Models — Directories · Directories by Enterprise DNA

Cheap Indexed

Llama 3.1 70B Dracarys 2

Abacusai

Open Llama instruction model for multilingual chat, reasoning, and coding

$0.493 / Mtok in 16,384 ctx closed

Context Indexed

dracarys-llama-3.1-70b-instruct

Abacusai

Open Llama instruction model for multilingual chat, reasoning, and coding

$0 / Mtok in 128,000 ctx open-weights

Context Indexed

DeepSeek V4 Pro

Accounts

Open MoE flagship with million-token context for coding and long agent runs

$1.74 / Mtok in 1,000,000 ctx open-weights

Context Indexed

GLM 5.1

Accounts

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

$1.40 / Mtok in 202,800 ctx open-weights

Context Indexed

GLM 5.2

Accounts

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

$1.40 / Mtok in 1,048,575 ctx open-weights

Context Indexed

GPT OSS 120B

Accounts

Kimi coding model for software agents, refactors, and repository reasoning

$1.90 / Mtok in 262,000 ctx open-weights

Context Indexed

Jamba Large 1.7

Ai21

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 a

$2.00 / Mtok in 256,000 ctx open-weights

Context Indexed

Alibaba

Video model for prompt-guided generation, editing, and motion workflows

$0 / Mtok in 1 ctx closed

Cheap Indexed

A

Olmo 3 32B Think

Allenai

Amazon

Flagship model for demanding analysis, coding, and production agent workflows

$0.800 / Mtok in 300,000 ctx closed

Reason Indexed

A

Anthracite Org

Anthropic

Fast Claude model for responsive assistance, classification, and lightweight agents

$0.210 / Mtok in 189,096 ctx closed

Cheap

Claude Haiku 4.5

Anthropic

Claude Opus 4

Anthropic

Claude Sonnet 4.6 Thinking

Anthropic

Balanced Claude model for coding, analysis, agent workflows, and cost control

$2.99 / Mtok in 1,000,000 ctx closed

Coding

Claude Sonnet 4

Anthropic

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. Ac

$3.00 / Mtok in 1,000,000 ctx closed

Best for: Production coding agents and long-context document work that need vision

Vision Indexed

Claude Sonnet 5 (Free)

Anthropic

Everyday Claude agent model for coding, planning, browsing, and general work

$0 / Mtok in 1,000,000 ctx closed

Vision Indexed

Claude Sonnet 4.6

Anthropic

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex c

$3.00 / Mtok in 1,000,000 ctx closed

Vision Indexed

Baichuan

Baidu

OCR model for extracting structured text from documents and screenshots

$0.680 / Mtok in 65,536 ctx closed

Context Indexed

Kimi K2 0711 Instruct FP4

Baseten

Black Forest Labs

Image model for prompt-driven generation, editing, and visual design workflows

$1.00 / Mtok in 128,000 ctx open-weights

Vision Indexed

Seed 1.6

Bytedance

Multimodal reasoning model for visual analysis, planning, and tool use

$0.250 / Mtok in 256,000 ctx closed

Context Indexed

Canopy Labs Orpheus Arabic Saudi

Canopylabs

Speech generation model for controllable voice, narration, and audio delivery

$0 / Mtok in 4,000 ctx closed

Vision Indexed

UI-TARS 7B

Bytedance

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, i

$0.100 / Mtok in 128,000 ctx open-weights

Indexed

C

Canopy Labs Orpheus V1 English

Canopylabs

Speech generation model for controllable voice, narration, and audio delivery

$0 / Mtok in 4,000 ctx closed

Vision Indexed

GPT-OSS-120B-CS

Cerebras

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

$0.350 / Mtok in 128,000 ctx closed

Vision Indexed

Cerebras

Legacy model retained for compatibility with older integrations

$0 / Mtok in 1 ctx closed

Context Indexed

Gemma Sea Lion V4 27B It

Cf

Open Gemma instruction model for efficient chat and self-hosted deployments

$0.351 / Mtok in 128,000 ctx open-weights

Reason Indexed

Deepseek R1 Distill Qwen 32B

Cf

Classic open reasoning model for transparent math, coding, and deliberate problem solving

$0.497 / Mtok in 80,000 ctx open-weights

Vision Indexed

Gemma 4 26B A4B IT

Cf

Cf

Safety model for policy screening, moderation, and risk-aware routing workflows

$0.484 / Mtok in 131,072 ctx open-weights

Context Indexed

Mistral Small 3.1 24B Instruct

Cf

Efficient Mistral model for fast chat, extraction, and production assistants

$0.351 / Mtok in 128,000 ctx open-weights

Vision Indexed

Kimi K2.6

Cf

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

$0.950 / Mtok in 262,144 ctx open-weights

Vision Indexed

Kimi K2.7 Code

Cf

Cohere

JAIS 30b Chat

Core42

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

$0 / Mtok in 8,192 ctx open-weights

Context Indexed

Llama 3.3 70B

Cortecs

Open Llama instruction model for multilingual chat, reasoning, and coding

$0.530 / Mtok in 128,000 ctx open-weights

Context Indexed

Cogito v1 Preview Qwen 32B

Deepcogito

R1

DeepSeek

RNJ-1 Instruct 8B

Essentialai

General-purpose chat model for instruction following, writing, and analysis

$0.150 / Mtok in 128,000 ctx closed

Indexed

Evroc

Multimodal reasoning model for visual analysis, planning, and tool use

$2.88 / Mtok in 262,144 ctx closed

Indexed

Llama 3 70B abliterated

Failspy

Open Llama instruction model for multilingual chat, reasoning, and coding

$0.700 / Mtok in 8,192 ctx closed

Indexed

F

ElevenLabs Multilingual TTS v2

Fal Ai

Speech generation model for controllable voice, narration, and audio delivery

$0 / Mtok in 1 ctx closed

Indexed

F

Featherless Ai

General-purpose chat model for instruction following, writing, and analysis

$0.500 / Mtok in 32,000 ctx closed

Vision Indexed

Kimi-K2.5-FW

Fireworks Ai

Gemini 2.5 Flash

Google

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 "thinki

$0.300 / Mtok in 1,048,576 ctx closed

Best for: High-throughput multimodal and extraction jobs

Vision Indexed

Gemini 2.5 Pro Preview 05-06

Google

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

$1.25 / Mtok in 1,048,576 ctx closed

Vision Indexed

Gemini 2.5 Pro Preview 06-05

Google

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

$1.25 / Mtok in 1,048,576 ctx closed

Reason

Gemini 2.5 Pro

Google

Grok 4.3

Grok

xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk

$1.25 / Mtok in 1,000,000 ctx closed

Context Indexed

G

Compound Mini

Groq

Efficient model for low-latency assistance, extraction, and routine automation

$0 / Mtok in 131,072 ctx closed

Context Indexed

G

Compound

Groq

Qwen3.6 27B

Hf Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

$0.450 / Mtok in 262,144 ctx open-weights

Context Indexed

GLM-4.7-Flash

Hf Zai Org

Budget GLM lane for fast coding help, routing, and everyday automation

$0.100 / Mtok in 196,608 ctx open-weights

Context Indexed

GLM-5.2

Hf Zai Org

Open flagship GLM for long-horizon coding agents and million-token context work

$1.40 / Mtok in 524,288 ctx open-weights

Reason Indexed

H

SmolLM3 3B Base

Huggingfacetb

Tool-capable chat model for instruction following and agentic application workflows

$0.150 / Mtok in 32,768 ctx closed

Reason Indexed

DeepSeek R1 Llama 70B Abliterated

Huihui Ai

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

$0.700 / Mtok in 16,384 ctx closed

Indexed

Inclusionai

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency.

$0.075 / Mtok in 262,144 ctx closed

Cheap Indexed

Mistral Nemo Inferor 12B

Infermatic

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

$0.255 / Mtok in 16,384 ctx closed

Cheap Indexed

I

Mag Mell R1

Inflatebot

Intfloat

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

$0.114 / Mtok in 512 ctx open-weights

Context Indexed

J

Mellum2 12B A2.5B

Jetbrains

Mellum2-12B-A2.5B-Instruct is a fast MoE model with 131K context built for coding, tool use, and low-latency AI workflows.

$0.050 / Mtok in 131,072 ctx open-weights

Audio Indexed

KB Whisper

Kblab

Speech transcription model for accurate audio-to-text and captioning workflows

$0.0023 / Mtok in 448 ctx open-weights

Context Indexed

K

Kilo Auto Balanced

Kilo Auto

Automatic model router for matching prompts to suitable backends and budgets

$0.600 / Mtok in 204,800 ctx closed

Context Indexed

K

Kilo Auto Free

Kilo Auto

Automatic model router for matching prompts to suitable backends and budgets

$0 / Mtok in 204,800 ctx closed

Vision Indexed

K

Kilo Auto Frontier

Kilo Auto

Automatic model router for matching prompts to suitable backends and budgets

$5.00 / Mtok in 1,000,000 ctx closed

Vision Indexed

K

Kilo Auto Small

Kilo Auto

Automatic model router for matching prompts to suitable backends and budgets

$0.050 / Mtok in 400,000 ctx closed

Vision Indexed

Kwaipilot

Coding model for repository understanding, refactors, and agentic engineering tasks

$0.740 / Mtok in 262,144 ctx closed

Context Indexed

K

Meta

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

$0.200 / Mtok in 1,048,576 ctx open-weights

Best for: Teams that want open-weight flexibility with hosted convenience

Vision Indexed

Llama 4 Scout 17B 16E

Meta

Open multimodal Llama model for long-context analysis and efficient agents

$0.110 / Mtok in 131,072 ctx open-weights

Cheap

Llama 4 Scout

Meta

Meta

Mistral

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 Apa

$0.500 / Mtok in 262,144 ctx open-weights

Coding

Mistral Large

Mistral

Mistral

Mistral

Nousresearch

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

$0.300 / Mtok in 128,000 ctx closed

Cheap Indexed

Hermes 2 Pro Llama 3 8B

Nousresearch

OpenAI

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is m

$0.150 / Mtok in 128,000 ctx closed

Best for: Cost-efficient product features and multimodal volume

Context Indexed

GPT-4o Search Preview

OpenAI

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

$2.50 / Mtok in 128,000 ctx closed

Audio Indexed

GPT-4o Transcribe

OpenAI

Speech transcription model for accurate audio-to-text and captioning workflows

$2.50 / Mtok in 1 ctx closed

Coding

GPT-4o

OpenAI

Paddlepaddle

Multimodal model for analyzing text, images, documents, and rich media

$0.020 / Mtok in 16,384 ctx open-weights

Vision Indexed

P

PaddlePaddle/PaddleOCR-VL-1.5

Paddlepaddle

Multimodal model for analyzing text, images, documents, and rich media

$0 / Mtok in 16,384 ctx open-weights

Reason Indexed

OpenReasoning Nemotron 32B

Pamanseau

Nemotron model for efficient reasoning, coding, and specialized AI agents

$0.100 / Mtok in 32,768 ctx closed

Reason Indexed

Pearl AI Gemma 4 31B Instruct

Pearl Ai

Open Gemma instruction model for efficient chat and self-hosted deployments

$0.280 / Mtok in 32,000 ctx closed

Vision Indexed

P

Perceptron Mk1

Perceptron

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language q

$0.150 / Mtok in 32,768 ctx closed

Context Indexed

Sonar Deep Research

Perplexity

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 so

$2.00 / Mtok in 128,000 ctx closed

Vision Indexed

Sonar Pro

Perplexity

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-sona

$3.00 / Mtok in 200,000 ctx closed

Vision Indexed

Sonar Pro Search

Perplexity

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.

$3.00 / Mtok in 200,000 ctx closed

Vision Indexed

Sonar Reasoning Pro

Perplexity

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-sona

$2.00 / Mtok in 128,000 ctx closed

Vision Indexed

Sonar

Perplexity

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 lightwei

$1.00 / Mtok in 127,072 ctx closed

Vision Indexed

P

Prime Intellect

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

$0.200 / Mtok in 131,072 ctx open-weights

Context Indexed

Pro/deepseek-ai/DeepSeek-R1

Pro

Qwen

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, to

$0.300 / Mtok in 262,144 ctx open-weights

Best for: Dedicated coding agents on a budget

Cheap Indexed

Qwen3 Embedding 0.6B

Qwen

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

$0.010 / Mtok in 40,960 ctx open-weights

Cheap Indexed

Qwen 3 Embedding 4B

Qwen

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

$0.010 / Mtok in 32,000 ctx open-weights

Cheap Indexed

Qwen3-Embedding-8B

Qwen

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

$0.010 / Mtok in 32,768 ctx open-weights

Reason

Qwen3 Max

Qwen

Runwayml

Sao10k

Open Llama instruction model for multilingual chat, reasoning, and coding

$0.050 / Mtok in 8,192 ctx open-weights

Indexed

Sarvam

Siliconflow

DeepSeek chat model for instruction following, coding, and analysis

$0.270 / Mtok in 163,840 ctx closed

Cheap Indexed

S

Speakleash

Open-weight instruction model for adaptable chat and self-hosted production workloads

$0.670 / Mtok in 32,000 ctx open-weights

Vision Indexed

Stealth: Claude Opus 4.7 (20% off)

Stealth

Flagship Claude model for deep reasoning, coding, and long-horizon agents

$4.00 / Mtok in 1,000,000 ctx closed

Vision Indexed

Stealth: Claude Sonnet 4.6 (20% off)

Stealth

Balanced Claude model for coding, analysis, agent workflows, and cost control

$2.40 / Mtok in 1,000,000 ctx closed

Vision Indexed

Steelskull

Open Llama instruction model for multilingual chat, reasoning, and coding

$0.493 / Mtok in 16,384 ctx closed

Vision Indexed

Stepfun-Ai/Gelab Zero 4b Preview

Stepfun Ai

StepFun flash model for efficient multimodal reasoning, coding, and tool use

$0 / Mtok in 8,192 ctx closed

Context Indexed

S

Step 3.5 Flash 2603

Stepfun Ai

StepFun flash model for efficient multimodal reasoning, coding, and tool use

$0.100 / Mtok in 256,000 ctx closed

Context Indexed

stepfun-ai/Step-3.5-Flash

Stepfun Ai

TIM-Qwen3.6 27B

Subconscious

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

$0.300 / Mtok in 8,192 ctx closed

Context Indexed

GLM-5.2

Subconscious

Tee

Multimodal reasoning model for visual analysis, planning, and tool use

$0.300 / Mtok in 131,072 ctx closed

Context Indexed

Hunyuan A13B Instruct

Tencent

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-Thou

$0.140 / Mtok in 131,072 ctx open-weights

Indexed

Hunyuan MT 7B

Tencent

Translation model for multilingual conversion, localization, and cross-language workflows

$10.00 / Mtok in 8,192 ctx closed

Context Indexed

Hy3 (free)

Tencent

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It

$0 / Mtok in 262,144 ctx open-weights

Context Indexed

Thinkingmachines

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning

$1.00 / Mtok in 1,048,576 ctx open-weights

Cheap Indexed

GLM 4 9B 0414

Thudm

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

$0.200 / Mtok in 32,000 ctx closed

Context Indexed

GLM 4 32B 0414

Thudm

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

$0.200 / Mtok in 128,000 ctx closed

Cheap Indexed

solar-10.7b-instruct

Upstage

Open-weight instruction model for adaptable chat and self-hosted production workloads

$0 / Mtok in 128,000 ctx open-weights

Vision Indexed

Doubao-Seed-1.8

Volcengine

Xiaomimimo

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

$1.00 / Mtok in 1,048,576 ctx open-weights

Vision Indexed

X

MiMo-V2.5

Xiaomimimo

Open MiMo model for multimodal coding agents and long-context automation

$0.400 / Mtok in 262,144 ctx open-weights

Vision Indexed

Z-Ai/Autoglm Phone 9b

Z Ai

GLM vision model for visual reasoning, documents, and multimodal agents

$0 / Mtok in 12,800 ctx closed

Context Indexed

X

MiMo-V2-Flash

Xiaomimimo

DeepSeek

Granite 4.2 8B

Ibm Granite

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It s

$0.060 / Mtok in 131,072 ctx open-weights

Context Indexed

I

Mercury 2.5 Preview

Inception

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple t

$0.040 / Mtok in 260,000 ctx closed

Context Indexed

I

Ling 3.0 Flash Fin (free)

Inclusionai

Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-wo

$0 / Mtok in 262,144 ctx closed

Context Indexed

I

Ling 3.0 Flash

Inclusionai

Laguna S 2.1 (free)

Poolside

Qwen

Ling 3.0 Flash Fin

Inclusionai

Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-wo

$0.060 / Mtok in 262,144 ctx closed

Vision Indexed

Nemotron 3.5 Content Safety

NVIDIA

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses fr

$0.200 / Mtok in 131,072 ctx open-weights

Vision Indexed

Grok 4.3 (batch)

xAI

Mercury 2.5

Inception

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple t

$0.040 / Mtok in 260,000 ctx closed

Vision Indexed

N

Nex-N2.5-Mini (free)

Nex Agi

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, imple

$0 / Mtok in 262,144 ctx open-weights

Vision Indexed

N

Nex-N2.5-Pro (free)

Nex Agi

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, imple

$0 / Mtok in 262,144 ctx open-weights