llmdeal API reference.

Authorization: Bearer lld_<your-32-hex-token>

curl https://api.llmdeal.me/v1/chat/completions \
  -H "Authorization: Bearer $LLMDEAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "smart-route-fast",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

curl https://api.llmdeal.me/v1/chat/completions \
  -H "Authorization: Bearer $LLMDEAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "smart-route",
    "messages": [
      {"role": "system", "content": "You are a terse assistant."},
      {"role": "user",   "content": "Summarise this PR in one sentence."}
    ],
    "temperature": 0.2,
    "max_tokens": 512
  }'

{
  "id": "chatcmpl-9f2c...",
  "object": "chat.completion",
  "created": 1747200000,
  "model": "llama-3.3-70b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Refactored the loop into a single-pass reduce."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens":     412,
    "completion_tokens": 87,
    "total_tokens":      499
  }
}

curl -N https://api.llmdeal.me/v1/chat/completions \
  -H "Authorization: Bearer $LLMDEAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "smart-route",
    "stream": true,
    "messages": [{"role": "user", "content": "Stream a haiku."}]
  }'

# Server-Sent Events:
# data: {"id":"chatcmpl-9f2c","object":"chat.completion.chunk","choices":[{"delta":{"role":"assistant","content":"Refactored"}}]}
# data: {"id":"chatcmpl-9f2c","object":"chat.completion.chunk","choices":[{"delta":{"content":" the loop"}}]}
# data: {"id":"chatcmpl-9f2c","object":"chat.completion.chunk","choices":[{"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":12,"completion_tokens":5,"total_tokens":17}}
# data: [DONE]

curl https://api.llmdeal.me/v1/embeddings \
  -H "Authorization: Bearer $LLMDEAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bge-m3",
    "input": [
      "The quick brown fox jumps over the lazy dog.",
      "Embed me too."
    ]
  }'

{
  "object": "list",
  "model": "bge-m3",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [0.012, -0.034] },
    { "object": "embedding", "index": 1, "embedding": [0.057,  0.018] }
  ],
  "usage": { "prompt_tokens": 24, "total_tokens": 24 }
}

curl https://api.llmdeal.me/v1/cost-preview \
  -H "Authorization: Bearer $LLMDEAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "smart-route",
    "messages": [
      {"role": "user", "content": "Explain Raft consensus in 200 words."}
    ],
    "max_tokens": 300
  }'

{
  "ok": true,
  "model": "smart-route",
  "input_tokens": 11,
  "est_output_tokens": { "low": 60, "expected": 180, "high": 300 },
  "est_cost_usd": {
    "low":      0.0000573,
    "expected": 0.0001653,
    "high":     0.0002733
  },
  "breakdown":   { "input_usd": 0.0000033, "output_usd": 0.000162 },
  "rate_per_1m": { "input": 0.30, "output": 0.90 },
  "currency": "usd",
  "estimator": "tiktoken-cl100k-base"
}

curl https://api.llmdeal.me/v1/cost-preview/rates \
  -H "Authorization: Bearer $LLMDEAL_KEY"

{
  "ok": true,
  "currency": "usd",
  "default_rate": { "input": 0.4, "output": 1.2 },
  "rates": [
    { "model": "bge-m3",                 "input_per_1m": 0.01, "output_per_1m": 0.00 },
    { "model": "codestral",              "input_per_1m": 0.30, "output_per_1m": 0.90 },
    { "model": "consortium-llama-70b",   "input_per_1m": 0.15, "output_per_1m": 0.45 },
    { "model": "llama-3.3-70b",          "input_per_1m": 0.20, "output_per_1m": 0.60 },
    { "model": "smart-route-fast",       "input_per_1m": 0.15, "output_per_1m": 0.45 }
  ],
  "catalog": [
    { "id": "llama-70b", "display_name": "Llama 3.3 70B", "tiers": ["free-trial","starter","pro","founder","charter"], "context_window": 128000 }
  ],
  "accessible_to_caller": ["llama-70b","llama-8b","gemini-flash","smart-route","smart-route-fast"],
  "caller_tier": "starter",
  "note": "Unknown models fall back to the default rate (conservative)."
}

curl https://api.llmdeal.me/v1/models \
  -H "Authorization: Bearer $LLMDEAL_KEY"

{
  "object": "list",
  "data": [
    {
      "id": "llama-70b",
      "object": "model",
      "created": 1747353600,
      "owned_by": "llmdeal",
      "context_window": 128000,
      "tags": ["chat", "fast"]
    },
    {
      "id": "smart-route-fast",
      "object": "model",
      "created": 1747353600,
      "owned_by": "llmdeal",
      "context_window": 131072,
      "tags": ["auto", "fast"]
    }
  ]
}

{
  "error": {
    "code":    "model_not_in_tier",
    "message": "Your tier (starter) cannot call 'qwen-coder'. Upgrade to pro+ or use smart-route.",
    "type":    "invalid_request_error"
  }
}

from openai import OpenAI

client = OpenAI(
    api_key="lld_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.llmdeal.me/v1",
)

resp = client.chat.completions.create(
    model="smart-route",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey:  process.env.LLMDEAL_KEY,
  baseURL: 'https://api.llmdeal.me/v1',
});

const resp = await client.chat.completions.create({
  model:    'smart-route',
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(resp.choices[0].message.content);

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="smart-route",
    api_key="lld_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.llmdeal.me/v1",
)
print(llm.invoke("Hello!").content)

import instructor
from openai import OpenAI
from pydantic import BaseModel

class Answer(BaseModel):
    summary: str

client = instructor.from_openai(OpenAI(
    api_key="lld_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.llmdeal.me/v1",
))

answer = client.chat.completions.create(
    model="smart-route",
    response_model=Answer,
    messages=[{"role": "user", "content": "What is Raft consensus?"}],
)
print(answer.summary)