Text Generation

Generate human-like text using state-of-the-art LLMs via the OpenAI-compatible Chat Completions API.

OpenAI Compatible: Use the standard openai Python library just set base_url to https://api.oxlo.ai/v1. Any existing OpenAI code works without changes.

Available Models

Chat Models

Model	API ID	Tier	Best For
Llama-3.2-3B	llama-3.2-3b	Free	Fast responses, edge deployment
Mistral-7B	mistral-7b	Free	Chat, summaries, basic reasoning
DeepSeek V3.2	deepseek-v3.2	Free	General-purpose chat, analysis
Llama-3.1-8B	llama-3.1-8b	Pro	Instruction following, reasoning
Qwen 2.5 7B	qwen-2.5-7b	Pro	Multilingual, general reasoning
Ministral-14B	ministral-14b	Pro	Multilingual, vision-capable
Llama-4-Maverick-17B	llama-4-maverick-17b	Pro	Versatile MoE, diverse tasks
DeepSeek V3 0324	deepseek-v3-0324	Pro	Enhanced general-purpose chat
Kimi-2.5	kimi-k2.5	Premium	Balanced reasoning, vision
Qwen 3 32B	qwen-3-32b	Premium	Advanced reasoning, enterprise
Llama-3.3-70B	llama-3.3-70b	Premium	Long context, instruction following
GPT-OSS 120B	gpt-oss-120b	Premium	Complex reasoning, long context

Reasoning Models

Model	API ID	Tier	Best For
DeepSeek R1 8B	deepseek-r1-8b	Free	Math, science, chain-of-thought
DeepSeek R1 70B	deepseek-r1-70b	Pro	Advanced reasoning, analysis
GPT-OSS 20B	gpt-oss-20b	Pro	Agentic workflows, complex tasks
Kimi-K2-Thinking	kimi-k2-thinking	Premium	Deep reasoning, long-form analysis
DeepSeek-R1-0528	deepseek-r1-0528	Premium	Frontier-class reasoning

Coding Models

Model	API ID	Tier	Best For
DeepSeek Coder 33B	deepseek-coder-33b	Pro	Code generation, refactoring

Quick Example

Chat with any model using the OpenAI-compatible API:

import openai

client = openai.OpenAI(
    base_url="https://api.oxlo.ai/v1",
    api_key="<YOUR_API_KEY>"
)

response = client.chat.completions.create(
    model="deepseek-r1-8b",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=512
)

print(response.choices[0].message.content)

Multi-Turn Conversation

Pass conversation history in the messages array:

response = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Write a Python function to reverse a string"},
        {"role": "assistant", "content": "def reverse(s): return s[::-1]"},
        {"role": "user", "content": "Now make it handle Unicode correctly"}
    ],
    max_tokens=1024,
    temperature=0.3
)

Parameters

Parameter	Type	Default	Description
model	string	—	Model ID (required)
messages	array	—	Conversation messages (required)
max_tokens	integer	256	Max tokens to generate (1–131,072)
temperature	float	0.7	Randomness (0.0 = deterministic, 2.0 = creative)
top_p	float	1.0	Nucleus sampling threshold
frequency_penalty	float	0	Penalize repeated tokens (-2.0 to 2.0)
presence_penalty	float	0	Penalize tokens already present (-2.0 to 2.0)
stop	string[]	null	Up to 4 stop sequences
seed	integer	null	For reproducible results