Create Chat Completion

OpenAI-compatible uncensored chat and role-play, with streaming.

Drop-in compatible with the OpenAI SDK: point baseURL at https://api.spicyapi.com/v1 and pass your SpicyAPI key. Billed per 1M prompt tokens and per 1M completion tokens, at the model's rates.

Models. spicy-chat-1 ($0.80 in, $2.40 out per 1M tokens) is the general uncensored chat model. spicy-companion-1 ($1.00 in, $2.80 out per 1M tokens) is fine-tuned for role-play and AI companions: put the persona in the system message and it stays in character, writes explicit adult scenes, handles group scenes with several characters, and returns up to 4 alternative replies with n. It is the recommended model for explicit role-play, which spicy-chat-1 may decline. spicy-companion-1-flash ($0.10 in, $0.80 out per 1M tokens) is the same role-play behaviour priced for high-volume traffic such as NPCs. All three take the same request body.

Text only, with caps: input across all messages up to about 200,000 tokens on spicy-chat-1, 131,072 on spicy-companion-1 and at least 144,000 (tested) on spicy-companion-1-flash, max_tokens up to 8192 (default 4096), n up to 4. Requests that set enable_thinking, thinking_budget, enable_search or search_options, ask for response_format.type: "json_schema", or carry non-text content parts (images, audio) are rejected with a 400 before any charge. Unknown fields are dropped silently.

Function calling: tools, tool_choice and parallel_tool_calls work as in the OpenAI API on spicy-chat-1 and spicy-companion-1 (not on spicy-companion-1-flash, which returns a 400). The reply carries tool_calls; send the result back as a tool message with its tool_call_id. Tool definitions and earlier tool calls are prompt tokens, billed at the model's input price.

Billing: the balance (and any monthly spend limit) must cover the worst case before the call: the estimated prompt plus every completion at max_tokens, else a 402. You are then charged for the tokens actually used. Prompt tokens the provider serves from its cache (usage.prompt_tokens_details.cached_tokens, a repeated prefix of 1,024 tokens or more) bill at the model's cached input price (pricing.usd_cached_input in GET /v1/models): $0.16 per 1M on spicy-chat-1, $0.20 on spicy-companion-1 and $0.02 on spicy-companion-1-flash, a fifth of their input prices.

Safety signal: self-harm is not a blocked category. When the screen reads a risk of self-harm in the conversation, the response (streamed or not) carries the header x-spicyapi-safety: self_harm so your app can show crisis resources (in the US 988, in the UK and Ireland Samaritans on 116 123, elsewhere findahelpline.com). The header is absent otherwise.

Companion laws: New York (GBL Art 47) and California (SB 243) ask companion apps to tell users they are talking to an AI (in New York at the start of each session and at least every 3 hours) and to refer users at risk to crisis services. If your app offers companions, send safety_mode: "companion" to have SpicyAPI add both to the reply text.

curl --request POST \
  --url https://api.spicyapi.com/v1/chat/completions \
  --header 'Authorization: Bearer $SPICYAPI_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "spicy-chat-1",
    "messages": [
      { "role": "user", "content": "Hey, how was your day?" }
    ],
    "temperature": 0.9
  }'

# role-play: persona in the system message, three reply options
curl --request POST \
  --url https://api.spicyapi.com/v1/chat/completions \
  --header 'Authorization: Bearer $SPICYAPI_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "spicy-companion-1",
    "messages": [
      { "role": "system", "content": "You are Mara, 29, a confident bartender who flirts with the user. Stay in character, write in first person, keep replies under 120 words." },
      { "role": "user", "content": "Last call. What are you pouring me?" }
    ],
    "n": 3,
    "temperature": 0.9
  }'

{
  "id": "chatcmpl_7b3f",
  "object": "chat.completion",
  "model": "spicy-chat-1",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "<string>" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 12, "completion_tokens": 84, "total_tokens": 96 },
  "cost_usd": 0.001
}