API Documentation

Quick Start

Get started with the HyndSyte AI API in minutes.

1. Get your API Key

2. Make your first request

curl https://www.hyndsyte.ai/api/v1/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ]
  }'

3. Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1706745600,
  "model": "gpt-4o",
  "choices": [{
    "index": 0,
    "message": {"role": "assistant", "content": "Hello! How can I help you today?"},
    "finish_reason": "stop"
  }],
  "usage": {"prompt_tokens": 20, "completion_tokens": 9, "total_tokens": 29}
}

Authentication

All API requests require authentication using your API key.

Bearer Token

Include your API key in the Authorization header:

Authorization: Bearer hyndsyte_xxxxxxxxxxxxxxxxxxxx

Python Example

import requests

response = requests.post(
    "https://www.hyndsyte.ai/api/v1/chat",
    headers={
        "Authorization": "Bearer hyndsyte_xxxxxxxxxxxxxxxxxxxx",
        "Content-Type": "application/json"
    },
    json={
        "model": "gpt-4o",
        "messages": [{"role": "user", "content": "Hello!"}]
    }
)
print(response.json())

JavaScript Example

const response = await fetch('https://www.hyndsyte.ai/api/v1/chat', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer hyndsyte_xxxxxxxxxxxxxxxxxxxx',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Hello!' }]
  })
});
const data = await response.json();

Chat Completions

Create chat completions with any of our 570+ supported models.

Endpoint

POST https://www.hyndsyte.ai/api/v1/chat

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (e.g., "gpt-4o", "claude-3-sonnet")
`messages`	array	Yes	Array of message objects with role and content
`max_tokens`	integer	No	Maximum tokens in response (default: 4096)
`temperature`	float	No	Sampling temperature 0-2 (default: 0.7)
`top_p`	float	No	Nucleus sampling 0-1 (default: 1)
`frequency_penalty`	float	No	Frequency penalty -2 to 2 (default: 0)
`presence_penalty`	float	No	Presence penalty -2 to 2 (default: 0)
`stream`	boolean	No	Stream responses (default: false)
`stop`	string/array	No	Stop sequences (up to 4)
`user`	string	No	Unique user identifier for abuse detection

Message Object

Each message in the messages array must have:

Field	Type	Description
`role`	string	"system", "user", or "assistant"
`content`	string	The message content
`name`	string	(Optional) Name of the participant

Complete Request Example

{
  "model": "gpt-4o",
  "messages": [
    {"role": "system", "content": "You are a helpful coding assistant."},
    {"role": "user", "content": "Write a Python function to calculate fibonacci numbers."}
  ],
  "max_tokens": 1000,
  "temperature": 0.7,
  "top_p": 1,
  "stream": false
}

Response Format

{
  "id": "chatcmpl-abc123xyz",
  "object": "chat.completion",
  "created": 1706745600,
  "model": "gpt-4o",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Here's a Python function for fibonacci..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 45,
    "completion_tokens": 120,
    "total_tokens": 165
  }
}

Switching Models

Simply change the model parameter to use any provider:

// OpenAI Models
{"model": "gpt-4o", "messages": [...]}
{"model": "gpt-4o-mini", "messages": [...]}
{"model": "gpt-4-turbo", "messages": [...]}
{"model": "o1", "messages": [...]}
{"model": "o3-mini", "messages": [...]}

// Anthropic Models
{"model": "claude-3-5-sonnet", "messages": [...]}
{"model": "claude-3-opus", "messages": [...]}
{"model": "claude-3-haiku", "messages": [...]}

// Google Models
{"model": "gemini-2.0-flash", "messages": [...]}
{"model": "gemini-1.5-pro", "messages": [...]}

// xAI Models
{"model": "grok-3", "messages": [...]}
{"model": "grok-3-mini", "messages": [...]}

// Free Models (no cost)
{"model": "llama-3.2-3b:free", "messages": [...]}
{"model": "qwen-2.5-7b:free", "messages": [...]}
{"model": "gemma-2-9b:free", "messages": [...]}
{"model": "phi-3-mini:free", "messages": [...]}

Image Generation

Generate images using DALL-E, Grok Aurora, and Gemini models.

Endpoint

POST https://www.hyndsyte.ai/api/v1/images

Request Parameters

Parameter	Type	Required	Description
`prompt`	string	Yes	Description of the image to generate
`model`	string	No	Model to use (default: "dall-e-3")
`size`	string	No	Image size: "1024x1024", "1792x1024", "1024x1792"
`quality`	string	No	"standard" or "hd" (DALL-E 3 only)
`style`	string	No	"vivid" or "natural" (DALL-E 3 only)
`n`	integer	No	Number of images (1-4, default: 1)

Supported Models

Model ID	Provider	Cost per Image
`dall-e-3`	OpenAI	~$0.06
`dall-e-2`	OpenAI	~$0.03
`grok-2-image`	xAI	~$0.05
`aurora`	xAI	~$0.05
`gemini-2.0-flash-exp`	Google	~$0.03

Example Request

curl -X POST https://www.hyndsyte.ai/api/v1/images \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A futuristic city skyline at sunset with flying cars",
    "model": "dall-e-3",
    "size": "1024x1024",
    "quality": "standard"
  }'

Response Format

{
  "created": 1706745600,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
    }
  ]
}

Python Example

import requests
import base64

response = requests.post(
    "https://www.hyndsyte.ai/api/v1/images",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "prompt": "A cute robot playing chess",
        "model": "dall-e-3"
    }
)

data = response.json()
image_data = base64.b64decode(data["data"][0]["b64_json"])
with open("generated_image.png", "wb") as f:
    f.write(image_data)

Web Search

Perform AI-powered web searches with real-time results and source citations.

Endpoint

POST https://www.hyndsyte.ai/api/v1/search

Request Parameters

Parameter	Type	Required	Description
`query`	string	Yes	The search query
`model`	string	No	Search model (default: "openai/gpt-4o-mini-search-preview")
`max_results`	integer	No	Maximum sources to return (1-20, default: 10)

Supported Search Models

Model ID	Provider	Description
`openai/gpt-4o-search-preview`	OpenAI	GPT-4o with web search
`openai/gpt-4o-mini-search-preview`	OpenAI	Faster, cheaper search
`perplexity/sonar`	Perplexity	Perplexity Sonar
`perplexity/sonar-pro`	Perplexity	Advanced search
`perplexity/sonar-deep-research`	Perplexity	Deep research mode

Example Request

curl -X POST https://www.hyndsyte.ai/api/v1/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What are the latest developments in AI in 2026?",
    "model": "openai/gpt-4o-mini-search-preview"
  }'

Response Format

{
  "id": "search-abc123",
  "object": "search.result",
  "created": 1706745600,
  "model": "openai/gpt-4o-mini-search-preview",
  "query": "What are the latest developments in AI in 2026?",
  "answer": "The latest developments in AI in 2026 include...",
  "sources": [
    {"title": "AI News Today", "url": "https://example.com/ai-news"},
    {"title": "Tech Review", "url": "https://example.com/tech-review"}
  ],
  "usage": {
    "prompt_tokens": 50,
    "completion_tokens": 200,
    "total_tokens": 250
  }
}

JavaScript Example

const response = await fetch('https://www.hyndsyte.ai/api/v1/search', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    query: 'Best programming languages to learn in 2026',
    model: 'perplexity/sonar'
  })
});

const data = await response.json();
console.log('Answer:', data.answer);
console.log('Sources:', data.sources);

Streaming Responses

Stream responses in real-time for a better user experience.

Enable Streaming

Set stream: true in your request:

{
  "model": "gpt-4o",
  "messages": [{"role": "user", "content": "Write a story"}],
  "stream": true
}

Stream Response Format

Responses are sent as Server-Sent Events (SSE):

data: {"id":"chatcmpl-123","choices":[{"delta":{"content":"Hello"}}]}

data: {"id":"chatcmpl-123","choices":[{"delta":{"content":" world"}}]}

data: {"id":"chatcmpl-123","choices":[{"delta":{"content":"!"}}]}

data: [DONE]

JavaScript Streaming Example

const response = await fetch('https://www.hyndsyte.ai/api/v1/chat', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Write a poem' }],
    stream: true
  })
});

const reader = response.body.getReader();
const decoder = new TextDecoder();

while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  
  const chunk = decoder.decode(value);
  const lines = chunk.split('\n').filter(line => line.startsWith('data: '));
  
  for (const line of lines) {
    const data = line.slice(6); // Remove 'data: ' prefix
    if (data === '[DONE]') break;
    
    const json = JSON.parse(data);
    const content = json.choices[0]?.delta?.content || '';
    process.stdout.write(content); // Or append to your UI
  }
}

Python Streaming Example

import requests
import json

response = requests.post(
    "https://www.hyndsyte.ai/api/v1/chat",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "gpt-4o",
        "messages": [{"role": "user", "content": "Write a poem"}],
        "stream": True
    },
    stream=True
)

for line in response.iter_lines():
    if line:
        line = line.decode('utf-8')
        if line.startswith('data: '):
            data = line[6:]
            if data == '[DONE]':
                break
            chunk = json.loads(data)
            content = chunk['choices'][0].get('delta', {}).get('content', '')
            print(content, end='', flush=True)

Available Models (570+)

Access models from 67 providers through a single API. Here are all available models organized by provider:

AI21

Model ID	Description	Context
`ai21/jamba-large-1.7`	Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with ...	256K
`ai21/jamba-mini-1.7`	Jamba Mini 1.7 is a compact and efficient member of the Jamba open model family, incorporating key improvements in grounding and instruction-following while maintaining the benefits of the SSM-Tran...	256K

Aion-labs

Model ID	Description	Context
`aion-labs/aion-1.0`	Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such...	131K
`aion-labs/aion-1.0-mini`	Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified vari...	131K
`aion-labs/aion-rp-llama-3.1-8b`	Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s respo...	33K

Alfredpros

Model ID	Description	Context
`alfredpros/codellama-7b-instruct-solidity`	A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.	4K

Alibaba

Model ID	Description	Context
`alibaba/tongyi-deepresearch-30b-a3b`	Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep informati...	131K

AllenAI

Model ID	Description	Context
`allenai/molmo-2-8b:free`	Molmo2-8B is an open vision-language model developed by the Allen Institute for AI (Ai2) as part of the Molmo2 family, supporting image, video, and multi-image understanding and grounding. It is ba...	37K
`allenai/olmo-2-0325-32b-instruct`	OLMo-2 32B Instruct is a supervised instruction-finetuned variant of the OLMo-2 32B March 2025 base model. It excels in complex reasoning and instruction-following tasks across diverse benchmarks s...	128K
`allenai/olmo-3-32b-think`	Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong perfor...	66K
`allenai/olmo-3-7b-instruct`	Olmo 3 7B Instruct is a supervised instruction-fine-tuned variant of the Olmo 3 7B base model, optimized for instruction-following, question-answering, and natural conversational dialogue. By lever...	66K
`allenai/olmo-3-7b-think`	Olmo 3 7B Think is a research-oriented language model in the Olmo family designed for advanced reasoning and instruction-driven tasks. It excels at multi-step problem solving, logical inference, an...	66K
`allenai/olmo-3.1-32b-instruct`	Olmo 3.1 32B Instruct is a large-scale, 32-billion-parameter instruction-tuned language model engineered for high-performance conversational AI, multi-turn dialogue, and practical instruction follo...	66K
`allenai/olmo-3.1-32b-think`	Olmo 3.1 32B Think is a large-scale, 32-billion-parameter model designed for deep reasoning, complex multi-step logic, and advanced instruction following. Building on the Olmo 3 series, version 3.1...	66K

Alpindale

Model ID	Description	Context
`alpindale/goliath-120b`	A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the ...	6K

Amazon

Model ID	Description	Context
`amazon/nova-2-lite-v1`	Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processi...	1.0M
`amazon/nova-lite-v1`	Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time ...	300K
`amazon/nova-micro-v1`	Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for ...	128K
`amazon/nova-premier-v1`	Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.	1.0M
`amazon/nova-pro-v1`	Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-th...	300K

Anthracite-org

Model ID	Description	Context
`anthracite-org/magnum-v4-72b`	This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anth...	16K

Anthropic (Claude)

Model ID	Description	Context
`anthropic/claude-3-haiku`	Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](http...	200K
`anthropic/claude-3.5-haiku`	Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential fo...	200K
`anthropic/claude-3.5-sonnet`	New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at: - Coding: Scores ~49% on SWE-Bench Verified, hig...	200K
`anthropic/claude-3.7-sonnet`	Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between ...	200K
`anthropic/claude-3.7-sonnet:thinking`	Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between ...	200K
`anthropic/claude-haiku-4.5`	Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s...	200K
`anthropic/claude-opus-4`	Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in sof...	200K
`anthropic/claude-opus-4.1`	Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notab...	200K
`anthropic/claude-opus-4.5`	Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, com...	200K
`anthropic/claude-sonnet-4`	Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-...	1.0M
`anthropic/claude-sonnet-4.5`	Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SW...	1.0M

Arcee AI

Model ID	Description	Context
`arcee-ai/coder-large`	Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports ...	33K
`arcee-ai/maestro-reasoning`	Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the e...	131K
`arcee-ai/spotlight`	Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context w...	131K
`arcee-ai/trinity-large-preview:free`	Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routi...	131K
`arcee-ai/trinity-mini`	Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with...	131K
`arcee-ai/trinity-mini:free`	Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with...	131K
`arcee-ai/virtuoso-large`	Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains...	131K

Baidu

Model ID	Description	Context
`baidu/ernie-4.5-21b-a3b`	A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heteroge...	120K
`baidu/ernie-4.5-21b-a3b-thinking`	ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generatio...	131K
`baidu/ernie-4.5-300b-a47b`	ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and supports text generatio...	123K
`baidu/ernie-4.5-vl-28b-a3b`	A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogen...	30K
`baidu/ernie-4.5-vl-424b-a47b`	ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and i...	123K

Bytedance

Model ID	Description	Context
`bytedance/ui-tars-1.5-7b`	UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the...	128K

ByteDance Seed

Model ID	Description	Context
`bytedance-seed/seed-1.6`	Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.	262K
`bytedance-seed/seed-1.6-flash`	Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of up to ...	262K

Cognitivecomputations

Model ID	Description	Context
`cognitivecomputations/dolphin-mistral-24b-venice-edition:free`	Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an �...	33K

Cohere

Model ID	Description	Context
`cohere/command-a`	Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading pr...	256K
`cohere/command-r-08-2024`	command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better ...	128K
`cohere/command-r-plus-08-2024`	command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, whi...	128K
`cohere/command-r7b-12-2024`	Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple ste...	128K

Deepcogito

Model ID	Description	Context
`deepcogito/cogito-v2-preview-llama-109b-moe`	An instruction-tuned, hybrid-reasoning Mixture-of-Experts model built on Llama-4-Scout-17B-16E. Cogito v2 can answer directly or engage an extended “thinking” phase, with alignment guided by It...	33K
`deepcogito/cogito-v2-preview-llama-405b`	Cogito v2 405B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. It represents a significant step toward frontier intelligence with dense ...	33K
`deepcogito/cogito-v2-preview-llama-70b`	Cogito v2 70B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. Built with iterative policy improvement, it delivers strong performance ac...	33K
`deepcogito/cogito-v2.1-671b`	Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...	128K

DeepSeek

Model ID	Description	Context
`deepseek/deepseek-chat`	DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported...	164K
`deepseek/deepseek-chat-v3-0324`	DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3)...	164K
`deepseek/deepseek-chat-v3.1`	DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-pha...	33K
`deepseek/deepseek-v3.1-terminus`	DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language c...	164K
`deepseek/deepseek-v3.1-terminus:exacto`	DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language c...	164K
`deepseek/deepseek-v3.2`	DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a ...	164K
`deepseek/deepseek-v3.2-exp`	DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-g...	164K
`deepseek/deepseek-v3.2-speciale`	DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context pr...	164K
`deepseek/deepseek-r1`	DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Ful...	64K
`deepseek/deepseek-r1-0528`	May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in ...	164K
`deepseek/deepseek-r1-0528:free`	May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in ...	164K
`deepseek/deepseek-r1-distill-llama-70b`	DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The...	131K
`deepseek/deepseek-r1-distill-qwen-32b`	DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outper...	33K

Eleutherai

Model ID	Description	Context
`eleutherai/llemma_7b`	Llemma 7B is a language model for mathematics. It was initialized with Code Llama 7B weights, and trained on the Proof-Pile-2 for 200B tokens. Llemma models are particularly strong at chain-of-thou...	4K

EssentialAI

Model ID	Description	Context
`essentialai/rnj-1-instruct`	Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates stro...	33K

Google (Gemini)

Model ID	Description	Context
`google/gemini-2.0-flash-001`	Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini ...	1.0M
`google/gemini-2.0-flash-lite-001`	Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Ge...	1.0M
`google/gemini-2.5-flash`	Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities,...	1.0M
`google/gemini-2.5-flash-image`	Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, an...	33K
`google/gemini-2.5-flash-lite`	Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and bet...	1.0M
`google/gemini-2.5-flash-lite-preview-09-2025`	Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and bet...	1.0M
`google/gemini-2.5-flash-preview-09-2025`	Gemini 2.5 Flash Preview September 2025 Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes...	1.0M
`google/gemini-2.5-pro`	Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason thro...	1.0M
`google/gemini-2.5-pro-preview-05-06`	Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason thro...	1.0M
`google/gemini-2.5-pro-preview`	Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason thro...	1.0M
`google/gemini-3-flash-preview`	Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performan...	1.0M
`google/gemini-3-pro-preview`	Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. R...	1.0M
`google/gemma-2-27b-it`	Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of text generati...	8K
`google/gemma-2-9b-it`	Gemma 2 9B by Google is an advanced, open-source language model that sets a new standard for efficiency and performance in its size class. Designed for a wide variety of tasks, it empowers develop...	8K
`google/gemma-3-12b-it`	Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasonin...	131K
`google/gemma-3-12b-it:free`	Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasonin...	33K
`google/gemma-3-27b-it`	Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasonin...	96K
`google/gemma-3-27b-it:free`	Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasonin...	131K
`google/gemma-3-4b-it`	Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasonin...	96K
`google/gemma-3-4b-it:free`	Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasonin...	33K
`google/gemma-3n-e2b-it:free`	Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, designed to operate efficiently at an effective parameter size of 2B while leveraging a 6B architecture. Based...	8K
`google/gemma-3n-e4b-it`	Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio...	33K
`google/gemma-3n-e4b-it:free`	Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio...	8K
`google/gemini-3-pro-image-preview`	Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-wor...	66K

Gryphe

Model ID	Description	Context
`gryphe/mythomax-l2-13b`	One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge	4K

Ibm-granite

Model ID	Description	Context
`ibm-granite/granite-4.0-h-micro`	Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long context tool calling.	131K

Inception

Model ID	Description	Context
`inception/mercury`	Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and C...	128K
`inception/mercury-coder`	Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 H...	128K

Inflection

Model ID	Description	Context
`inflection/inflection-3-pi`	Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like cu...	8K
`inflection/inflection-3-productivity`	Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news. For emoti...	8K

Kwaipilot

Model ID	Description	Context
`kwaipilot/kat-coder-pro`	KAT-Coder-Pro V1 is KwaiKAT's most advanced agentic coding model in the KAT-Coder series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, ach...	256K

LiquidAI

Model ID	Description	Context
`liquid/lfm-2.2-6b`	LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.	33K
`liquid/lfm2-8b-a1b`	LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only...	33K
`liquid/lfm-2.5-1.2b-instruct:free`	LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference...	33K
`liquid/lfm-2.5-1.2b-thinking:free`	LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up t...	33K

Mancer

Model ID	Description	Context
`mancer/weaver`	An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.	8K

Meituan

Model ID	Description	Context
`meituan/longcat-flash-chat`	LongCat-Flash-Chat is a large-scale Mixture-of-Experts (MoE) model with 560B total parameters, of which 18.6B–31.3B (≈27B on average) are dynamically activated per input. It introduces a shortc...	131K

Meta (Llama)

Model ID	Description	Context
`meta-llama/llama-guard-3-8b`	Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classific...	131K
`meta-llama/llama-3-70b-instruct`	Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong perf...	8K
`meta-llama/llama-3-8b-instruct`	Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong perfo...	8K
`meta-llama/llama-3.1-405b`	Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This is the base 405B pre-trained version. It has demonstrated strong performance compared to leading closed-so...	33K
`meta-llama/llama-3.1-405b-instruct`	The highly anticipated 400B class of Llama3 is here! Clocking in at 128k context with impressive eval scores, the Meta AI team continues to push the frontier of open-source LLMs. Meta's latest cla...	10K
`meta-llama/llama-3.1-405b-instruct:free`	The highly anticipated 400B class of Llama3 is here! Clocking in at 128k context with impressive eval scores, the Meta AI team continues to push the frontier of open-source LLMs. Meta's latest cla...	131K
`meta-llama/llama-3.1-70b-instruct`	Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong per...	131K
`meta-llama/llama-3.1-8b-instruct`	Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to leadin...	16K
`meta-llama/llama-3.2-11b-vision-instruct`	Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question an...	131K
`meta-llama/llama-3.2-1b-instruct`	Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allo...	60K
`meta-llama/llama-3.2-3b-instruct`	Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed wi...	131K
`meta-llama/llama-3.2-3b-instruct:free`	Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed wi...	131K
`meta-llama/llama-3.3-70b-instruct`	The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optim...	131K
`meta-llama/llama-3.3-70b-instruct:free`	The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optim...	131K
`meta-llama/llama-4-maverick`	Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per f...	1.0M
`meta-llama/llama-4-scout`	Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text a...	328K
`meta-llama/llama-guard-4-12b`	Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inpu...	164K
`meta-llama/llama-guard-2-8b`	This safeguard model has 8B parameters and is based on the Llama 3 family. Just like is predecessor, [LlamaGuard 1](https://huggingface.co/meta-llama/LlamaGuard-7b), it can do both prompt and respo...	8K

Microsoft

Model ID	Description	Context
`microsoft/phi-4`	[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At...	16K
`microsoft/wizardlm-2-8x22b`	WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing st...	66K

MiniMax

Model ID	Description	Context
`minimax/minimax-m1`	MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custo...	1.0M
`minimax/minimax-m2`	MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-front...	197K
`minimax/minimax-m2-her`	MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and persona...	66K
`minimax/minimax-m2.1`	MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it deliv...	197K
`minimax/minimax-01`	MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can ...	1.0M

Mistral

Model ID	Description	Context
`mistralai/mistral-large`	This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch ...	128K
`mistralai/mistral-large-2407`	This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch an...	131K
`mistralai/mistral-large-2411`	Mistral Large 2 2411 is an update of [Mistral Large 2](/mistralai/mistral-large) released together with [Pixtral Large 2411](/mistralai/pixtral-large-2411) It provides a significant upgrade on the...	131K
`mistralai/mistral-tiny`	Note: This model is being deprecated. Recommended replacement is the newer [Ministral 8B](/mistral/ministral-8b) This model is currently powered by Mistral-7B-v0.2, and incorporates a "better" fin...	33K
`mistralai/codestral-2508`	Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test gen...	256K
`mistralai/devstral-2512`	Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 support...	262K
`mistralai/devstral-medium`	Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on...	131K
`mistralai/devstral-small`	Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and re...	131K
`mistralai/ministral-14b-2512`	The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient langua...	262K
`mistralai/ministral-3b-2512`	The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.	131K
`mistralai/ministral-8b-2512`	A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.	262K
`mistralai/ministral-3b`	Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on ...	131K
`mistralai/ministral-8b`	Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k con...	131K
`mistralai/mistral-7b-instruct`	A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. *Mistral 7B Instruct has multiple version variants, and this is intended to be the lates...	33K
`mistralai/mistral-7b-instruct-v0.1`	A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.	3K
`mistralai/mistral-7b-instruct-v0.2`	A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. An improved version of [Mistral 7B Instruct](/modelsmistralai/mistral-7b-instruct-v0.1),...	33K
`mistralai/mistral-7b-instruct-v0.3`	A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. An improved version of [Mistral 7B Instruct v0.2](/models/mistralai/mistral-7b-instruct-...	33K
`mistralai/mistral-large-2512`	Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.	262K
`mistralai/mistral-medium-3`	Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reason...	131K
`mistralai/mistral-medium-3.1`	Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced op...	131K
`mistralai/mistral-nemo`	A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, C...	131K
`mistralai/mistral-small-24b-instruct-2501`	Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-t...	33K
`mistralai/mistral-small-3.1-24b-instruct`	Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in t...	131K
`mistralai/mistral-small-3.1-24b-instruct:free`	Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in t...	128K
`mistralai/mistral-small-3.2-24b-instruct`	Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 rele...	131K
`mistralai/mistral-small-creative`	Mistral Small Creative is an experimental small model designed for creative writing, narrative generation, roleplay and character-driven dialogue, general-purpose instruction following, and convers...	33K
`mistralai/mixtral-8x22b-instruct`	Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. It...	66K
`mistralai/mixtral-8x7b-instruct`	Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion par...	33K
`mistralai/pixtral-12b`	The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent: https://x.com/mistralai/status/1833758285167722836.	33K
`mistralai/pixtral-large-2411`	Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural imag...	131K
`mistralai/mistral-saba`	Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performa...	33K
`mistralai/voxtral-small-24b-2507`	Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, transl...	32K

MoonshotAI

Model ID	Description	Context
`moonshotai/kimi-dev-72b`	Kimi-Dev-72B is an open-source large language model fine-tuned for software engineering and issue resolution tasks. Based on Qwen2.5-72B, it is optimized using large-scale reinforcement learning th...	131K
`moonshotai/kimi-k2`	Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized fo...	131K
`moonshotai/kimi-k2:free`	Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized fo...	33K
`moonshotai/kimi-k2-0905`	Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total paramete...	262K
`moonshotai/kimi-k2-0905:exacto`	Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total paramete...	262K
`moonshotai/kimi-k2-thinking`	Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE...	262K
`moonshotai/kimi-k2.5`	Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over a...	262K

Morph

Model ID	Description	Context
`morph/morph-v3-fast`	Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruc...	82K
`morph/morph-v3-large`	Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instr...	262K

NeverSleep

Model ID	Description	Context
`neversleep/llama-3.1-lumimaid-8b`	Lumimaid v0.2 8B is a finetune of [Llama 3.1 8B](/models/meta-llama/llama-3.1-8b-instruct) with a "HUGE step up dataset wise" compared to Lumimaid v0.1. Sloppy chats output were purged. Usage of t...	33K
`neversleep/noromaid-20b`	A collab between IkariDev and Undi. This merge is suitable for RP, ERP, and general knowledge. #merge #uncensored	4K

Nex AGI

Model ID	Description	Context
`nex-agi/deepseek-v3.1-nex-n1`	DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent autonomy, tool use, and real-world productivity. Nex-N1 demonstrates competi...	131K

NousResearch

Model ID	Description	Context
`nousresearch/deephermes-3-mistral-24b-preview`	DeepHermes 3 (Mistral 24B Preview) is an instruction-tuned language model by Nous Research based on Mistral-Small-24B, designed for chat, function calling, and advanced multi-turn reasoning. It int...	33K
`nousresearch/hermes-3-llama-3.1-405b`	Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context cohe...	131K
`nousresearch/hermes-3-llama-3.1-405b:free`	Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context cohe...	131K
`nousresearch/hermes-3-llama-3.1-70b`	Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, ...	66K
`nousresearch/hermes-4-405b`	Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...	131K
`nousresearch/hermes-4-70b`	Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either respond directl...	131K
`nousresearch/hermes-2-pro-llama-3-8b`	Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON ...	8K

NVIDIA

Model ID	Description	Context
`nvidia/llama-3.1-nemotron-70b-instruct`	NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging [Llama 3.1 70B](/models/meta-llama/llama-3.1-70b-instruct) architecture and Rein...	131K
`nvidia/llama-3.1-nemotron-ultra-253b-v1`	Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from...	131K
`nvidia/llama-3.3-nemotron-super-49b-v1.5`	Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflow...	131K
`nvidia/nemotron-3-nano-30b-a3b`	NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-...	262K
`nvidia/nemotron-3-nano-30b-a3b:free`	NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-...	256K
`nvidia/nemotron-nano-12b-v2-vl`	NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture...	131K
`nvidia/nemotron-nano-12b-v2-vl:free`	NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture...	128K
`nvidia/nemotron-nano-9b-v2`	NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries an...	131K
`nvidia/nemotron-nano-9b-v2:free`	NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries an...	128K

Opengvlab

Model ID	Description	Context
`opengvlab/internvl3-78b`	The InternVL3 series is an advanced multimodal large language model (MLLM). Compared to InternVL 2.5, InternVL3 demonstrates stronger multimodal perception and reasoning capabilities. In addition...	33K

OpenRouter

Model ID	Description	Context
`openrouter/auto`	Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used, visit [Activity](/activity), ...	2.0M
`openrouter/bodybuilder`	Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API cal...	128K

Perplexity

Model ID	Description	Context
`perplexity/sonar`	Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-an...	127K
`perplexity/sonar-deep-research`	Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining i...	128K
`perplexity/sonar-pro`	Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enter...	200K
`perplexity/sonar-pro-search`	Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based ...	200K
`perplexity/sonar-reasoning-pro`	Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Rea...	128K

Prime-intellect

Model ID	Description	Context
`prime-intellect/intellect-3`	INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It o...	131K

Qwen

Model ID	Description	Context
`qwen/qwen-2.5-72b-instruct`	Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding...	33K
`qwen/qwen-2.5-coder-32b-instruct`	Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly impro...	33K
`qwen/qwq-32b`	QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance i...	33K
`qwen/qwen-plus-2025-07-28`	Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.	1.0M
`qwen/qwen-plus-2025-07-28:thinking`	Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.	1.0M
`qwen/qwen-vl-max`	Qwen VL Max is a visual understanding model with 7500 tokens context length. It excels in delivering optimal performance for a broader spectrum of complex tasks.	131K
`qwen/qwen-vl-plus`	Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up to millions of p...	8K
`qwen/qwen-max`	Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on ove...	33K
`qwen/qwen-plus`	Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.	131K
`qwen/qwen-turbo`	Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.	1.0M
`qwen/qwen-2.5-7b-instruct`	Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding ...	33K
`qwen/qwen2.5-coder-7b-instruct`	Qwen2.5-Coder-7B-Instruct is a 7B parameter instruction-tuned language model optimized for code-related tasks such as code generation, reasoning, and bug fixing. Based on the Qwen2.5 architecture, ...	33K
`qwen/qwen2.5-vl-32b-instruct`	Qwen2.5-VL-32B is a multimodal vision-language model fine-tuned through reinforcement learning for enhanced mathematical reasoning, structured outputs, and visual problem-solving capabilities. It e...	16K
`qwen/qwen2.5-vl-72b-instruct`	Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.	33K
`qwen/qwen-2.5-vl-7b-instruct`	Qwen2.5 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements: - SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art perform...	33K
`qwen/qwen-2.5-vl-7b-instruct:free`	Qwen2.5 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements: - SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art perform...	33K
`qwen/qwen3-14b`	Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mod...	41K
`qwen/qwen3-235b-a22b`	Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for comple...	41K
`qwen/qwen3-235b-a22b-2507`	Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimiz...	262K
`qwen/qwen3-235b-a22b-thinking-2507`	Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward p...	262K
`qwen/qwen3-30b-a3b`	Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent ...	41K
`qwen/qwen3-30b-a3b-instruct-2507`	Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-qu...	262K
`qwen/qwen3-30b-a3b-thinking-2507`	Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “think...	33K
`qwen/qwen3-32b`	Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mo...	41K
`qwen/qwen3-4b:free`	Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinki...	41K
`qwen/qwen3-8b`	Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mod...	32K
`qwen/qwen3-coder-30b-a3b-instruct`	Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding,...	160K
`qwen/qwen3-coder`	Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-...	262K
`qwen/qwen3-coder:exacto`	Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-...	262K
`qwen/qwen3-coder:free`	Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-...	262K
`qwen/qwen3-coder-flash`	Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling and...	128K
`qwen/qwen3-coder-plus`	Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and environme...	128K
`qwen/qwen3-max`	Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the Ja...	256K
`qwen/qwen3-next-80b-a3b-instruct`	Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning...	262K
`qwen/qwen3-next-80b-a3b-instruct:free`	Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning...	262K
`qwen/qwen3-next-80b-a3b-thinking`	Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proof...	128K
`qwen/qwen3-vl-235b-a22b-instruct`	Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-langu...	262K
`qwen/qwen3-vl-235b-a22b-thinking`	Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in ...	262K
`qwen/qwen3-vl-30b-a3b-instruct`	Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general...	262K
`qwen/qwen3-vl-30b-a3b-thinking`	Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and compl...	131K
`qwen/qwen3-vl-32b-instruct`	Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combin...	262K
`qwen/qwen3-vl-8b-instruct`	Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimo...	131K
`qwen/qwen3-vl-8b-thinking`	Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequen...	256K

Raifle

Model ID	Description	Context
`raifle/sorcererlm-8x22b`	SorcererLM is an advanced RP and storytelling model, built as a Low-rank 16-bit LoRA fine-tuned on [WizardLM-2 8x22B](/microsoft/wizardlm-2-8x22b). - Advanced reasoning and emotional intelligence ...	16K

Relace

Model ID	Description	Context
`relace/relace-apply-3`	Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 toke...	256K
`relace/relace-search`	The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic ...	256K

Sao10k

Model ID	Description	Context
`sao10k/l3-lunaris-8b`	Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge. Cr...	8K
`sao10k/l3.1-70b-hanami-x1`	This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).	16K
`sao10k/l3.1-euryale-70b`	Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).	33K
`sao10k/l3.3-euryale-70b`	Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).	131K
`sao10k/l3-euryale-70b`	Euryale 70B v2.1 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). - Better prompt adherence. - Better anatomy / spatial awareness. - Adapts much better to unique an...	8K

Stepfun-ai

Model ID	Description	Context
`stepfun-ai/step3`	Step3 is a cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while...	66K

Switchpoint

Model ID	Description	Context
`switchpoint/router`	Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensuring you always...	131K

Tencent

Model ID	Description	Context
`tencent/hunyuan-a13b-instruct`	Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers co...	131K

Thedrummer

Model ID	Description	Context
`thedrummer/cydonia-24b-v4.1`	Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.	131K
`thedrummer/rocinante-12b`	Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narra...	33K
`thedrummer/skyfall-36b-v2`	Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.	33K
`thedrummer/unslopnemo-12b`	UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.	33K

Tngtech

Model ID	Description	Context
`tngtech/deepseek-r1t-chimera`	DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE...	164K
`tngtech/deepseek-r1t-chimera:free`	DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE...	164K
`tngtech/deepseek-r1t2-chimera`	DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0...	164K
`tngtech/deepseek-r1t2-chimera:free`	DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0...	164K
`tngtech/tng-r1t-chimera`	TNG-R1T-Chimera is an experimental LLM with a faible for creative storytelling and character interaction. It is a derivate of the original TNG/DeepSeek-R1T-Chimera released in April 2025 and is ava...	164K
`tngtech/tng-r1t-chimera:free`	TNG-R1T-Chimera is an experimental LLM with a faible for creative storytelling and character interaction. It is a derivate of the original TNG/DeepSeek-R1T-Chimera released in April 2025 and is ava...	164K

Undi95

Model ID	Description	Context
`undi95/remm-slerp-l2-13b`	A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge	6K

Upstage

Model ID	Description	Context
`upstage/solar-pro-3:free`	Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaini...	128K

Writer

Model ID	Description	Context
`writer/palmyra-x5`	Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 mill...	1.0M

xAI (Grok)

Model ID	Description	Context
`x-ai/grok-3`	Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, ...	131K
`x-ai/grok-3-beta`	Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, ...	131K
`x-ai/grok-3-mini`	A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.	131K
`x-ai/grok-3-mini-beta`	Grok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-heavy tasks that ...	131K
`x-ai/grok-4`	Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoni...	256K
`x-ai/grok-4-fast`	Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news ...	2.0M
`x-ai/grok-4.1-fast`	Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window. Reasoning can be enabled/disabled using the `...	2.0M
`x-ai/grok-code-fast-1`	Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality work flows.	256K

Xiaomi

Model ID	Description	Context
`xiaomi/mimo-v2-flash`	MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention archi...	262K

Z.AI

Model ID	Description	Context
`z-ai/glm-4-32b`	GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intellige...	128K
`z-ai/glm-4.5`	GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens....	131K
`z-ai/glm-4.5-air`	GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but ...	131K
`z-ai/glm-4.5-air:free`	GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but ...	131K
`z-ai/glm-4.5v`	GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves sta...	66K
`z-ai/glm-4.6`	Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more comp...	203K
`z-ai/glm-4.6:exacto`	Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more comp...	205K
`z-ai/glm-4.6v`	GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes c...	131K
`z-ai/glm-4.7`	GLM-4.7 is Z.AI’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improve...	203K
`z-ai/glm-4.7-flash`	As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-...	200K

Free Models (Available at No Cost)

These models have no usage cost - perfect for testing and development:

Model ID	Provider	Description
`allenai/molmo-2-8b:free`	AllenAI	Molmo2-8B is an open vision-language model developed by the Allen Institute for AI (Ai2) as part of the Molmo2 family, supporting image, video, and multi-image understanding and grounding. It is ba...
`arcee-ai/trinity-large-preview:free`	Arcee AI	Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routi...
`arcee-ai/trinity-mini:free`	Arcee AI	Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with...
`cognitivecomputations/dolphin-mistral-24b-venice-edition:free`	Cognitivecomputations	Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an �...
`deepseek/deepseek-r1-0528:free`	DeepSeek	May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in ...
`google/gemma-3-12b-it:free`	Google (Gemini)	Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasonin...
`google/gemma-3-27b-it:free`	Google (Gemini)	Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasonin...
`google/gemma-3-4b-it:free`	Google (Gemini)	Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasonin...
`google/gemma-3n-e2b-it:free`	Google (Gemini)	Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, designed to operate efficiently at an effective parameter size of 2B while leveraging a 6B architecture. Based...
`google/gemma-3n-e4b-it:free`	Google (Gemini)	Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio...
`liquid/lfm-2.5-1.2b-instruct:free`	LiquidAI	LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference...
`liquid/lfm-2.5-1.2b-thinking:free`	LiquidAI	LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up t...
`meta-llama/llama-3.1-405b-instruct:free`	Meta (Llama)	The highly anticipated 400B class of Llama3 is here! Clocking in at 128k context with impressive eval scores, the Meta AI team continues to push the frontier of open-source LLMs. Meta's latest cla...
`meta-llama/llama-3.2-3b-instruct:free`	Meta (Llama)	Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed wi...
`meta-llama/llama-3.3-70b-instruct:free`	Meta (Llama)	The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optim...
`mistralai/mistral-small-3.1-24b-instruct:free`	Mistral	Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in t...
`moonshotai/kimi-k2:free`	MoonshotAI	Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized fo...
`nousresearch/hermes-3-llama-3.1-405b:free`	NousResearch	Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context cohe...
`nvidia/nemotron-3-nano-30b-a3b:free`	NVIDIA	NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-...
`nvidia/nemotron-nano-12b-v2-vl:free`	NVIDIA	NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture...
`nvidia/nemotron-nano-9b-v2:free`	NVIDIA	NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries an...
`qwen/qwen-2.5-vl-7b-instruct:free`	Qwen	Qwen2.5 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements: - SoTA understanding of images of various resolution & ratio: Qwen2.5-VL achieves state-of-the-art perform...
`qwen/qwen3-4b:free`	Qwen	Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinki...
`qwen/qwen3-coder:free`	Qwen	Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-...
`qwen/qwen3-next-80b-a3b-instruct:free`	Qwen	Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning...
`tngtech/deepseek-r1t-chimera:free`	Tngtech	DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE...
`tngtech/deepseek-r1t2-chimera:free`	Tngtech	DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0...
`tngtech/tng-r1t-chimera:free`	Tngtech	TNG-R1T-Chimera is an experimental LLM with a faible for creative storytelling and character interaction. It is a derivate of the original TNG/DeepSeek-R1T-Chimera released in April 2025 and is ava...
`upstage/solar-pro-3:free`	Upstage	Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaini...
`z-ai/glm-4.5-air:free`	Z.AI	GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but ...

View complete pricing details on the Pricing page.

SDKs & Code Examples

Use our API with any language. Here are complete examples:

Python

import requests

API_KEY = "hyndsyte_xxxxxxxxxxxxxxxxxxxx"
BASE_URL = "https://www.hyndsyte.ai/api/v1"

def chat(messages, model="gpt-4o", max_tokens=4096, temperature=0.7):
    response = requests.post(
        f"{BASE_URL}/chat",
        headers={
            "Authorization": f"Bearer {API_KEY}",
            "Content-Type": "application/json"
        },
        json={
            "model": model,
            "messages": messages,
            "max_tokens": max_tokens,
            "temperature": temperature
        }
    )
    return response.json()

# Example usage
result = chat([
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is the capital of France?"}
])
print(result["choices"][0]["message"]["content"])

JavaScript / Node.js

const API_KEY = 'hyndsyte_xxxxxxxxxxxxxxxxxxxx';
const BASE_URL = 'https://www.hyndsyte.ai/api/v1';

async function chat(messages, model = 'gpt-4o', maxTokens = 4096, temperature = 0.7) {
  const response = await fetch(`${BASE_URL}/chat`, {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${API_KEY}`,
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      model,
      messages,
      max_tokens: maxTokens,
      temperature
    })
  });
  return response.json();
}

// Example usage
const result = await chat([
  { role: 'system', content: 'You are a helpful assistant.' },
  { role: 'user', content: 'What is the capital of France?' }
]);
console.log(result.choices[0].message.content);

cURL

curl -X POST https://www.hyndsyte.ai/api/v1/chat \
  -H "Authorization: Bearer hyndsyte_xxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "max_tokens": 4096,
    "temperature": 0.7
  }'

PHP

<?php
$apiKey = 'hyndsyte_xxxxxxxxxxxxxxxxxxxx';
$baseUrl = 'https://www.hyndsyte.ai/api/v1';

function chat($messages, $model = 'gpt-4o', $maxTokens = 4096, $temperature = 0.7) {
    global $apiKey, $baseUrl;
    
    $ch = curl_init("$baseUrl/chat");
    curl_setopt_array($ch, [
        CURLOPT_RETURNTRANSFER => true,
        CURLOPT_POST => true,
        CURLOPT_HTTPHEADER => [
            "Authorization: Bearer $apiKey",
            "Content-Type: application/json"
        ],
        CURLOPT_POSTFIELDS => json_encode([
            'model' => $model,
            'messages' => $messages,
            'max_tokens' => $maxTokens,
            'temperature' => $temperature
        ])
    ]);
    
    $response = curl_exec($ch);
    curl_close($ch);
    return json_decode($response, true);
}

// Example usage
$result = chat([
    ['role' => 'system', 'content' => 'You are a helpful assistant.'],
    ['role' => 'user', 'content' => 'What is the capital of France?']
]);
echo $result['choices'][0]['message']['content'];
?>

Ruby

require 'net/http'
require 'json'

API_KEY = 'hyndsyte_xxxxxxxxxxxxxxxxxxxx'
BASE_URL = 'https://www.hyndsyte.ai/api/v1'

def chat(messages, model: 'gpt-4o', max_tokens: 4096, temperature: 0.7)
  uri = URI("#{BASE_URL}/chat")
  http = Net::HTTP.new(uri.host, uri.port)
  http.use_ssl = true
  
  request = Net::HTTP::Post.new(uri)
  request['Authorization'] = "Bearer #{API_KEY}"
  request['Content-Type'] = 'application/json'
  request.body = {
    model: model,
    messages: messages,
    max_tokens: max_tokens,
    temperature: temperature
  }.to_json
  
  response = http.request(request)
  JSON.parse(response.body)
end

# Example usage
result = chat([
  { role: 'system', content: 'You are a helpful assistant.' },
  { role: 'user', content: 'What is the capital of France?' }
])
puts result['choices'][0]['message']['content']

Go

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

const (
    apiKey  = "hyndsyte_xxxxxxxxxxxxxxxxxxxx"
    baseURL = "https://www.hyndsyte.ai/api/v1"
)

type Message struct {
    Role    string `json:"role"`
    Content string `json:"content"`
}

type ChatRequest struct {
    Model       string    `json:"model"`
    Messages    []Message `json:"messages"`
    MaxTokens   int       `json:"max_tokens"`
    Temperature float64   `json:"temperature"`
}

func chat(messages []Message, model string) (map[string]interface{}, error) {
    reqBody, _ := json.Marshal(ChatRequest{
        Model:       model,
        Messages:    messages,
        MaxTokens:   4096,
        Temperature: 0.7,
    })
    
    req, _ := http.NewRequest("POST", baseURL+"/chat", bytes.NewBuffer(reqBody))
    req.Header.Set("Authorization", "Bearer "+apiKey)
    req.Header.Set("Content-Type", "application/json")
    
    client := &http.Client{}
    resp, err := client.Do(req)
    if err != nil {
        return nil, err
    }
    defer resp.Body.Close()
    
    body, _ := io.ReadAll(resp.Body)
    var result map[string]interface{}
    json.Unmarshal(body, &result)
    return result, nil
}

func main() {
    result, _ := chat([]Message{
        {Role: "system", Content: "You are a helpful assistant."},
        {Role: "user", Content: "What is the capital of France?"},
    }, "gpt-4o")
    
    choices := result["choices"].([]interface{})
    message := choices[0].(map[string]interface{})["message"].(map[string]interface{})
    fmt.Println(message["content"])
}

Rate Limits & Best Practices

Rate Limits

Limit Type	Value	Description
Requests per minute	60	Maximum API calls per minute per key
Requests per day	10,000	Maximum API calls per day per key
Tokens per minute	100,000	Maximum tokens processed per minute
Concurrent requests	10	Maximum simultaneous requests

Rate Limit Headers

Check these response headers to monitor your usage:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 45
X-RateLimit-Reset: 1706745660

Handling Rate Limits

When rate limited, you'll receive a 429 response. Implement exponential backoff:

async function chatWithRetry(messages, maxRetries = 3) {
  for (let i = 0; i < maxRetries; i++) {
    const response = await fetch(API_URL, { /* ... */ });
    
    if (response.status === 429) {
      const retryAfter = response.headers.get('Retry-After') || Math.pow(2, i);
      console.log(`Rate limited. Retrying in ${retryAfter}s...`);
      await new Promise(r => setTimeout(r, retryAfter * 1000));
      continue;
    }
    
    return response.json();
  }
  throw new Error('Max retries exceeded');
}

Best Practices

Use streaming for long responses to improve perceived latency
Cache responses when appropriate to reduce API calls
Batch requests when possible instead of many small calls
Set reasonable max_tokens to avoid unnecessary costs
Use system prompts to guide model behavior consistently
Monitor your usage in the dashboard to avoid surprises
Use free models for testing and development
Implement retries with exponential backoff for reliability

Cost Optimization Tips

Use gpt-4o-mini instead of gpt-4o when possible (10x cheaper)
Use free models like llama-3.2-3b:free for simple tasks
Keep system prompts concise - they count toward input tokens
Truncate conversation history to only include relevant context
Use lower max_tokens when you expect short responses

Error Handling

Code	Description
400	Bad Request - Invalid parameters
401	Unauthorized - Invalid or missing API key
402	Payment Required - Insufficient balance
429	Rate Limited - Too many requests
500	Server Error - Try again later

Error Response Format

{
  "error": {
    "code": "insufficient_balance",
    "message": "Your account balance is too low. Please add funds.",
    "type": "payment_error"
  }
}