AI Chat — Unified LLM Gateway
AceDataCloud exposes two documented chat surfaces:
| Endpoint |
Use For |
POST /aichat2/conversations |
Recommended stateful / multimodal / agentic conversations |
POST /aichat/conversations |
Legacy conversation endpoint |
POST /openai/chat/completions |
OpenAI-compatible stateless chat completions |
POST /openai/responses |
OpenAI-compatible responses API |
Setup: See authentication for token setup.
Quick Start
Recommended: stateful conversations
curl -X POST https://api.acedata.cloud/aichat2/conversations \
-H "Authorization: ******ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-4.1","question":"Summarize the latest release notes.","stateful":true}'
OpenAI-compatible SDK
from openai import OpenAI
client = OpenAI(
api_key="your-token-here",
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)
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-5.6-luna, gpt-5.6-terra, 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-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-3.6-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-4.5, grok-4, grok-4-0709, grok-3, grok-3-fast |
| DeepSeek |
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 |
/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 and do
not work on any chat surface listed above. Generate images through the
dedicated endpoints instead — Gemini via
POST /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) |
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 |
Trim retained turn 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 |
Gotchas
- The documented OpenAI-compatible routes live under
/openai/*, not /v1/*.
POST /aichat2/conversations is the recommended stateful endpoint; POST /aichat/conversations remains for legacy clients.message on /aichat2/conversations can be multimodal (text, image_url, file_url); plain question still works for simple text prompts.action on /aichat2/conversations is not chat-only — it also supports retrieve, retrieve_batch, update, and delete.- Free-tier model variants such as
gpt-5.5:free are documented on /openai/chat/completions.
1---
2name: ai-chat
3description: Access 50+ LLM models through AceDataCloud's unified chat APIs. Use when you need OpenAI-compatible chat/responses calls or the newer `/aichat2/conversations` API across GPT, Claude, Gemini, Grok, Kimi, GLM, and DeepSeek models. Supports streaming, multimodal input, and tool calling.
4license: Apache-2.0
5metadata:
6 author: acedatacloud
7 version: "1.0"
8compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Works with OpenAI-compatible SDKs against the `/openai/*` routes.
9---
10
11# AI Chat — Unified LLM Gateway
12
13AceDataCloud exposes two documented chat surfaces:
14
15| Endpoint | Use For |
16|----------|---------|
17| `POST /aichat2/conversations` | Recommended stateful / multimodal / agentic conversations |
18| `POST /aichat/conversations` | Legacy conversation endpoint |
19| `POST /openai/chat/completions` | OpenAI-compatible stateless chat completions |
20| `POST /openai/responses` | OpenAI-compatible responses API |
21
22> **Setup:** See [authentication](../_shared/authentication.md) for token setup.
23
24## Quick Start
25
26### Recommended: stateful conversations
27
28```bash
29curl -X POST https://api.acedata.cloud/aichat2/conversations \
30 -H "Authorization: ******ACEDATACLOUD_API_TOKEN" \
31 -H "Content-Type: application/json" \
32 -d '{"model":"gpt-4.1","question":"Summarize the latest release notes.","stateful":true}'
33```
34
35### OpenAI-compatible SDK
36
37```python
38from openai import OpenAI
39
40client = OpenAI(
41 api_key="your-token-here",
42 base_url="https://api.acedata.cloud/openai"
43)
44
45response = client.chat.completions.create(
46 model="gpt-5.5",
47 messages=[{"role": "user", "content": "Explain quantum computing"}]
48)
49print(response.choices[0].message.content)
50```
51
52## Currently Documented Model Families
53
54The OpenAPI specs expose a broad, fast-moving model catalog. Representative current
55models include:
56
57| Family | Current examples |
58|--------|------------------|
59| OpenAI / reasoning | `gpt-6-astra`, `gpt-5.6-luna`, `gpt-5.6-terra`, `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` |
60| 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` |
61| Claude | `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` |
62| Gemini | `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` |
63| Grok | `grok-4.5`, `grok-4`, `grok-4-0709`, `grok-3`, `grok-3-fast` |
64| DeepSeek | `deepseek-v4-pro`, `deepseek-v4-flash`, `deepseek-r1`, `deepseek-r1-0528`, `deepseek-v3`, `deepseek-v3-250324`, `deepseek-v3.2-exp` |
65| Kimi | `kimi-k3`, `kimi-k2.6`, `kimi-k2.5`, `kimi-k2-thinking-turbo`, `kimi-k2-thinking` |
66| 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` |
67
68`/aichat2/conversations` also accepts `model_group` values
69`chatgpt`, `claude`, `gemini`, `grok`, `kimi`, `glm`, and `deepseek`.
70
71> **Image-generating models are not chat models.** Names ending in `-image`
72> (e.g. `gemini-*-image`, `gpt-4o-image`) are image-generation models and do
73> not work on any chat surface listed above. Generate images through the
74> dedicated endpoints instead — Gemini via
75> `POST /v1beta/models/{model}:generateContent`, or `/nano-banana/images`.
76
77## OpenAI-Compatible Chat
78
79```json
80POST /openai/chat/completions
81{
82 "model": "gpt-4.1",
83 "messages": [{"role": "user", "content": "Write a haiku about observability."}],
84 "stream": true,
85 "tools": [
86 {
87 "type": "function",
88 "function": {
89 "name": "get_weather",
90 "parameters": {"type": "object", "properties": {"location": {"type": "string"}}}
91 }
92 }
93 ]
94}
95```
96
97Common parameters:
98
99| Parameter | Type | Description |
100|-----------|------|-------------|
101| `model` | string | One of the documented OpenAI-compatible models |
102| `messages` | array | Standard OpenAI chat message list |
103| `temperature` / `top_p` | number | Sampling controls |
104| `max_tokens` | integer | Output cap |
105| `stream` | boolean | Enable SSE streaming |
106| `tools` / `tool_choice` | array / string-object | Function-calling controls |
107| `service_tier` | string | Processing tier (`auto`, `default`, `flex`, `scale`, `priority`) |
108
109## Stateful / Agentic Conversations
110
111`POST /aichat2/conversations` generalizes the legacy conversation API with
112multimodal user content, CRUD-style actions, and server-side conversation state.
113
114```json
115POST /aichat2/conversations
116{
117 "action": "chat",
118 "model": "claude-sonnet-4-6",
119 "message": [
120 {"type": "text", "text": "Describe this image."},
121 {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
122 ],
123 "stateful": true,
124 "allowed_skills": ["google-search"],
125 "allowed_mcp_servers": ["mcp-google-search"]
126}
127```
128
129Useful parameters:
130
131| Parameter | Type | Description |
132|-----------|------|-------------|
133| `action` | string | `chat`, `retrieve`, `retrieve_batch`, `update`, `delete` |
134| `model` | string | Model name |
135| `question` | string | Simple text prompt |
136| `message` | string or array | Multimodal content using `text`, `image_url`, or `file_url` items |
137| `stateful` | boolean | Keep conversation history server-side |
138| `references` | array | Extra context documents |
139| `preset` | string | Preset/system prompt |
140| `max_turns` | integer | Trim retained turn history |
141| `allowed_skills` / `allowed_mcp_servers` | array | Restrict tool-use scope |
142| `unattended_policy` | object | Tool-use permission policy |
143| `tool_results` | array | Return results for previously requested tool calls |
144| `model_group` | string | Family selector (`chatgpt`, `claude`, `gemini`, `grok`, `kimi`, `glm`, `deepseek`) |
145| `offset` / `limit` | integer | Pagination for retrieval actions |
146| `callback_url` / `async` | string / boolean | Async execution |
147
148## Gotchas
149
150- The documented OpenAI-compatible routes live under `/openai/*`, not `/v1/*`.
151- `POST /aichat2/conversations` is the recommended stateful endpoint; `POST /aichat/conversations` remains for legacy clients.
152- `message` on `/aichat2/conversations` can be multimodal (`text`, `image_url`, `file_url`); plain `question` still works for simple text prompts.
153- `action` on `/aichat2/conversations` is not chat-only — it also supports `retrieve`, `retrieve_batch`, `update`, and `delete`.
154- Free-tier model variants such as `gpt-5.5:free` are documented on `/openai/chat/completions`.
acedatacloud