conversationscan be multimodal (text,image_url,file_url); plainquestionstill works for simple text prompts.actionon/aichat2/conversationsis not chat-only — it also supportsretrieve,retrieve_batch,update, anddelete.- Free-tier model variants such as
gpt-5.5:freeare documented on/openai/chat/completions.