API Documentation

llmair is OpenAI-compatible. If you can use the OpenAI API, you can use llmair — just change the base URL to https://api.llmair.ai/v1.

Get Your API Key

Sign up for free and get 100,000 tokens. No credit card required.

Base URL

https://api.llmair.ai/v1OpenAI-compatible endpoint — same format, just swap the URL

Authentication

Pass your API key in the Authorization header:

Authorization: Bearer $LLMAIR_API_KEY

Code Examples

Make your first API call in under a minute.

curl https://api.llmair.ai/v1/chat/completions \
  -H "Authorization: Bearer $LLMAIR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V3",
    "messages": [{"role": "user", "content": "Explain quantum computing in one sentence."}],
    "max_tokens": 100
  }'

Available Models

82 models from DeepSeek, Qwen, GLM, Kimi, and more. Prices shown per 1M tokens.

premiumhighmidbudgetutility
GPT-4o
by OpenAI

Flagship multimodal model

Input
$2.50
Output
$10.00
Context
128K
GPT-4 Turbo
by OpenAI

High-capability GPT-4

Input
$10.00
Output
$30.00
Context
128K
GPT-4o (router)
by OpenAI
gpt-4o

OpenAI-compatible router id

Input
$2.50
Output
$10.00
Context
128K
GPT-4 Turbo (router)
by OpenAI
gpt-4-turbo

OpenAI-compatible router id

Input
$10.00
Output
$30.00
Context
128K
GPT-4 Turbo Preview
by OpenAI
gpt-4-turbo-preview

Preview Turbo variant

Input
$10.00
Output
$30.00
Context
128K
GPT-4o Mini
by OpenAI

Fast, lightweight GPT-4o

Input
$0.15
Output
$0.60
Context
128K
GPT-3.5 Turbo
by OpenAI

Fast, older generation

Input
$0.50
Output
$1.50
Context
16K
GPT-5.5
by OpenAI

Latest flagship, complex reasoning, code, long context

Input
$3.50
Output
$10.50
Context
256K
GPT-5.5 (router)
by OpenAI
gpt-5.5

OpenAI-compatible router id

Input
$3.50
Output
$10.50
Context
256K
o1
by OpenAI

Deep reasoning model

Input
$15.00
Output
$60.00
Context
128K
o3
by OpenAI

Frontier reasoning model

Input
$10.00
Output
$40.00
Context
128K
o1 (router)
by OpenAI
o1

Reasoning model, router id

Input
$15.00
Output
$60.00
Context
128K
o1 Preview
by OpenAI
o1-preview

Reasoning preview

Input
$15.00
Output
$60.00
Context
128K
o1 Mini
by OpenAI
o1-mini

Lightweight reasoning

Input
$3.00
Output
$12.00
Context
128K
o3 (router)
by OpenAI
o3

Frontier reasoning, router id

Input
$10.00
Output
$40.00
Context
128K
o3 Mini
by OpenAI
o3-mini

Compact reasoning

Input
$1.10
Output
$4.40
Context
128K
Claude 3 Opus
by Anthropic

Deep analysis, long-form writing

Input
$15.00
Output
$75.00
Context
200K
Claude 3 Opus (2024-02)
by Anthropic

Snapshot Opus version

Input
$15.00
Output
$75.00
Context
200K
Claude 3.5 Sonnet
by Anthropic

Balanced, thoughtful, capable

Input
$3.00
Output
$15.00
Context
200K
Claude 3 Haiku
by Anthropic

Fast and lightweight

Input
$0.25
Output
$1.25
Context
200K
Claude 3.5 Haiku
by Anthropic

Fast and lightweight

Input
$0.25
Output
$1.25
Context
200K
Claude 3 Opus (router)
by Anthropic
claude-3-opus

OpenRouter-style id

Input
$15.00
Output
$75.00
Context
200K
Claude Sonnet 4
by Anthropic
claude-sonnet-4

Latest Sonnet

Input
$3.00
Output
$15.00
Context
200K
Claude Sonnet 4 (2025-05)
by Anthropic
claude-sonnet-4-20250514

Latest Sonnet snapshot

Input
$3.00
Output
$15.00
Context
200K
Gemini Pro
by Google

Clear, balanced answers

Input
$0.50
Output
$1.50
Context
128K
Gemini Ultra
by Google

Deepest Google model

Input
$1.50
Output
$4.50
Context
128K
Gemini 2.5 Pro
by Google
gemini-2.5-pro

Latest Gemini Pro tier

Input
$1.25
Output
$5.00
Context
128K
Gemini 2.5 Flash
by Google
gemini-2.5-flash

Fast, lightweight Gemini

Input
$0.10
Output
$0.40
Context
128K
Grok 2
by xAI

Witty, slightly rebellious

Input
$2.00
Output
$6.00
Context
128K
Llama 3 70B
by Meta

Open-weights flagship

Input
$0.79
Output
$0.79
Context
128K
Llama 3 8B
by Meta

Mid-tier open model

Input
$0.07
Output
$0.07
Context
128K
Llama 3 8B (alt)
by Meta

Alt id for Llama 3 8B

Input
$0.07
Output
$0.07
Context
128K
Llama 3 70B (alt)
by Meta

Alt id for Llama 3 70B

Input
$0.79
Output
$0.79
Context
128K
Mistral Large
by Mistral

Clear, structured European model

Input
$2.00
Output
$6.00
Context
128K
DeepSeek Chat
by DeepSeek

Direct chat model

Input
$0.14
Output
$0.28
Context
128K
DeepSeek R1 (chat)
by DeepSeek

Chat form of R1 reasoning

Input
$0.55
Output
$2.19
Context
128K
Qwen Turbo
by Alibaba

Fast, economical Qwen

Input
$0.20
Output
$0.60
Context
128K
Qwen Plus
by Alibaba

Balanced Qwen tier

Input
$0.40
Output
$1.20
Context
128K
DeepSeek V3
by DeepSeek
DeepSeek-V3

Complex reasoning, research

Input
$0.50
Output
$2.00
Context
128K
DeepSeek V3.1
by DeepSeek
DeepSeek-V3.1-Terminus

Complex reasoning

Input
$0.50
Output
$2.00
Context
128K
DeepSeek V3.2
by DeepSeek
DeepSeek-V3.2

Complex reasoning, latest

Input
$0.55
Output
$2.20
Context
128K
DeepSeek R1
by DeepSeek
DeepSeek-R1

Advanced reasoning

Input
$0.70
Output
$2.80
Context
128K
DeepSeek V4 Flash
by DeepSeek
DeepSeek-V4-Flash

Fast, cost-efficient

Input
$0.10
Output
$0.40
Context
128K
DeepSeek V4 Pro
by DeepSeek
DeepSeek-V4-Pro

Balanced performance

Input
$0.15
Output
$0.60
Context
128K
Qwen3 8B
by Alibaba
Qwen3-8B

Fast, low-cost tasks

Input
$0.05
Output
$0.15
Context
32K
Qwen3 14B
by Alibaba
Qwen3-14B

Balanced general purpose

Input
$0.08
Output
$0.30
Context
64K
Qwen3 32B
by Alibaba
Qwen3-32B

Strong reasoning, coding

Input
$0.15
Output
$0.60
Context
64K
Qwen3 30B MoE
by Alibaba
Qwen3-30B-A3B-Instruct-2507

Efficient high-capability MoE

Input
$0.20
Output
$0.80
Context
64K
Qwen3 Coder 30B
by Alibaba
Qwen3-Coder-30B-A3B-Instruct

Code generation, debugging

Input
$0.20
Output
$0.80
Context
64K
Qwen2.5 27B
by Alibaba
Qwen3.5-27B

General purpose, long context

Input
$0.12
Output
$0.50
Context
64K
Qwen2.5 35B MoE
by Alibaba
Qwen3.5-35B-A3B

High capability, efficient

Input
$0.18
Output
$0.70
Context
64K
Qwen2.5 9B
by Alibaba
Qwen3.5-9B

Fast, low-cost tasks

Input
$0.05
Output
$0.20
Context
32K
Qwen2.5 4B
by Alibaba
Qwen3.5-4B

Minimal cost, quick tasks

Input
$0.03
Output
$0.10
Context
32K
Qwen2.5 397B
by Alibaba
Qwen3.5-397B-A17B

Maximum capability, research

Input
$3.00
Output
$12.00
Context
128K
Qwen3.6 27B
by Alibaba
Qwen3.6-27B

Latest generation, reasoning

Input
$0.15
Output
$0.60
Context
64K
Qwen3 72B
by Alibaba
Qwen3-72B-Instruct

High capability, complex tasks

Input
$0.80
Output
$3.20
Context
64K
Qwen2.5 72B 128K
by Alibaba
Qwen2.5-72B-Instruct-128K

Long documents, massive context

Input
$1.00
Output
$4.00
Context
128K
GLM-4.5 Air
by Zhipu
GLM-4.5-Air

Long context, Chinese language

Input
$0.10
Output
$0.40
Context
128K
GLM-4.7
by Zhipu
GLM-4.7

Advanced reasoning, long context

Input
$0.20
Output
$0.80
Context
128K
GLM-5
by Zhipu
GLM-5

Latest GLM, highest capability

Input
$0.30
Output
$1.20
Context
128K
GLM-5.1
by Zhipu
GLM-5.1

Latest version, research

Input
$0.35
Output
$1.40
Context
128K
GLM-Z1 9B
by Zhipu
GLM-Z1-9B-0414

Fast reasoning, low cost

Input
$0.05
Output
$0.20
Context
32K
Hunyuan 13B MoE
by Tencent
Hunyuan-A13B-Instruct

General purpose, Tencent ecosystem

Input
$0.15
Output
$0.60
Context
64K
Hunyuan MT 7B
by Tencent
Hunyuan-MT-7B

Translation, multilingual

Input
$0.08
Output
$0.30
Context
32K
Step-3.5 Flash
by StepFun
Step-3.5-Flash

Fast, cost-effective tasks

Input
$0.05
Output
$0.20
Context
32K
Nex-N2 Pro
by Nex-AGI
Nex-N2-Pro

Advanced reasoning, agentic tasks

Input
$0.20
Output
$0.80
Context
128K
Seed 36B
by ByteDance
Seed-OSS-36B-Instruct

High capability, creative tasks

Input
$0.50
Output
$2.00
Context
64K
MiniMax-M2.5
by MiniMax
MiniMax-M2.5

Long context, multimodal

Input
$0.12
Output
$0.50
Context
128K
DeepSeek R1 Pro
by DeepSeek
deepseek-ai

Maximum reasoning capability

Input
$0.80
Output
$3.20
Context
128K
DeepSeek V3 Pro
by DeepSeek
deepseek-ai

Premium DeepSeek performance

Input
$0.60
Output
$2.40
Context
128K
Kimi K2.5 Pro
by Moonshot
moonshotai

Very long context, research

Input
$0.50
Output
$2.00
Context
200K
Kimi K2.6 Pro
by Moonshot
moonshotai

Latest Kimi, longest context

Input
$0.60
Output
$2.40
Context
200K
GLM-5 Pro
by Zhipu
zai-org

Premium GLM capability

Input
$0.40
Output
$1.60
Context
128K
Qwen2.5 7B Pro
by Alibaba
Qwen

Efficient Pro tier

Input
$0.04
Output
$0.15
Context
32K
Qwen3 VL 8B👁 Vision
by Alibaba
Qwen3-VL-8B-Instruct

Vision + text, image understanding

Input
$0.10
Output
$0.40
Context
32K
Qwen3 VL 32B👁 Vision
by Alibaba
Qwen3-VL-32B-Instruct

High-capability vision

Input
$0.25
Output
$1.00
Context
64K
Qwen3 VL30B MoE👁 Vision
by Alibaba
Qwen3-VL-30B-A3B-Instruct

Vision MoE, efficient

Input
$0.30
Output
$1.20
Context
64K
GLM-4.5V👁 Vision
by Zhipu
GLM-4.5V

Vision + text, Chinese focus

Input
$0.20
Output
$0.80
Context
64K
Kolors
by Kwai
Kolors

Image generation, creative

Input
$0.05
Output
$0.20
Context
4K
Qwen Image👁 Vision
by Alibaba
Qwen-Image

Image understanding

Input
$0.03
Output
$0.10
Context
4K
SenseVoice Small
by FunAudioLLM
SenseVoiceSmall

Speech recognition, voice AI

Input
$0.02
Output
$0.05
Context
32K
CosyVoice 2
by FunAudioLLM
CosyVoice2-0.5B

Voice synthesis, TTS

Input
$0.03
Output
$0.10
Context
8K

Request Parameters

ParameterTypeDefaultDescription
modelstringModel ID (see Available Models above)*required
messagesarrayArray of {role, content}. Roles: system, user, assistant*required
temperaturefloat0.7Sampling temperature 0–2. Lower = more focused
max_tokensint4096Max tokens to generate
top_pfloat1.0Nucleus sampling threshold
streamboolfalseStream response token-by-token
stopstring/arraynullStop sequence(s) to end generation

API Endpoints

POST/v1/chat/completionsSend a chat completion requestChat
POST/v1/embeddingsGenerate text embeddingsEmbeddings
GET/v1/modelsList all available modelsModels
POST/auth/registerCreate a new accountAuth
POST/auth/loginGet access tokenAuth
GET/user/balanceCheck token balanceUser
GET/user/subscriptionGet subscription detailsUser
GET/api-keys/List your API keysAPI Keys
POST/api-keys/Create a new API keyAPI Keys
DELETE/api-keys/{key_id}Delete an API keyAPI Keys

Error Codes

400Bad Request — invalid parameters
401Unauthorized — invalid or missing API key
402Insufficient balance — buy more tokens
403Forbidden — model not available on your plan
429Rate limit exceeded — slow down requests
500Server error — contact support if persistent

Start building in minutes

100,000 free tokens. No credit card required.