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 | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
GPT-4o minigpt-4o-mini | OpenAI | Text | 17 sites | 128K | 16.4K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$0.15 / $0.6Lowest$0.0022 / $0.0087 | 2024-07-18 | |
Small omni GPT for cheap multimodal assistance and production-scale traffic 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
| ||||||||||||
o3-deep-researcho3-deep-research | OpenAI | Text | 3 sites | 200K | 100K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowest$1.2 / $4.79 | 2024-06-26 | |
Research model for long-horizon investigation, synthesis, and analytical reports 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: Not supported Pricing
| ||||||||||||
o4-mini-deep-researcho4-mini-deep-research | OpenAI | Text | 3 sites | 200K | 100K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowest$0.2393 / $0.9572 | 2024-06-26 | |
Research model for long-horizon investigation, synthesis, and analytical reports 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: Not supported Pricing
| ||||||||||||
GPT-4ogpt-4o | OpenAI | Text | 19 sites | 128K | 16.4K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$2.5 / $10Lowest$0.0362 / $0.1448 | 2024-05-13 | |
Omni-era GPT for multimodal chat, practical coding, and general assistants 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
| ||||||||||||
GPT-4o (2024-05-13)gpt-4o-2024-05-13 | OpenAI | Text | 10 sites | 128K | 4.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$5 / $15Lowest$0.0724 / $0.2172 | 2024-05-13 | |
GPT model for general reasoning, writing, coding, and tool-assisted 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: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Qwen-VL Maxqwen-vl-max | Alibaba Cloud | Text | 2 sites | 131.1K | 8.2K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$0.8 / $3.2Lowest$0.0888 / $0.3527 | 2024-04-08 | |
Qwen vision-language model for visual reasoning, documents, and agent 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: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Qwen Maxqwen-max | Alibaba Cloud | Text | 5 sites | 32.8K | 8.2K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$1.6 / $6.4Lowest$0.1723 / $0.6892 | 2024-04-03 | |
Flagship Qwen model for complex reasoning, coding, and agentic 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
| ||||||||||||
Claude Haiku 3claude-3-haiku-20240307 | Anthropic | Text | 4 sites | 200K | 4.1K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | 5.6 | OfficialNo priceLowest$0.0561 / $0.2804 | 2024-03-13 | |
Legacy model retained for compatibility with older integrations 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
| ||||||||||||
Qwen Plusqwen-plus | Alibaba Cloud | Text | 6 sites | 1M | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$0.4 / $1.2Lowest$0.0431 / $0.1292 | 2024-01-25 | |
Qwen instruction model for multilingual chat, reasoning, 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
| ||||||||||||
Qwen-VL Plusqwen-vl-plus | Alibaba Cloud | Text | 2 sites | 131.1K | 8.2K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$0.21 / $0.63Lowest$8.58 / $21.45 | 2024-01-25 | |
Qwen vision-language model for visual reasoning, documents, and agent 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: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
GPT-4gpt-4 | OpenAI | Text | 6 sites | 8.2K | 8.2K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$30 / $60Lowest$0.7628 / $1.53 | 2023-11-06 | |
GPT model for general reasoning, writing, coding, and tool-assisted 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
| ||||||||||||
GPT-4 Turbogpt-4-turbo | OpenAI | Text | 8 sites | 128K | 4.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$10 / $30Lowest$0.2543 / $0.7628 | 2023-11-06 | |
Compact GPT model for low-latency assistance and high-volume 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
| ||||||||||||
GPT-3.5-turbogpt-3.5-turbo | OpenAI | Text | 11 sites | 16.4K | 4.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Supported | - | Official$0.5 / $1.5Lowest$0.0127 / $0.0381 | 2023-03-01 | |
Compact GPT model for low-latency assistance and high-volume 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
| ||||||||||||
Doubao Seed 2.0 Litedoubao-seed-2.0-lite | ByteDance | Text | 2 sites | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowest$0.0269 / $0.1588 | - | |
Doubao Seed 2.0 Lite is a lightweight AI model from ByteDance for everyday text interaction and information processing. It offers a concise and convenient model option for applications that need a lightweight experience. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
Doubao Seed 2.1 Turbodoubao-seed-2.1-turbo | ByteDance | Text | 2 sites | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowest$0.1508 / $0.7551 | - | |
Doubao Seed 2.1 Turbo is an AI model from ByteDance. It can be used in AI applications and workflows. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
Doubao-Seedance-1.5-prodoubao-seedance-1.5-pro | ByteDance | Text | 4 sites | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowest$0.003/ 次 | - | |
Doubao-Seedance-1.5-pro is an artificial intelligence model developed by Bytedance. This profile focuses on the model’s identity and basic information for cataloging and management. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
/ 次 | ||||||||||||
Composer 2.5composer-2.5 | Cursor | Text | 4 sites | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowest$0.0523 / $0.1047 | - | |
Composer 2.5 is Cursor's own model, trained for capable agentic coding. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
Gemini 3 Flashgemini-3-flash | Text | 29 sites | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowest$0.0142 / $0.0853 | - | ||
Gemini 3 Flash is a Google model currently listed on Cursor's models and pricing page. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
Doubao-Seedance-2.0-minidoubao-seedance-2.0-mini | ByteDance | Video | 7 sites | - | - | - | Video: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowest$0.0021/ 次 | - | |
Doubao-Seedance-2.0-mini is an AI model from ByteDance that supports video output. It can be used for video content creation and exploring visual ideas through video. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
/ 次 | ||||||||||||
Inkling 2 Smallinkling-2-small | Thinking Machines | Text | - | 1.05M | 131.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-11-05 | |
Multimodal MoE reasoning model (594B total, 17B active) for agentic coding, vision, and knowledge work 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
| ||||||||||||
Flintflint | 瑞克西夫 | Text | - | 262.1K | 262.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-10-21 | |
Open-weight mixture-of-experts model with about 2.5B active parameters for local coding 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
| ||||||||||||
Mercury 3mercury-3 | Inception | Text | - | 1M | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-10-16 | |
Inception's diffusion reasoning model for chat, 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
| ||||||||||||
Muse Spark Openmuse-spark-open | Meta | Text | - | 1.05M | 131.1K | Text: SupportedImage: SupportedAudio: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 24.9 | OfficialNo priceLowestNo price | 2026-10-15 | |
Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context. 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
| ||||||||||||
Nemotron 3.5 Super 120B A12Bnemotron-3.5-super-120b-a12b | Nvidia | Text | - | 1.05M | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-10-15 | |
NVIDIA Nemotron 3.5 Super reasoning model (120B total, 12B active) served with text-only input 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 3.5 Super VL 120B A12Bnemotron-3.5-super-vl-120b-a12b | Nvidia | Text | - | 1.05M | 8.2K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-10-15 | |
NVIDIA vision-language reasoning model for text, image, and video understanding and agentic 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
| ||||||||||||
Muse Wonder Fullmuse-wonder-full | Meta | Text | - | 1.05M | - | Text: SupportedImage: SupportedAudio: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-10-12 | |
Muse Wonder Full is the most capable model in Meta's Muse Wonder series, built for long-running professional agents and ultra-long-horizon software engineering. It shares Muse Wonder's Active Memory and Active Focus capabilities and generally scores higher on Meta's agentic and coding evaluations. 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
| ||||||||||||
LightOnOCR-3 0.8Blightonocr-3-0.8b | 莱顿人工智能 | Text | - | 262.1K | 16.4K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-10-08 | |
LightOnOCR-3-0.8B is the lightest model of LightOn's LightOnOCR-3 family, with the same layout and visual understanding features as its larger siblings. 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
| ||||||||||||
MiniCPM-V 4.7 35B-A3Bminicpm-v-4.7-35b-a3b | OpenBMB | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-10-07 | |
First MoE MiniCPM-V model for single-image, multi-image and video understanding 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
| ||||||||||||
MiniCPM-V 4.7 1Bminicpm-v-4.7-1b | OpenBMB | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-10-06 | |
Compact MiniCPM-V model for single-image, multi-image and video understanding 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
| ||||||||||||
Mistral Large 4mistral-large-4 | Mistral | Text | - | 1.05M | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 26.1 | Official$0.7 / $2.1LowestNo price | 2026-10-06 | |
Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work 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
| ||||||||||||
Beam 1.0 501B A23Bbeam-1.0-501b-a23b | Reflection | Text | - | 1.05M | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 17.7 | OfficialNo priceLowestNo price | 2026-10-05 | |
Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic 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
| ||||||||||||
Kolibri 1kolibri-1 | 阿列夫阿尔法 | Text | - | 1.05M | - | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-10-03 | |
Aleph Alpha's German and English mixture-of-experts reasoning model (78B total, 3.46B active) for chat, RAG 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
| ||||||||||||
Grok Imagine Video 1.5 Litegrok-imagine-video-1.5-lite | xAI | Video | - | 1K | - | Text: SupportedImage: SupportedFile: Supported | Video: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-10-01 | |
Cost-efficient video model for text-to-video and image-to-video generation 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
| ||||||||||||
Ling 3.1 Flashling-3.1-flash | InclusionAI | Text | - | 262.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 41.1 | OfficialNo priceLowestNo price | 2026-09-29 | |
Efficient model for low-latency assistance, extraction, and routine automation 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
| ||||||||||||
MiniMax-M3.1-Flash-Previewminimax-m3.1-flash-preview | MiniMax | Text | - | 1M | 512K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-09-27 | |
MiniMax-M3.1-Flash-Preview is retired. MiniMax says requests under the old name are served by MiniMax-M3.1-Flash (verified 2026-10-20). 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
| ||||||||||||
LongCat-2.5-Previewlongcat-2.5-preview | 美团 | Text | - | 1M | 131.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-09-25 | |
Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window 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: Not supported Pricing
| ||||||||||||
Perceptron Mk1.5perceptron-mk1.5 | 佩尔塞普特龙 | Text | - | 36.9K | 8.2K | Text: SupportedImage: SupportedAudio: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-09-25 | |
Image, video, and audio understanding with visual grounding, reasoning, and function calling 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
| ||||||||||||
Qwen 3.8 Max Primeqwen3.8-max-prime | Alibaba Cloud | Text | - | 1M | 131.1K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-09-23 | |
High-throughput edition of Qwen3.8 Max for coding, professional work, multimodal understanding, and long-running agent 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
| ||||||||||||
Ember-1ember-1 | 烟花人工智能 | Text | - | 1.05M | 131.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-09-22 | |
Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality 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
| ||||||||||||
Solar Mini 4solar-mini4 | Upstage | Text | - | 524.3K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 24.1 | Official$0.1 / $0.4LowestNo price | 2026-09-22 | |
Upstage's compact, cost-efficient model for agentic 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
| ||||||||||||
Viv Fastviv-fast | Vivgrid | Text | - | 1M | 256K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-09-21 | |
Fast coding model 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: Not supported Pricing
| ||||||||||||
Grok Voice Transcribe 2.0grok-voice-transcribe-2.0 | xAI | Text | - | - | - | Audio: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-09-17 | |
Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming Basics
Limits
InputText: Not supportedImage: Not supportedAudio: 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
| ||||||||||||
Paretopareto | 安比艾斯 | Text | - | 262.1K | 131.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-09-17 | |
Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer 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
| ||||||||||||
Arrow 2arrow-2 | 奎弗人工智能 | Image | - | 131.1K | 65.5K | Text: SupportedImage: SupportedFile: Supported | Text: SupportedImage: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-09-16 | |
Fast SVG generation model for creation, vectorization, editing, and animation Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Arrow 2 Telosarrow-2-telos | 奎弗人工智能 | Image | - | 1.05M | 65.5K | Text: SupportedImage: SupportedFile: Supported | Text: SupportedImage: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-09-16 | |
High-fidelity SVG generation model for complex vector work and long-context refinement Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Schematron V2 Smallschematron-v2-small | 因弗伦斯-内特 | Text | - | 128K | 4.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-09-12 | |
Efficient model for low-latency assistance, extraction, and routine automation 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
| ||||||||||||
Schematron V2 Turboschematron-v2-turbo | 因弗伦斯-内特 | Text | - | 128K | 8.2K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-09-12 | |
Efficient model for low-latency assistance, extraction, and routine automation 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
| ||||||||||||
Fugu Maxfugu-max | Sakana AI | Text | - | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-09-11 | |
Multi-agent model for routing expert agents across complex analytical tasks Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Fugu Ultra v2fugu-ultra-v2 | Sakana AI | Text | - | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-09-11 | |
Quality-first multi-agent model for hard research, analysis, and competitions Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Ling 3.0 Flash VLling-3.0-flash-vl | InclusionAI | Text | - | 262.1K | 32.8K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-09-10 | |
Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual 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
| ||||||||||||
North Small Translatenorth-small-translate-1-0 | Cohere | Text | - | 16K | 16K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$0 / $0LowestNo price | 2026-09-09 | |
Open-weight translation model for more than 50 languages and locale variants 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
| ||||||||||||
Mercury 2.5mercury-2.5 | Inception | Text | - | 260K | 65.5K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 12.3 | OfficialNo priceLowestNo price | 2026-09-08 | |
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
| ||||||||||||
MiniCPM5-2Bminicpm5-2b | OpenBMB | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-09-06 | |
Dense 2B-class open-source model for on-device and resource-constrained use, with native long-context support, tool calling, and agentic 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: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Ling 3.0 Flash Santeling-3.0-flash-sante | InclusionAI | Text | - | 262.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-09-04 | |
Health and medicine specialization of Ling 3.0 Flash for medical reasoning and evidence-based retrieval 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
| ||||||||||||
Granite 4.2 8Bgranite-4.2-8b | 国际商业机器公司 | Text | - | 131.1K | 118K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 5.1 | OfficialNo priceLowestNo price | 2026-08-31 | |
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
| ||||||||||||
Ling 3.0 Flash Finling-3.0-flash-fin | InclusionAI | Text | - | 262.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-08-27 | |
Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution 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
| ||||||||||||
Gemini 3.5 Transcribe Livegemini-3.5-transcribe-live | Text | - | - | - | Audio: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-08-26 | ||
Speech transcription model for accurate audio-to-text and captioning workflows Basics
Limits
InputText: Not supportedImage: Not supportedAudio: 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
| ||||||||||||
Apodex 1.1 Miniapodex-1.1-mini | 阿波德克斯 | Text | - | 262.1K | 262.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-08-24 | |
Open-weight 35B MoE model for long-horizon research, forecasting, and tool-assisted 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
| ||||||||||||
Hy-MT2-1.8Bhy-mt2-1.8b | Tencent | Text | - | 8.2K | 4.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-08-20 | |
Tencent Hy reasoning model for coding, instruction following, and agent 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: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Hy-MT2-30B-A3Bhy-mt2-30b-a3b | Tencent | Text | - | 8.2K | 4.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-08-20 | |
Tencent Hy reasoning model for coding, instruction following, and agent 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: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Hy-MT2-7Bhy-mt2-7b | Tencent | Text | - | 8.2K | 4.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-08-19 | |
Tencent Hy reasoning model for coding, instruction following, and agent 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: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Ornith 1.5 35B A3Bornith-1.5-35b-a3b | 深度强化 | Text | - | 262.1K | - | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-08-18 | |
Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, 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: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Toast 1toast-1 | Mixedbread | Text | - | 131K | 4K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-08-13 | |
Specialized search model for knowledge-intensive questions, multi-step retrieval, and evidence synthesis 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
| ||||||||||||
Qwen3.8 2.4T A95Bqwen3.8-2.4t-a95b | Alibaba Cloud | Text | - | 262.1K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-08-12 | |
Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic 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
| ||||||||||||
MAI-Code-1.1-Flashmai-code-1.1-flash | 微软 | Text | - | 256K | 128K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-08-11 | |
Microsoft coding model with native vision support, optimized for fast and efficient software development 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: Not supported Pricing
| ||||||||||||
Nemotron 3.5 Lightning 30B A3Bnemotron-3.5-lightning | Nvidia | Text | - | 262.1K | 262.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 5.5 | OfficialNo priceLowestNo price | 2026-08-11 | |
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise 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
| ||||||||||||
Muse Glimmer 30Bmuse-glimmer-30b | Meta | Text | - | 131.1K | 131.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 6.3 | OfficialNo priceLowestNo price | 2026-08-10 | |
Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, 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: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Motif 3motif-3 | 莫蒂夫科技 | Text | - | 262.1K | 262.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-08-07 | |
Motif 3 is a large-scale, decoder-only Mixture-of-Experts (MoE) language model with 314 billion total parameters and 13.2 billion parameters activated per token. 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
| ||||||||||||
Solar Pro 4solar-pro4 | Upstage | Text | - | 524.3K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 28.2 | Official$0.3 / $1.2LowestNo price | 2026-08-06 | |
Upstage's flagship model, specialized for agentic 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
| ||||||||||||
Sakana Namazusakana-namazu | Sakana AI | Text | - | 262.1K | 65.5K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$0.95 / $4LowestNo price | 2026-08-03 | |
Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Inkling Smallinkling-small | Thinking Machines | Text | - | 1.05M | 1.05M | Text: SupportedImage: SupportedAudio: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 12.9 | Official$0.58 / $1.44LowestNo price | 2026-07-30 | |
Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio 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
| ||||||||||||
Ling 3.0 Flashling-3.0-flash | InclusionAI | Text | - | 262.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-07-23 | |
Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient 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
| ||||||||||||
Laguna S 2.1laguna-s-2.1 | Poolside | Text | - | 1.05M | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-07-21 | |
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
| ||||||||||||
Macaron V1 Tallmacaron-v1-tall | 明德实验室 | Text | - | 262.1K | 32.8K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-07-21 | |
Qwen3.6-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI 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
| ||||||||||||
Macaron V1 Ventimacaron-v1-venti | 明德实验室 | Text | - | 1.05M | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-07-21 | |
GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI 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
| ||||||||||||
Aion-3.0aion-3.0 | 埃昂实验室 | Text | - | 131.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-07-07 | |
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
| ||||||||||||
Aion-3.0-Miniaion-3.0-mini | 埃昂实验室 | Text | - | 131.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-07-07 | |
Efficient model for low-latency assistance, extraction, and routine automation 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
| ||||||||||||
Laguna XS 2.1laguna-xs-2.1 | Poolside | Text | - | 262.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-07-02 | |
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
| ||||||||||||
Ornith 1.0 31Bornith-1.0-31b | 深度强化 | Text | - | 262.1K | - | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-06-25 | |
Open coding-reasoning model for repository tasks and self-improving 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
| ||||||||||||
Ornith 1.0 35Bornith-1.0-35b | 深度强化 | Text | - | 262.1K | - | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-06-25 | |
Large coding-reasoning model for agentic software tasks and RL search 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
| ||||||||||||
Ornith 1.0 397Bornith-1.0-397b | 深度强化 | Text | - | 262.1K | - | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-06-25 | |
Large coding-reasoning model for agentic software tasks and RL search 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
| ||||||||||||
Ornith 1.0 9Bornith-1.0-9b | 深度强化 | Text | - | 262.1K | - | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-06-25 | |
Open coding-reasoning model for repository tasks and self-improving 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
| ||||||||||||
Fugufugu | Sakana AI | Text | - | 1M | - | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowestNo price | 2026-06-15 | |
Multi-agent model for routing expert agents across complex analytical 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: Not supported Pricing
| ||||||||||||
Fugu Ultrafugu-ultra | Sakana AI | Text | - | 1M | - | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | Official$5 / $30LowestNo price | 2026-06-15 | |
Quality-first multi-agent model for hard research, analysis, and competitions 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: Not supported Pricing
| ||||||||||||
DiffusionGemma 26B A4B ITdiffusiongemma-26b-a4b-it | Text | - | 262.1K | 32.8K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-06-09 | ||
Gemma 4 based discrete text diffusion model for fast chat, reasoning, 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: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Gemma 4 12B ITgemma-4-12b-it | Text | - | 262.1K | 32.8K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-06-09 | ||
Compact Gemma 4 instruction model for open, self-hosted chat and reasoning 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
| ||||||||||||
North Mini Codenorth-mini-code-1-0 | Cohere | Text | - | 256K | 64K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 3.4 | Official$0 / $0LowestNo price | 2026-06-09 | |
Cohere coding model for practical software engineering and agentic edits 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
| ||||||||||||
MiMo-V2.5-Pro-UltraSpeedmimo-v2.5-pro-ultraspeed | Xiaomi | Text | - | 1.05M | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | Official$1.31 / $2.61LowestNo price | 2026-06-08 | |
MiMo pro model for strong multimodal reasoning and agent execution 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 Ultra 550B A55Bnemotron-3-ultra-550b-a55b | Nvidia | Text | - | 1M | 128K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 11.8 | OfficialNo priceLowestNo price | 2026-06-04 | |
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy 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 3.5 Content Safetynemotron-3.5-content-safety | Nvidia | Text | - | 128K | 8.2K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-06-04 | |
Safety model for policy screening, moderation, and risk-aware routing workflows Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
MAI-Code-1-Flashmai-code-1-flash | 微软 | Text | - | 256K | 128K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-06-02 | |
Microsoft coding model built for fast, efficient assistance in everyday developer 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
| ||||||||||||
Nex-N2-Pronex-n2-pro | 奈克斯人工智能 | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-06-02 | |
Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows 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
| ||||||||||||
Command A Pluscommand-a-plus-05-2026 | Cohere | Text | - | 128K | 64K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 6.2 | Official$2.5 / $10LowestNo price | 2026-05-20 | |
Cohere's stronger command model for multilingual agents and enterprise workflows 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
| ||||||||||||
MiniCPM5-1Bminicpm5-1b | OpenBMB | Text | - | 131.1K | 131.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-05-19 | |
Dense 1B-class open-source model for on-device and resource-constrained use, with native long-context support, Think / No Think chat modes, 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: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Perceptron Mk1perceptron-mk1 | 佩尔塞普特龙 | Text | - | 32.8K | 8.2K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: Not supportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-05-12 | |
Multimodal reasoning model for visual analysis, planning, 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: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
GPT Realtime Whispergpt-realtime-whisper | OpenAI | Text | - | 16K | 2K | Audio: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-05-07 | |
Streaming speech-to-text model for low-latency transcript deltas from live audio Basics
Limits
InputText: Not supportedImage: Not supportedAudio: 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
| ||||||||||||
CoBuddycobuddy | 百度 | Text | - | 131.1K | 65.5K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2026-05-06 | |
Baidu Qianfan model optimized for code generation and tool-using coding 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
| ||||||||||||
Mistral Mediummistral-medium-latest | Mistral | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 5.5 | Official$1.5 / $7.5LowestNo price | 2026-04-29 | |
Balanced Mistral model for enterprise assistants, multilingual work, and tools 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 Medium 3.5mistral-medium-2604 | Mistral | Text | - | 262.1K | 262.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 4.6 | Official$1.5 / $7.5LowestNo price | 2026-04-29 | |
Balanced Mistral model for enterprise assistants, multilingual work, and tools 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
| ||||||||||||
Laguna M.1laguna-m.1 | Poolside | Text | - | 262.1K | 32.8K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2026-04-28 | |
Poolside's open-weight model for agentic coding and long-horizon 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
| ||||||||||||
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.