Skip to main content
POST
/
api
/
v1
/
chat
curl --request POST \
  --url https://ninjachat.ai/api/v1/chat \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello, what can you do?"
    }
  ]
}
'
{
  "model": "gpt-5",
  "message": {
    "role": "assistant",
    "content": "I can help with a wide range of topics..."
  },
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 128,
    "total_tokens": 170
  },
  "cost": {
    "this_request": "$0.006"
  },
  "metadata": {
    "latency_ms": 1234
  }
}

Authorizations

​
Authorization
string
header
required

API key starting with nj_sk_

Body

application/json
​
messages
object[]
required

Conversation history (1–50 messages).

Required array length: 1 - 50 elements
​
model
enum<string>
default:ninja-1

Model to use. Ultra ($0.03/req): claude-opus-4.6. Premium ($0.015/req): claude-sonnet-4.6. Standard ($0.006/req): gpt-5, o3-mini, claude-sonnet-4.5, claude-haiku-4.5, gemini-2.5-pro, gemini-3-pro, gemini-3.1-pro, grok-4, kimi-k2, mistral-large, llama-4-maverick, kimi-k2.5. Budget ($0.003/req): gpt-5-mini, gemini-2.5-flash, gemini-3-flash, llama-4-scout, deepseek-v3, qwq-32b, glm-5, minimax-m2.5, ninja-1, uncensored-ai.

Available options:
gpt-5,
gpt-5-mini,
o3-mini,
claude-sonnet-4.5,
claude-sonnet-4.6,
claude-haiku-4.5,
claude-opus-4.6,
gemini-2.5-pro,
gemini-2.5-flash,
gemini-3-pro,
gemini-3-flash,
gemini-3.1-pro,
grok-4,
kimi-k2,
kimi-k2.5,
llama-4-scout,
llama-4-maverick,
deepseek-v3,
mistral-large,
qwq-32b,
glm-5,
minimax-m2.5,
ninja-1,
uncensored-ai
​
temperature
number
default:0.7

Sampling temperature. Lower = more precise, higher = more creative.

Required range: 0 <= x <= 2
​
max_tokens
integer
default:2048

Maximum output tokens.

Required range: 1 <= x <= 16384
​
stream
boolean
default:false

Enable server-sent events streaming.

Response

Successful completion.

​
model
string
Example:

"gpt-5"

​
message
object
​
usage
object
​
cost
object
​
metadata
object