Skip to main content

​
Supported Models

DeepMyst provides a unified API for accessing various language models with built-in token optimization. The platform supports models from multiple providers through a single, consistent interface.

​
Enabled Providers

The following providers are enabled by default for all users:

​
OpenAI

  • gpt-5.2-pro - GPT-5.2 Pro
  • gpt-5.2 - GPT-5.2
  • gpt-5 - GPT-5
  • gpt-5-chat-latest - GPT-5 Chat Latest
  • gpt-5-mini - GPT-5 Mini
  • gpt-5-nano - GPT-5 Nano
  • gpt-4.1 - GPT-4.1
  • chatgpt-4o-latest - ChatGPT-4o Latest
  • o3-deep-research - O3 Deep Research
  • o4-mini-deep-research - O4 Mini Deep Research
  • gpt-audio - GPT Audio
  • gpt-audio-mini - GPT Audio Mini
  • gpt-realtime - GPT Realtime
  • gpt-realtime-mini - GPT Realtime Mini
  • gpt-oss-120b - GPT OSS 120B
  • gpt-oss-20b - GPT OSS 20B

​
Claude (Anthropic)

  • claude-opus-4-5 - Claude Opus 4.5
  • claude-opus-4-1 - Claude Opus 4.1
  • claude-opus-4 - Claude Opus 4
  • claude-sonnet-4-5 - Claude Sonnet 4.5
  • claude-sonnet-4 - Claude Sonnet 4
  • claude-haiku-4-5 - Claude Haiku 4.5
  • claude-haiku-3 - Claude Haiku 3

​
Gemini (Google)

  • gemini-3-pro-preview - Gemini 3 Pro Preview
  • gemini-3-flash-preview - Gemini 3 Flash Preview
  • gemini-2.5-pro - Gemini 2.5 Pro
  • gemini-2.5-flash - Gemini 2.5 Flash
  • gemini-2.5-flash-lite - Gemini 2.5 Flash Lite
  • gemini-2.0-flash - Gemini 2.0 Flash
  • gemini-2.0-flash-lite - Gemini 2.0 Flash Lite

​
Grok (xAI)

  • grok-4 - Grok 4
  • grok-4-fast - Grok 4 Fast
  • grok-4.1-fast - Grok 4.1 Fast
  • grok-3 - Grok 3
  • grok-3-mini - Grok 3 Mini
  • grok-2-vision - Grok 2 Vision
  • grok-2-vision-latest - Grok 2 Vision Latest
  • grok-code-fast-1 - Grok Code Fast

​
Groq

  • llama-4-maverick - Llama 4 Maverick
  • llama-4-scout - Llama 4 Scout
  • llama-3.3-70b-versatile - Llama 3.3 70B Versatile
  • llama-3.1-8b-instant - Llama 3.1 8B Instant
  • llama-guard-4-12b - Llama Guard 4 12B

​
DeepSeek

  • deepseek-chat - DeepSeek Chat
  • deepseek-reasoner - DeepSeek Reasoner

​
AWS Bedrock

  • bedrock-claude-3-7-sonnet - Bedrock Claude 3.7 Sonnet
  • bedrock-claude-3-5-sonnet - Bedrock Claude 3.5 Sonnet
  • bedrock-claude-3-opus - Bedrock Claude 3 Opus
  • bedrock-claude-3-sonnet - Bedrock Claude 3 Sonnet
  • bedrock-claude-3-haiku - Bedrock Claude 3 Haiku
  • bedrock-claude-v2 - Bedrock Claude V2
  • bedrock-claude-instant - Bedrock Claude Instant
  • bedrock-deepseek-r1 - Bedrock DeepSeek R1
  • bedrock-llama3-1-405b - Bedrock Llama 3.1 405B
  • bedrock-llama3-1-70b - Bedrock Llama 3.1 70B
  • bedrock-llama3-1-8b - Bedrock Llama 3.1 8B
  • bedrock-llama3-70b - Bedrock Llama 3 70B
  • bedrock-mixtral-8x7b - Bedrock Mixtral 8x7B
  • bedrock-mistral-7b - Bedrock Mistral 7B
  • bedrock-titan-express - Bedrock Titan Express

​
OpenRouter

Access 400+ models through OpenRouter integration. Use the openrouter/ prefix:
  • openrouter-auto - Auto-router (selects best model)
  • openrouter/* - Wildcard access to all OpenRouter models
Popular OpenRouter Models:
  • openrouter/openai/gpt-5.2 - GPT-5.2
  • openrouter/openai/gpt-5 - GPT-5
  • openrouter/openai/gpt-4.1 - GPT-4.1
  • openrouter/openai/o3-mini - O3 Mini
  • openrouter/anthropic/claude-opus-4.5 - Claude Opus 4.5
  • openrouter/anthropic/claude-sonnet-4.5 - Claude Sonnet 4.5
  • openrouter/anthropic/claude-haiku-4.5 - Claude Haiku 4.5
  • openrouter/google/gemini-3-pro-preview - Gemini 3 Pro
  • openrouter/google/gemini-2.5-pro - Gemini 2.5 Pro
  • openrouter/deepseek/deepseek-r1 - DeepSeek R1
  • openrouter/deepseek/deepseek-v3.2 - DeepSeek V3.2
  • openrouter/x-ai/grok-4 - Grok 4
  • openrouter/mistralai/mistral-large-2512 - Mistral Large
  • openrouter/qwen/qwen3-coder - Qwen 3 Coder

​
Additional Providers

The following providers are available upon request. Contact us to enable these for your account:
ProviderModels Available
AnyscaleVarious open-source models
Azure AIAzure-hosted AI models
Azure OpenAIazure-gpt-4o, azure-gpt-4o-mini, azure-gpt-4-turbo, azure-gpt-4, azure-o1, azure-o1-mini
Basetenbaseten-llama-3-1-70b, baseten-mistral-7b
Cerebrascerebras-llama3-3-70b, cerebras-llama3-1-70b, cerebras-llama3-1-8b
Coherecommand-a-03-2025, command-r-plus, command-r, command-nightly, command-light
Databricksdatabricks-dbrx-instruct, databricks-llama-3-1-70b, databricks-mixtral-8x7b
Google AI StudioDirect Google AI Studio access
Gradient AIGradient-hosted models
HerokuHeroku-deployed models
HuggingFacehuggingface-gemma-7b, huggingface-llama-3-1-8b, huggingface-mistral-7b, huggingface-phi-3-mini, huggingface-qwen2-72b
IBM Watsonxwatsonx-llama-3-1-70b, watsonx-mixtral-8x7b, watsonx-granite-13b
Meta LlamaDirect Meta Llama API access
Mistral AImistral-large-latest, mistral-medium-latest, mistral-small-latest, codestral-latest, magistral-medium, open-mixtral-8x22b
Moonshot AImoonshot-v1-32k, moonshot-v1-8k
NVIDIA NIMnvidia-llama-3-1-405b, nvidia-llama-3-1-70b, nvidia-llama-3-1-8b, nvidia-mixtral-8x7b
Oracle Cloudoci-cohere-command-r-plus, oci-cohere-command-r
Perplexity AIsonar, sonar-pro, sonar-reasoning, sonar-reasoning-pro, sonar-deep-research
Replicatereplicate-llama-2-70b-chat, replicate-mistral-7b-instruct, replicate-mixtral-8x7b
AWS SageMakersagemaker-llama-3-1-70b, sagemaker-mistral-7b
Snowflakesnowflake-arctic-instruct, snowflake-llama-3-1-405b
Together AItogether-llama-2-70b-chat, together-wizardlm-70b, together-codellama-34b
Vertex AIvertex-gemini-2-0-flash, vertex-gemini-1-5-pro, vertex-claude-3-5-sonnet, vertex-llama3-1-405b
Voyage AIvoyage-large-2, voyage-code-2, voyage-lite-02-instruct

​
Using Models with Direct API Requests

​
Standard Request

// Standard request with Claude Sonnet 4.5
const response = await fetch('https://api.deepmyst.com/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': `Bearer YOUR_API_KEY`
  },
  body: JSON.stringify({
    model: 'claude-sonnet-4-5',
    messages: [
      { role: 'user', content: 'What are the benefits of token optimization?' }
    ]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

​
Optimized Request

// Using token optimization with GPT-5
const response = await fetch('https://api.deepmyst.com/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': `Bearer YOUR_API_KEY`
  },
  body: JSON.stringify({
    model: 'gpt-5-optimize', // Note the -optimize suffix
    messages: [
      { role: 'user', content: 'Explain quantum computing in simple terms.' }
    ]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

​
Streaming Request

// Streaming response with Gemini 2.5 Pro
const response = await fetch('https://api.deepmyst.com/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': `Bearer YOUR_API_KEY`
  },
  body: JSON.stringify({
    model: 'gemini-2.5-pro-optimize',
    messages: [
      { role: 'user', content: 'Write a short story about AI.' }
    ],
    stream: true
  })
});

// Process the stream
const reader = response.body.getReader();
const decoder = new TextDecoder('utf-8');

while (true) {
  const { done, value } = await reader.read();
  if (done) break;

  const chunk = decoder.decode(value);
  const lines = chunk.split('\n').filter(line => line.trim() !== '' && line.trim() !== 'data: [DONE]');

  for (const line of lines) {
    if (line.startsWith('data: ')) {
      const jsonStr = line.slice(6);

      try {
        const parsed = JSON.parse(jsonStr);
        const content = parsed.choices?.[0]?.delta?.content || '';
        if (content) process.stdout.write(content);
      } catch (e) {
        console.error('Error parsing chunk:', e);
      }
    }
  }
}

​
Using Models with OpenAI Library

You can use the OpenAI SDK with DeepMyst by simply changing the base URL. This allows you to leverage familiar OpenAI patterns while accessing all supported models.

​
Installation

npm install openai

​
Configuration

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.deepmyst.com/v1'
});

​
Standard Request

// Using Llama 4 Maverick through OpenAI SDK
async function generateResponse() {
  const completion = await openai.chat.completions.create({
    model: 'llama-4-maverick',
    messages: [
      { role: 'user', content: 'Compare and contrast different AI architectures.' }
    ]
  });

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

generateResponse();

​
Optimized Request

// Using Grok 4 with optimization
async function generateOptimizedResponse() {
  const completion = await openai.chat.completions.create({
    model: 'grok-4-optimize', // Note the -optimize suffix
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Explain how transformers work in machine learning.' }
    ]
  });

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

generateOptimizedResponse();

​
Streaming Request

// Streaming with OpenAI SDK using Claude Opus 4.5
async function generateStreamingResponse() {
  const stream = await openai.chat.completions.create({
    model: 'claude-opus-4-5-optimize',
    messages: [
      { role: 'user', content: 'Write a poem about artificial intelligence.' }
    ],
    stream: true
  });

  // Process the stream
  for await (const chunk of stream) {
    const content = chunk.choices[0]?.delta?.content || '';
    if (content) process.stdout.write(content);
  }
}

generateStreamingResponse();

​
Model Selection Guidance

  • Use -optimize suffix when token efficiency is important
  • Choose smaller models (mini, nano, flash variants) for faster responses and lower costs
  • Choose larger models (opus, pro variants) for more complex reasoning tasks
  • For high-throughput applications, consider models like llama-3.1-8b-instant or gemini-2.0-flash-lite
  • Consider using the router to automatically route to the best model