Text Models (LLMs)

Text models on XRoute encompass state-of-the-art Large Language Models (LLMs) and reasoning engines for conversational AI, code generation, summarization, and agent workflows. All text models support three flexible invocation formats:

OpenAI Unified Format: POST https://api.xroute.ai/v1/chat/completions
Anthropic Unified Format: POST https://api.xroute.ai/v1/messages
Provider Native Direct Format: POST https://api.xroute.ai/{Provider}/...

Supported Text Models

Provider	Model Identifier	Max Context	Recommended Protocol	Primary Features
OpenAI	`OpenAI/gpt-5.6-sol`	200K	OpenAI / Anthropic / Native	Frontier general reasoning, deep coding, structured JSON
Anthropic	`Anthropic/claude-fable-5`	200K	Anthropic / OpenAI / Native	Nuanced writing, complex instructions, extended reasoning
Google	`Google/gemini-3.1-pro-preview`	1M	OpenAI / Anthropic / Native	Million-token context window, multimodal reasoning
Byteplus	`Byteplus/seed-2-0-code-preview-260328`	128K	OpenAI / Anthropic / Native	Low-latency programming, high-throughput agent tasks
Deepseek	`Deepseek/deepseek-v4-flash`	64K	OpenAI / Anthropic / Native	Ultra-high performance, economical token rates
GLM	`GLM/glm-5`	128K	OpenAI / Anthropic / Native	Robust bilingual reasoning, knowledge grounding

1. OpenAI Unified Invocation

Call any text model using the standard OpenAI Chat Completions schema. Simply set base_url="https://api.xroute.ai/v1" and authenticate with your XRoute API key.

Endpoint: POST https://api.xroute.ai/v1/chat/completions
Header: Authorization: Bearer $XROUTE_API_KEY

curl -X POST "https://api.xroute.ai/v1/chat/completions" \
  -H "Authorization: Bearer $XROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "OpenAI/gpt-5.6-sol",
    "messages": [
      {"role": "system", "content": "You are a senior systems engineer."},
      {"role": "user", "content": "Explain the architectural advantages of distributed AI gateways."}
    ],
    "temperature": 0.7,
    "stream": false
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.xroute.ai/v1",
    api_key="your_xroute_api_key",
)

response = client.chat.completions.create(
    model="OpenAI/gpt-5.6-sol",
    messages=[
        {"role": "system", "content": "You are a senior systems engineer."},
        {"role": "user", "content": "Explain the architectural advantages of distributed AI gateways."}
    ],
    temperature=0.7,
)

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

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.xroute.ai/v1',
  apiKey: process.env.XROUTE_API_KEY,
});

const response = await client.chat.completions.create({
  model: 'OpenAI/gpt-5.6-sol',
  messages: [
    { role: 'user', content: 'Explain the architectural advantages of distributed AI gateways.' }
  ],
});

console.log(response.choices[0].message.content);

2. Anthropic Unified Invocation

Route requests across any provider using the Anthropic Messages schema. Compatible with Claude Code and tools built around /v1/messages.

Endpoint: POST https://api.xroute.ai/v1/messages
Headers:
- x-api-key: $XROUTE_API_KEY
- anthropic-version: 2023-06-01

curl -X POST "https://api.xroute.ai/v1/messages" \
  -H "x-api-key: $XROUTE_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Anthropic/claude-fable-5",
    "max_tokens": 1024,
    "system": "You are a concise software architect.",
    "messages": [
      {"role": "user", "content": "Compare REST and gRPC latency characteristics."}
    ]
  }'

from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.xroute.ai/v1",
    api_key="your_xroute_api_key",
)

message = client.messages.create(
    model="Anthropic/claude-fable-5",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Compare REST and gRPC latency characteristics."}
    ],
)

print(message.content[0].text)

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  baseURL: 'https://api.xroute.ai/v1',
  apiKey: process.env.XROUTE_API_KEY,
});

const message = await client.messages.create({
  model: 'Anthropic/claude-fable-5',
  max_tokens: 1024,
  messages: [
    { role: 'user', content: 'Compare REST and gRPC latency characteristics.' }
  ],
});

console.log(message.content[0].text);

3. Provider Native Invocation

Directly communicate with vendor-specific APIs and SDKs by targeting the {Provider} routing namespace.

Google Gemini Native
Byteplus Ark Native
Deepseek / GLM Native

Endpoint: POST https://api.xroute.ai/Google/models/{model_id}:generateContent

cURL

curl -X POST "https://api.xroute.ai/Google/models/gemini-3.1-pro-preview:generateContent" \
  -H "Authorization: Bearer $XROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {"text": "Provide an overview of speculative decoding in LLMs."}
        ]
      }
    ]
  }'

Python (google-genai SDK)

from google import genai

client = genai.Client(
    api_key="your_xroute_api_key",
    http_options={"base_url": "https://api.xroute.ai/Google"},
)

response = client.models.generate_content(
    model="gemini-3.1-pro-preview",
    contents="Provide an overview of speculative decoding in LLMs.",
)
print(response.text)

Endpoint: POST https://api.xroute.ai/Byteplus/chat/completions

Python (Byteplus Ark SDK)

from byteplus_sdk_ark_runtime import Ark

client = Ark(
    base_url="https://api.xroute.ai/Byteplus",
    api_key="your_xroute_api_key",
)

completion = client.chat.completions.create(
    model="Byteplus/seed-2-0-code-preview-260328",
    messages=[{"role": "user", "content": "Implement quicksort in Go."}],
)
print(completion.choices[0].message.content)

Endpoint: POST https://api.xroute.ai/Deepseek/services/aigc/text-generation/generation

cURL

curl -X POST "https://api.xroute.ai/Deepseek/services/aigc/text-generation/generation" \
  -H "Authorization: Bearer $XROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "input": {
      "messages": [
        {"role": "user", "content": "Explain zero-copy networking."}
      ]
    },
    "parameters": {
      "result_format": "message"
    }
  }'