connect

AI model routing

Kimi K3. DeepSeek. Muse.

Kimi K3, DeepSeek v4.1 Flash, and Meta Muse Spark Open. Use one OpenAI-compatible endpoint with clear pricing and usage receipts.

For specialized workloads, we run custom evals, train models, and manage serving. See custom models →

connect view models

Change the base URL. Keep your SDK.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["LOGITS_API_KEY"],
    base_url="https://api.thinwire.ai/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    reasoning_effort="low",
    max_tokens=2048,
    messages=[{"role": "user", "content": "Hello"}],
)

Live request path

Example request
Your SDK
Logits
deepseek-v4.1-flash
Receipt
Input1,284
Output342
StatusSettled

model routing

Choose your model. Keep the same API.

  • Change one URL
  • Published model rates
  • Per-request receipts

Pay for the models you use. DeepSeek and Muse use paid credits at the rates shown below.

models

Kimi K3. DeepSeek. Muse.

Explore Kimi K3, DeepSeek, and Muse with transparent token pricing and rate limits.

Kimi K3

Available

kimi-k3

Input
$2.4 / 1M tokens
Cached input
$0.24 / 1M tokens
Output
$12 / 1M tokens
Max output
65,536 tokens

Rate limits · per user, per model

Requests / min
600
Input tokens / min
8,000,000
Output tokens / min
200,000

524,288-token context window. Reasoning, streaming, and tool calls.

Also available as kimi-k3-base. Uses paid credits only.

DeepSeek v4.1 Flash

Available

deepseek-v4.1-flash

Input
$0.375 / 1M tokens
Cached input
$0.0075 / 1M tokens
Output
$1.5 / 1M tokens
Max output
65,536 tokens

Rate limits · per user, per model

Requests / min
600
Input tokens / min
8,000,000
Output tokens / min
200,000

Reasoning, streaming, and tool calls.

Uses paid credits only.

Meta Muse Spark Open

Available

muse-spark-open

50% off
Input
$1.25$0.625 / 1M tokens
Cached input
$0.15$0.075 / 1M tokens
Output
$4.25$2.125 / 1M tokens
Context window
262,144 tokens

Open-weight model optimized for agentic coding and tool calling.

Text API rate limits apply per user, per model, over a rolling 60-second window. If you receive HTTP 429, wait for the Retry-After interval before retrying.

next

Start with your next model.

One API for model routing, plus custom evals and model serving.

connect