MODEL DIRECTORY
AI Model Directory
Context length, max output, modalities, reasoning support and official API pricing for Claude, GPT, Gemini, DeepSeek, Qwen and other major AI models, alongside the lowest AI gateway price. Updated continuously.
618Models
77Providers
140Relay sites
Updated 2026-11-08 08:15 (UTC+8)618 models foundPrices in USD per 1M tokens; relay prices and ≈ are converted from CNY at today's rate
| Model | Provider | Type | Relays | Context | Max output | Input | Output | Capabilities | Price (input / output) | Details | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
Laguna XS.2laguna-xs.2 | Poolside | Text | - | 262.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-28 | |
Agentic coding model from Poolside in the XS size class for local deployment Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Nemotron 3 Nano Omni 30B A3B Reasoningnemotron-3-nano-omni-30b-a3b-reasoning | Nvidia | Text | - | 256K | 65.5K | Text: SupportedImage: SupportedAudio: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-28 | |
Open Nemotron omni model combining reasoning with text, vision, and audio Basics
Limits
InputText: SupportedImage: SupportedAudio: SupportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
DeepSeek V4 Flash 0423deepseek-v4-flash-0423 | DeepSeek | Text | - | 1M | 384K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-23 | |
Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
DeepSeek V4 Pro 0423deepseek-v4-pro-0423 | DeepSeek | Text | - | 1M | 384K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-23 | |
DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Deep Research Max Previewdeep-research-max-preview-04-2026 | Image | - | 1.05M | 65.5K | Text: SupportedImage: SupportedAudio: SupportedVideo: SupportedPDF: SupportedFile: Supported | Text: SupportedImage: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | Official$2 / $12LowestNo price | 2026-04-21 | ||
Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports Basics
Limits
InputText: SupportedImage: SupportedAudio: SupportedVideo: SupportedPDF: SupportedFile: Supported OutputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Gemini Deep Research Previewdeep-research-preview-04-2026 | Image | - | 1.05M | 65.5K | Text: SupportedImage: SupportedAudio: SupportedVideo: SupportedPDF: SupportedFile: Supported | Text: SupportedImage: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | Official$2 / $12LowestNo price | 2026-04-21 | ||
Agentic model for autonomous multi-step research, synthesis, and cited reports Basics
Limits
InputText: SupportedImage: SupportedAudio: SupportedVideo: SupportedPDF: SupportedFile: Supported OutputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
GPT-5.4 Image 2gpt-5.4-image-2 | OpenAI | Image | - | 272K | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: SupportedImage: Supported | Reason: SupportedTools: Not supportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-04-21 | |
Image model for prompt-driven generation, editing, and visual design workflows Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Nemotron 3 Content Safetynemotron-3-content-safety | Nvidia | Text | - | 128K | 4.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-16 | |
Safety model for policy screening, moderation, and risk-aware routing workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Gemma 4 26B A4B ITgemma-4-26b-a4b-it | Text | - | 262.1K | 32.8K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-02 | ||
Open Gemma instruction model for efficient chat and self-hosted deployments Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Gemma 4 E2B ITgemma-4-e2b-it | Text | - | 131.1K | 8.2K | Text: SupportedImage: SupportedAudio: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-02 | ||
Open Gemma instruction model for efficient chat and self-hosted deployments Basics
Limits
InputText: SupportedImage: SupportedAudio: SupportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Gemma 4 E4B ITgemma-4-e4b-it | Text | - | 131.1K | 8.2K | Text: SupportedImage: SupportedAudio: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-02 | ||
Open Gemma instruction model for efficient chat and self-hosted deployments Basics
Limits
InputText: SupportedImage: SupportedAudio: SupportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Step 3.5 Flash 2603step-3.5-flash-2603 | StepFun (China) | Text | - | 256K | 256K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.1 / $0.3LowestNo price | 2026-04-02 | |
StepFun flash model for efficient multimodal reasoning, coding, and tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Trinity Large Thinkingtrinity-large-thinking | 阿西人工智能 | Text | - | 524.3K | 262.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-01 | |
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Llama Nemotron Rerank VL 1B v2llama-nemotron-rerank-vl-1b-v2 | Nvidia | Text | - | 10.2K | 4.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-03-31 | |
Reranking model for improving retrieval quality in search and recommendation systems Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Veo 3.1 Lite Previewveo-3.1-lite-generate-preview | Video | - | 1K | - | Text: SupportedImage: SupportedFile: Supported | Video: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-03-31 | ||
Video model for prompt-guided generation, editing, and motion workflows Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Mercury Edit 2mercury-edit-2 | Inception | Text | - | 32K | 8.2K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-03-30 | |
Code editing dLLM for autocomplete (FIM) and next-edit suggestions Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Nemotron Cascade 2 30B A3Bnemotron-cascade-2-30b-a3b | Nvidia | Text | - | 256K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-03-24 | |
Nemotron model for efficient reasoning, coding, and specialized AI agents Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Reka Edgereka-edge | 雷卡人工智能 | Text | - | 16.4K | 14.7K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-03-20 | |
Multimodal model for analyzing text, images, documents, and rich media Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Mistral Smallmistral-small-latest | Mistral | Text | - | 256K | 256K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.15 / $0.6LowestNo price | 2026-03-16 | |
Efficient Mistral model for fast chat, extraction, and production assistants Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Mistral Small 4mistral-small-2603 | Mistral | Text | - | 256K | 256K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 4.3 | Official$0.15 / $0.6LowestNo price | 2026-03-16 | |
Fast Mistral production model for chat, extraction, and cost-sensitive agents Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Nemotron VoiceChatnemotron-voicechat | Nvidia | Text | - | 128K | 8.2K | Text: SupportedAudio: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-03-16 | |
Nemotron multimodal model for visual reasoning and agentic AI workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: SupportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Nemotron 3 Super 120B A12Bnemotron-3-super-120b-a12b | Nvidia | Text | - | 262.1K | 262.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-03-11 | |
Nemotron middle tier for collaborative agents and high-volume reasoning workloads Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Mercury 2mercury-2 | Inception | Text | - | 128K | 50K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-03-04 | |
Reasoning model for deliberate analysis, multi-step problem solving, and tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Qwen3.5 0.8Bqwen3.5-0.8b | Alibaba Cloud | Text | - | 262.1K | 81.9K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-03-02 | |
Smallest Qwen3.5 multimodal model for on-device chat, reasoning, and tool use Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Qwen3.5 2Bqwen3.5-2b | Alibaba Cloud | Text | - | 262.1K | 81.9K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-03-02 | |
Compact Qwen3.5 multimodal model for fast chat, reasoning, and tool use Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Qwen3.5 4Bqwen3.5-4b | Alibaba Cloud | Text | - | 262.1K | 81.9K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-03-02 | |
Small Qwen3.5 multimodal model for low-cost chat, reasoning, and tool use Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Qwen3.5 9B Baseqwen3.5-9b-base | Alibaba Cloud | Text | - | 262.1K | 65.5K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-26 | |
Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
LFM2 24B A2Blfm2-24b-a2b | Liquid Inference | Text | - | 32.8K | 32.8K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 5.9 | OfficialNo priceLowestNo price | 2026-02-24 | |
Efficient open Liquid MoE instruct model for on-device chat and tool calling Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Qwen3.5 35B-A3B Baseqwen3.5-35b-a3b-base | Alibaba Cloud | Text | - | 262.1K | 65.5K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-24 | |
Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Aion-2.0aion-2.0 | 埃昂实验室 | Text | - | 131.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-02-23 | |
Reasoning model for deliberate analysis, multi-step problem solving, and tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Qwen3.5 9Bqwen3.5-9b | Alibaba Cloud | Text | - | 262.1K | 65.5K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-23 | |
Qwen instruction model for multilingual chat, reasoning, and tool use Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Trendyol Asure 12Basure-12b | 特伦迪约尔 | Text | - | 131.1K | - | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-19 | |
Turkish-language multimodal instruct model built on Gemma 3 12B for e-commerce text, chat, and image-text tasks Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Sarvam 30Bsarvam-30b | Sarvam AI | Text | - | 128K | 128K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-18 | |
Efficient Indian-language reasoning model for chat, coding, and multilingual work Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Tiny Aya Earthtiny-aya-earth | Cohere | Text | - | 8K | 8K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-17 | |
Compact multilingual model specialized for West Asian and African languages Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Tiny Aya Firetiny-aya-fire | Cohere | Text | - | 8K | 8K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-17 | |
Compact multilingual model specialized for South Asian languages Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Tiny Aya Globaltiny-aya-global | Cohere | Text | - | 8K | 8K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-17 | |
Compact multilingual model balanced across 70 languages and regions Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Tiny Aya Watertiny-aya-water | Cohere | Text | - | 8K | 8K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-17 | |
Compact multilingual model specialized for European and Asia-Pacific languages Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Llama Nemotron Embed VL 1B v2llama-nemotron-embed-vl-1b-v2 | Nvidia | Text | - | 10.2K | 2K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-02-10 | |
Embedding model for semantic search, retrieval, clustering, and ranking pipelines Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
DeepSeek OCR 2deepseek-ocr-2 | DeepSeek | Text | - | 8.2K | 8.2K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-01-27 | |
High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Trinity Large Previewtrinity-large-preview | 阿西人工智能 | Text | - | 524.3K | 262.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-01-27 | |
Lightly post-trained 398B MoE chat model for creative work, long-context prompts, and tool-using agents Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
MiniMax-M2 Herminimax-m2-her | MiniMax | Text | - | 65.5K | 2K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-01-23 | |
MiniMax M2 variant tuned for conversational and character-driven agent interactions Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Nemotron Content Safety Reasoning 4Bnemotron-content-safety-reasoning-4b | Nvidia | Text | - | 128K | 4.1K | Text: Supported | Text: Supported | Reason: SupportedTools: Not supportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-01-22 | |
Safety model for policy screening, moderation, and risk-aware routing workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
GLM-Imageglm-image | Zhipu AI | Image | - | 10.2K | - | Text: SupportedImage: SupportedFile: Supported | Image: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-01-19 | |
GLM-Image is an image generation model adopts a hybrid autoregressive + diffusion decoder architecture. In general image generation quality, GLM‑Image aligns with mainstream latent diffusion approaches, but it shows significant advantages in text-rendering and knowledge‑intensive generation scenarios. It performs especially well in tasks requiring precise semantic understanding and complex information expression, while maintaining strong capabilities in high‑fidelity and fine‑grained detail gene Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: Not supportedImage: SupportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Jamba Minijamba-mini | AI21 Labs | Text | - | 256K | 4.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.2 / $0.4LowestNo price | 2026-01-01 | |
AI21's efficient, lightweight hybrid SSM-Transformer model for a wide range of tasks Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Solar Pro 3solar-pro3 | Upstage | Text | - | 131.1K | 8.2K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$0.25 / $0.25LowestNo price | 2026-01 | |
Flagship model for demanding analysis, coding, and production agent workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Orpheus V1 Englishorpheus-v1-english | 卡诺皮实验室 | Audio | - | 4K | 50K | Text: Supported | Audio: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2025-12-19 | |
Expressive English text-to-speech model with bracketed vocal directions Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: Not supportedImage: Not supportedAudio: SupportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Orpheus Arabic Saudiorpheus-arabic-saudi | 卡诺皮实验室 | Audio | - | 4K | 50K | Text: Supported | Audio: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2025-12-16 | |
Expressive Saudi Arabic text-to-speech model with bracketed vocal directions Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: Not supportedImage: Not supportedAudio: SupportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Nemotron 3 Nano 30B A3Bnemotron-3-nano-30b-a3b | Nvidia | Text | - | 262.1K | 262.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-12-15 | |
Small Nemotron 3 MoE for efficient coding, math, and long-context agents Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
AutoGLM Phone 9B Multilingualautoglm-phone-9b-multilingual | Zhipu AI | Text | - | 65.5K | 65.5K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-12-10 | |
Multilingual visual model for operating smartphone interfaces and mobile agents Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Devstral 2devstral-2512 | Mistral | Text | - | 262.1K | 262.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.4 / $2LowestNo price | 2025-12-09 | |
Mistral's coding-agent model for repository work, terminal tasks, and software fixes Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Devstral Small 2devstral-small-2 | Mistral | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-12-09 | |
Compact multimodal coding model for repository exploration, file editing, and software agents Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
GLM-4.6V-Flashglm-4.6v-flash | Zhipu AI | Text | - | 128K | 32.8K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0 / $0LowestNo price | 2025-12-08 | |
Lightweight GLM vision model for visual reasoning, documents, and multimodal agents Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Relace Searchrelace-search | 瑞莱斯 | Text | - | 256K | 128K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2025-12-08 | |
Tool-capable chat model for instruction following and agentic application workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Rnj-1 Instructrnj-1-instruct | 埃森舍尔人工智能 | Text | - | 32.8K | 32.8K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-12-04 | |
Open 8B Essential AI model for code, STEM reasoning, and agentic tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Ministral 14Bministral-14b | Mistral | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-12-02 | |
Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Ministral 3 14Bministral-3-14b-instruct-2512 | Mistral | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.2 / $0.2LowestNo price | 2025-12-02 | |
Open vision-language model for efficient local deployment, instruction following, and tool use Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Ministral 3 14B 2512ministral-14b-2512 | Mistral | Text | - | 262.1K | 209.7K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.2 / $0.2LowestNo price | 2025-12-02 | |
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Ministral 3 3Bministral-3-3b-instruct-2512 | Mistral | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.1 / $0.1LowestNo price | 2025-12-02 | |
Compact open vision-language model for edge deployment, instruction following, and tool use Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Ministral 3 3B 2512ministral-3b-2512 | Mistral | Text | - | 131.1K | 104.9K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.1 / $0.1LowestNo price | 2025-12-02 | |
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Ministral 3 8Bministral-3-8b-instruct-2512 | Mistral | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.15 / $0.15LowestNo price | 2025-12-02 | |
Compact open vision-language model for edge deployment, instruction following, and tool use Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Ministral 3 8B 2512ministral-8b-2512 | Mistral | Text | - | 262.1K | 209.7K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.15 / $0.15LowestNo price | 2025-12-02 | |
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Mistral Large 3mistral-large-2512 | Mistral | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.5 / $1.5LowestNo price | 2025-12-02 | |
Mistral's largest general model for enterprise agents, coding, and multilingual reasoning Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Nova 2 Litenova-2-lite | 亚马逊 | Text | - | 1M | 65.5K | Text: SupportedImage: SupportedVideo: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2025-12-02 | |
Multimodal reasoning model for visual analysis, planning, and tool use Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Trinity Minitrinity-mini | 阿西人工智能 | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-12-01 | |
Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Trinity Nano Previewtrinity-nano-preview | 阿西人工智能 | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-12-01 | |
Experimental chat-tuned 6B MoE model with 1B active parameters for low-resource chat and instruction following Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
GPT OSS Safeguard 120Bgpt-oss-safeguard-120b | OpenAI | Text | - | 131.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-10-29 | |
Safety model for policy screening, moderation, and risk-aware routing workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
GPT OSS Safeguard 20Bgpt-oss-safeguard-20b | OpenAI | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-10-29 | |
Safety model for policy screening, moderation, and risk-aware routing workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Llama 3.1 Nemotron Safety Guard 8B v3llama-3.1-nemotron-safety-guard-8b-v3 | Nvidia | Text | - | 128K | 4.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-10-28 | |
Safety model for policy screening, moderation, and risk-aware routing workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Nemotron Nano 12B v2 VLnemotron-nano-12b-v2-vl | Nvidia | Text | - | 128K | 128K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 7.5 | OfficialNo priceLowestNo price | 2025-10-28 | |
Nemotron multimodal model for visual reasoning and agentic AI workflows Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
GPT-5 Image Minigpt-5-image-mini | OpenAI | Image | - | 400K | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: SupportedImage: Supported | Reason: SupportedTools: Not supportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2025-10-16 | |
Image model for prompt-driven generation, editing, and visual design workflows Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Llama Nemotron Embed 1B v2llama-nemotron-embed-1b-v2 | Nvidia | Text | - | 8.2K | 2K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-10-16 | |
Multilingual text embedding model for retrieval and question answering pipelines Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
PaddleOCR VLpaddleocr-vl | 飞桨 | Text | - | 131.1K | 16.4K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-10-16 | |
Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
GPT-5 Imagegpt-5-image | OpenAI | Image | - | 400K | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: SupportedImage: Supported | Reason: SupportedTools: Not supportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2025-10-14 | |
Image model for prompt-driven generation, editing, and visual design workflows Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Gemini 2.5 Computer Use Previewgemini-2.5-computer-use-preview-10-2025 | Text | - | 128K | 64K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$1.25 / $10LowestNo price | 2025-10-07 | ||
Specialized Gemini 2.5 model for browser-control agents that automate UI tasks Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Granite-4.0-H-Microgranite-4-h-micro | 国际商业机器公司 | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 5.1 | OfficialNo priceLowestNo price | 2025-10-02 | |
Compact open-weight hybrid Granite model for lightweight enterprise chat and tool calling Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Granite-4.0-H-Smallgranite-4-h-small | 国际商业机器公司 | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-10-02 | |
Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Cydonia 24B V4.1cydonia-24b-v4.1 | 德拉默 | Text | - | 131.1K | 118K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-09-27 | |
Open-weight instruction model for adaptable chat and self-hosted production workloads Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Relace Apply 3relace-apply-3 | 瑞莱斯 | Text | - | 256K | 128K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2025-09-26 | |
General-purpose chat model for instruction following, writing, and analysis Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Gemma-SEA-LION-v4-27B-ITgemma-sea-lion-v4-27b-it | 新加坡人工智能 | Text | - | 128K | 128K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-09-23 | |
Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Qwen3 Omni 30B A3B Thinkingqwen3-omni-30b-a3b-thinking | Alibaba Cloud | Text | - | 65.5K | 16.4K | Text: SupportedImage: SupportedAudio: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-09-22 | |
Multimodal reasoning model accepting text, images, video, and audio with text output Basics
Limits
InputText: SupportedImage: SupportedAudio: SupportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Magistral Small 1.2magistral-small-2509 | Mistral | Text | - | 131.1K | 131.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-09-18 | |
Open multimodal reasoning model for transparent analysis of text and images Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Apertus 70Bapertus-70b | 瑞士人工智能 | Text | - | 65.5K | 8.2K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-09-02 | |
Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant. Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Apertus 8Bapertus-8b | 瑞士人工智能 | Text | - | 65.5K | 8.2K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-09-02 | |
Fully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant. Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Sarvam 105Bsarvam-105b | Sarvam AI | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-09-01 | |
Flagship Indian-language reasoning model for enterprise multilingual applications Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Command A Translatecommand-a-translate-08-2025 | Cohere | Text | - | 8K | 8K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$2.5 / $10LowestNo price | 2025-08-28 | |
Translation model for multilingual conversion, localization, and cross-language workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Hermes 4 405Bhermes-4-405b | 诺斯研究 | Text | - | 131.1K | 118K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 7.5 | OfficialNo priceLowestNo price | 2025-08-26 | |
Reasoning model for deliberate analysis, multi-step problem solving, and tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Command A Reasoningcommand-a-reasoning-08-2025 | Cohere | Text | - | 256K | 32K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$2.5 / $10LowestNo price | 2025-08-21 | |
Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
DeepSeek V3.1deepseek-chat-v3.1 | DeepSeek | Text | - | 163.8K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 13.7 | OfficialNo priceLowestNo price | 2025-08-21 | |
DeepSeek chat model for instruction following, coding, and analysis Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Seed-OSS-36B-Instructseed-oss-36b-instruct | ByteDance | Text | - | 524.3K | 524.3K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 12.1 | OfficialNo priceLowestNo price | 2025-08-20 | |
Open ByteDance Seed model for long-context reasoning, tool use, and agents Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Nemotron Nano 9B v2nemotron-nano-9b-v2 | Nvidia | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 7.4 | OfficialNo priceLowestNo price | 2025-08-18 | |
Compact Nemotron model for efficient reasoning and deployable AI agents Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Baichuan M2 32Bbaichuan-m2-32b | 百川智能 | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-08-13 | |
Open medical model trained for clinical reasoning and patient interaction with on, off, and auto thinking modes Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Mistral Medium 3.1mistral-medium-3.1 | Mistral | Text | - | 131.1K | 104.9K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2025-08-13 | |
Mistral model for multilingual chat, reasoning, and tool-assisted workflows Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Command A Visioncommand-a-vision-07-2025 | Cohere | Text | - | 128K | 8K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$2.5 / $10LowestNo price | 2025-07-31 | |
Cohere vision model for multilingual document analysis, OCR, and image understanding Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Codestral 25.08codestral-2508 | Mistral | Text | - | 128K | 8.2K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$0.3 / $0.9LowestNo price | 2025-07-30 | |
Mistral code model for low-latency completion, fill-in-the-middle, and code generation Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
GLM-4.5-Flashglm-4.5-flash | Zhipu AI | Text | - | 131.1K | 98.3K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$0 / $0LowestNo price | 2025-07-28 | |
Efficient GLM model for fast reasoning, coding, and agent workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Llama 3.3 Nemotron Super 49B v1.5llama-3.3-nemotron-super-49b-v1.5 | Nvidia | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 9.0 | OfficialNo priceLowestNo price | 2025-07-25 | |
Nemotron model for efficient reasoning, coding, and specialized AI agents Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Voxtral Mini 3B 2507voxtral-mini-3b-2507 | Mistral | Text | - | 32.8K | 32.8K | Text: SupportedAudio: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-07-15 | |
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: SupportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Voxtral Smallvoxtral-small-latest | Mistral | Text | - | 32K | 32K | Text: SupportedAudio: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0.1 / $0.4LowestNo price | 2025-07-15 | |
Instruct model with native audio input for speech understanding and tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: SupportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Voxtral Small 24B 2507voxtral-small-24b-2507 | Mistral | Text | - | 32.8K | 32.8K | Text: SupportedAudio: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2025-07-15 | |
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: SupportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Devstral Mediumdevstral-medium-2507 | Mistral | Text | - | 128K | 128K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | 9.0 | Official$0.4 / $2LowestNo price | 2025-07-10 | |
Mistral coding agent model for repository tasks and software engineering workflows Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Capabilities and limits come from public sources. “Unknown” means no reliable data yet, not “not supported”. Relay counts include only sites with a current public price, de-duplicated per site.
Data source: models.dev · OpenRouter
Intelligence scores come from the OpenRouter benchmark rankings (Intelligence Index); higher is smarter.