Agents
Support, sales, research and workflow agents that need a low cost per run.
OpenAI-compatible Switch in two lines ›
One LLM gateway for every model
LLM API is an LLM gateway that gives your team one API key and one bill for 394 models from 31 labs.
Requests244,050
Tokens3.05B
Cost$6,485.93
Avg per 1M tokens$2.13
Cost over time
$0$100$200$300$400
Oct 1Oct 6Oct 11Oct 16Oct 21Oct 26
Model usageAll models ›
| Model | Requests | Tokens | Cost |
|---|---|---|---|
 claude-sonnet-5-5anthropic | 38,400 | 1.08B | $2,650.00 |
 kimi-k3novita | 22,900 | 443.0M | $1,552.50 |
 gpt-6-astraopenai | 3,150 | 70.1M | $945.00 |
 glm-5.3novita | 41,700 | 568.0M | $845.28 |
 gemini-3.8-flashgoogle-vertex | 56,300 | 409.0M | $393.75 |
 deepseek/deepseek-v4.1-flashcanopywave | 9,800 | 162.0M | $59.40 |
| gpt-6-lunaazure | 71,800 | 312.0M | $40.00 |
Cost breakdown
Top API keys
Key nameRequestsUsage
support-assistant96,310$3,018.44
search-indexer88,720$1,407.92
nightly-evals12,460$1,156.30
Trusted by 2100+ companies
Use cases
Coding tools
High-volume completion and review traffic across frontier and open models.
Image, audio and video
Generation pipelines on 139 video, 67 audio and 20 image models through the same API.
Search and RAG
Low-cost models for retrieval and reranking, stronger models only where quality needs them.
Open models
DeepSeek, GLM, Kimi, MiMo and other open-weight models, served by inference providers on LLM API. No GPUs to run. Prices per 1M tokens from the cheapest provider.
ModelServed byIn / out per 1MContext
Plans
Pay as you go, commit to a monthly volume, or sell the platform under your brand. All three use the same models and routing.
01 · One API key
Pay per token for every model
Prepaid credits, with routing, fallbacks, caching and per-team analytics included.
See pricing02 · Volume
Lower prices for committed volume
Commit to a monthly spend and get custom discounts on frontier models, with no change to your code.
See volume pricing03 · White label
Your own LLM gateway, under your brand
Your domain, prices and customers on our routing platform, live in a few weeks.
See white labelQuickstart
LLM API speaks the OpenAI and Anthropic APIs. Keep the SDK you use; change the base URL and the key.
- Create a keySign up and top up credits.
- Point the SDK at LLM APIThe two highlighted lines.
- Call each model through its own APIClaude through Messages, GPT through Responses, open models through Chat Completions. Every model page shows its code.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.llmapi.ai/v1",
api_key=os.environ["LLMAPI_KEY"],
)
response = client.chat.completions.create(
model="deepseek/deepseek-v4.1-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.llmapi.ai/v1",
apiKey: process.env.LLMAPI_KEY,
});
const response = await client.chat.completions.create({
model: "deepseek/deepseek-v4.1-flash",
messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);curl https://api.llmapi.ai/v1/chat/completions \
-H "Authorization: Bearer $LLMAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4.1-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.llmapi.ai/v1",
api_key=os.environ["LLMAPI_KEY"],
)
response = client.chat.completions.create(
model="glm-5.3",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.llmapi.ai/v1",
apiKey: process.env.LLMAPI_KEY,
});
const response = await client.chat.completions.create({
model: "glm-5.3",
messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);curl https://api.llmapi.ai/v1/chat/completions \
-H "Authorization: Bearer $LLMAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
import anthropic
client = anthropic.Anthropic(
base_url="https://api.llmapi.ai",
api_key=os.environ["LLMAPI_KEY"],
)
message = client.messages.create(
model="claude-sonnet-5-5",
max_tokens=16000,
messages=[{"role": "user", "content": "Hello"}],
)
for block in message.content:
if block.type == "text":
print(block.text)import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({
baseURL: "https://api.llmapi.ai",
apiKey: process.env.LLMAPI_KEY,
});
const message = await client.messages.create({
model: "claude-sonnet-5-5",
max_tokens: 16000,
messages: [{ role: "user", content: "Hello" }],
});
for (const block of message.content) {
if (block.type === "text") console.log(block.text);
}curl https://api.llmapi.ai/v1/messages \
-H "x-api-key: $LLMAPI_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "claude-sonnet-5-5",
"max_tokens": 16000,
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.llmapi.ai/v1",
api_key=os.environ["LLMAPI_KEY"],
)
response = client.responses.create(
model="gpt-6-astra",
input="Hello",
)
print(response.output_text)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.llmapi.ai/v1",
apiKey: process.env.LLMAPI_KEY,
});
const response = await client.responses.create({
model: "gpt-6-astra",
input: "Hello",
});
console.log(response.output_text);curl https://api.llmapi.ai/v1/responses \
-H "Authorization: Bearer $LLMAPI_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-6-astra", "input": "Hello"}'Model:
Customer story
“LLM API gave us the flexibility to benchmark models and choose the most cost-efficient option without compromising user experience.”
Mate Academy
- saved per year
- $36K
- implementation time
- 1 week
Enterprise
Ask sales for the DPA, an MSA or dedicated capacity.
Deployment
Region options, private routing, migration from a self-hosted gateway.
Security and data
Retention controls, zero-retention routes, audit logs.
Cost governance
Per-team attribution, budget limits and model policies. Invoice billing on NET terms for committed volume.
Commercial
MSA, DPA and SLA. Dedicated capacity and a dedicated account manager.
Compliance
Security and compliance
LLM API is SOC 2 compliant, ISO 27001 certified, and compliant with GDPR and CCPA.
Read the DPA
FAQ
Frequently asked questions
What is an LLM gateway?
An LLM gateway is one API in front of many model providers. Your app sends every request to one endpoint. The gateway picks a provider, falls back to another when one fails, and records usage and cost per team.
Is LLM API compatible with the OpenAI SDK?
Yes. LLM API implements the OpenAI Chat Completions and Responses APIs. Point your OpenAI SDK at https://api.llmapi.ai/v1, use your LLM API key and call any model by its ID.
How much cheaper is LLM API than buying from providers directly?
Up to 30% below provider list prices. Each model page shows what you pay per 1M tokens. Committed volume gets custom discounts on top.
Which models can I use?
394 models from 31 labs: 159 text, 139 video, 67 audio, 20 image and 9 embedding models. Labs include OpenAI, Anthropic, Google, DeepSeek, Mistral, xAI, Alibaba (Qwen) and Moonshot AI. The models page lists every model with its price.
Is LLM API ready for enterprise use?
Yes. You get per-team attribution and budgets, model policies, zero-retention routes and audit logs. Contracts include an MSA, a DPA and an SLA. LLM API is SOC 2 compliant, ISO 27001 certified, and compliant with GDPR and CCPA.
Sign up, top up credits and send your first request with the OpenAI SDK.
