DeepInfra

GLM 5.2 running in a Trusted Execution Environment (TEE). Z.AI's flagship model for long-horizon tasks with enhanced reasoning and project-level engineering context, with hardware attestation evidence available for independent verification.

Gemma 4 31B served in a Tinfoil verified confidential enclave.

Kimi K3 served in a Tinfoil verified confidential enclave.

OpenAI GPT OSS 120B served in a Tinfoil verified confidential enclave.

DeepSeek-V3.2 is an efficient large language model with DeepSeek Sparse Attention (DSA) for long contexts. It features strong reasoning and tool-use skills, achieving top results on the 2025 IMO and IOI.

DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.

DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.

Hermes 3 405B is a frontier level, full parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.

Kimi K2.6 is an open-source, native multimodal agentic model from Moonshot AI with 1T total parameters and 32B active parameters. It excels at long-horizon coding, coding-driven design, agent swarm orchestration, and proactive autonomous execution with 256K context windows.

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6, with 1T total parameters and 32B active parameters. It always operates in thinking mode, supports text and image input, and targets long-horizon software engineering, agentic task decomposition, and multi-turn coding workflows with 256K context.

NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context.

Built for in-depth research and handling long, complex documents. Ideal for technical work, multimodal input, and high-precision tasks.

Turbo variant of Qwen3 Coder 480B, optimized for faster inference on code tasks.

Optimized for speed and efficiency.

Qwen 3.5 35B A3B is a highly efficient MoE model with 35B total parameters and only 3B active parameters. It surpasses the larger Qwen3-235B-A22B while being 6.7x smaller, excelling at reasoning, coding, and general knowledge tasks.

A 9B dense model with 262K native context window (extendable to 1M). Features Gated DeltaNet hybrid attention architecture for efficient long-context processing. Supports 201 languages, thinking/reasoning mode, and function calling.

The Qwen 3.6 27B native vision-language dense model builds upon the 3.5-27B version, with key improvements in agentic coding capabilities and enhanced STEM reasoning and inference skills. In the vision modality, it demonstrates significant advances in spatial intelligence, object localization, and detection, while video understanding, document OCR, and visual agent capabilities continue to improve steadily.

Qwen 3.6 35B A3B is a fast mixture-of-experts model with 35B total parameters and ~3B active per token. Strong at agentic coding, STEM reasoning, and tool use, with a native 256K context window.

Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window.

Qwen3-VL 235B vision-language model with MoE architecture. The most powerful VL model in the Qwen series with superior visual perception, OCR, and multimodal reasoning.

Inkling is a general-purpose multimodal model from Thinking Machines Lab that accepts text, image, and audio inputs and generates text. It is a 66-layer sparse MoE (975B total / 41B active) with hybrid local/global attention, 512K context, and variable thinking effort — suited for chat, coding, tool use, and agentic workflows. Video input is not supported on Venice.

GLM-4.6 is a large language model developed by Zhiyuan AI, featuring strong reasoning capabilities and support for multiple languages. Supports the largest context window for processing extensive text and detailed analysis.

GLM-4.7 is a large language model developed by Zhiyuan AI, featuring strong reasoning capabilities and support for multiple languages. Supports the largest context window for processing extensive text and detailed analysis.

GLM-5.1 is the next-generation large language model developed by Zhiyuan AI, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports large context windows for processing extensive text and detailed analysis with fast inference speed.

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.

GLM-5.3 Flash is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with visual context.

The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528.

DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2.

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.

DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window. It's tuned for fast inference and high-throughput use cases while still holding up on reasoning and coding tasks.

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities. DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.

DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and supports image input with visual grounding, tool calling, structured/JSON output, and configurable reasoning effort (low/high/max, or disabled).

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3-12B is Google's latest open source model, successor to Gemma 2

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3-12B is Google's latest open source model, successor to Gemma 2

Efficient, MoE variant of Gemma 4. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.

gemma 4 E4B it served on DeepInfra serverless inference.

MythoMax L2 13b served on DeepInfra serverless inference.

Granite-4.2-30B is the flagship reasoning model in the Granite 4.2 family. It delivers the strongest performance across reasoning-intensive tasks by leveraging built-in <think>...</think> chain-of-thought. It supports flexible thinking modes — full thinking (default), non-thinking, and low-effort — allowing users to balance depth vs. latency on a per-query basis.

Granite-4.2-3B is the compact reasoning model in the Granite 4.2 family. Despite its small parameter count, it delivers strong performance on reasoning-intensive tasks by leveraging built-in <think>...</think> chain-of-thought. It supports flexible thinking modes — full thinking (default), non-thinking, and low-effort — allowing users to balance depth vs. latency on a per-query basis.

Granite-4.2-8B is the mid-size reasoning model in the Granite 4.2 family. It delivers strong performance on reasoning-intensive tasks by leveraging built-in <think>...</think> chain-of-thought. It supports flexible thinking modes — full thinking (default), non-thinking, and low-effort — allowing users to balance depth vs. latency on a per-query basis.

The model prioritizes token efficiency and agentic inference at production scale, stretching what developers can achieve within limited token, latency, and serving-cost budgets.

Ling-3.0-flash-Fin is the first finance-enhanced model in the Ant Ling family. Developed by Ant Group with leading financial institutions and domain experts, it extends Ling-3.0-flash through continued training on high-quality financial data.

Llama 3.3-70B Turbo is a highly optimized version of the Llama 3.3-70B model, utilizing FP8 quantization to deliver significantly faster inference speeds with a minor trade-off in accuracy. The model is designed to be helpful, safe, and flexible, with a focus on responsible deployment and mitigating potential risks such as bias, toxicity, and misinformation. It achieves state-of-the-art performance on various benchmarks, including conversational tasks, language translation, and text generation.

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. Llama 4 Maverick, a 17 billion parameter model with 128 experts

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. Llama 4 Scout, a 17 billion parameter model with 16 experts

Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It itself acts as an LLM: it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.

Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes

Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes

Muse Glimmer is a 30B multimodal agentic model distilled from Muse Spark — reasoning, tool use, and failure recovery in a single model that runs locally on consumer hardware.

Phi-4 is a model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning.

MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware.

Mistral-Small-3.2-24B-Instruct is a drop-in upgrade over the 3.1 release, with markedly better instruction following, roughly half the infinite-generation errors, and a more robust function-calling interface—while otherwise matching or slightly improving on all previous text and vision benchmarks.

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.

NVIDIA Nemotron 3 Nano is an open small reasoning model optimized for fast, cost-efficient inference in agentic and production workloads. Built with a hybrid Mixture-of-Experts (MoE) and Mamba-Transformer architecture, it delivers strong multi-step reasoning, high token throughput, stable latency with predictable cost, and efficient deployment for agent-based systems. Designed for real-world AI systems where reasoning can generate significantly more tokens per prompt, Nemotron Nano reduces compute cost while maintaining strong reasoning quality.

Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, and can be used as an inference-time guardrail, as a judge for LLM safety testing and evaluation, or with the accompanying training dataset to post-train models for safer behavior.

NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.

gpt oss 120b Turbo served on DeepInfra serverless inference.

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling with MCP integration, and support for 201 languages. Sets state-of-the-art results on reasoning, coding, math, and multimodal benchmarks.

Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilingual capabilities for over 29 languages.

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

Qwen3.5-122B-A10B is a large Mixture-of-Experts model from Alibaba's Qwen3.5 series with 122B total parameters and 10B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Excels at complex reasoning, coding, multimodal understanding, and agentic tasks with the efficiency of sparse activation.

Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance.

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.

L3 8B Lunaris v1 Turbo served on DeepInfra serverless inference.

Euryale 3.1 - 70B v2.2 is a model focused on creative roleplay from Sao10k

Step 3.7 Flash is an open-source multimodal reasoning model by StepFun with 198B total parameters (11B active) using Mixture of Experts. It accepts text and image inputs and features a 256K context window, selectable reasoning effort, tool calling, and agentic capabilities for coding and search workflows, scoring 80.9% on GPQA Diamond and 56.3% on SWE-bench Pro.

Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data. Today, we introduce Hy3, which outperforms similar-size models and rivals flagship open-source models with 2-5x parameters. It also shows significant gains in utility across various products and productivity tasks.

Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable thinking effort

MiMo-V2.5-Pro is an open-source Mixture-of-Experts (MoE) language model with 1.02T total parameters and 42B active parameters. It utilizes the hybrid attention architecture and 3-layers Multi-Token Prediction (MTP) introduced in [MiMo-V2-Flash](https://github.com/XiaomiMiMo/MiMo-V2-Flash).

Claude Fable 5 is Anthropic's most capable widely released model, designed for demanding reasoning and long-horizon agentic work. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities.

Claude Opus 4.7 is Anthropic's most capable generally available model for complex reasoning and agentic coding. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.

Claude Opus 5 is Anthropic's most capable model in the Opus family. It delivers major gains over Opus 4.8 in agentic coding, professional knowledge work, and long-horizon reasoning, with a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.

Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency. It features a 1M token context window and 64K max output tokens.

Claude Sonnet 5 is Anthropic's latest Sonnet model, substantially improving on Sonnet 4.6 in coding and agentic work and reaching near-Opus quality on many tasks. It features a 1M token context window, adaptive thinking, and strong document and vision understanding.

Gemini 3.5 Flash is a high speed, high value thinking model with 1M context, designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.

Gemini 3.7 Flash is Google's most capable Flash model, built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.

Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.

Qwen 3.8 Max is Alibaba's flagship 2.4-trillion-parameter MoE model, with major gains over Qwen 3.7 Max in software engineering and office-productivity workflows and strong long-horizon, multi-agent performance. It accepts both text and vision-language input (images and video), operates in thinking mode only, and supports a 1M-token context window.

The next generation of Anthropic's fastest and most cost-effective model, optimal for use cases where speed and affordability matter.

Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.

A coding model optimized for real-world development environments, with reliable tool use in common IDEs such as Claude Code. It delivers strong front-end performance and supports Skills.

Built for low-latency, high-concurrency, cost-sensitive use cases, with flexible deployment, four-tier thinking, and multimodal

Built for the Agent era, it delivers stable performance in complex reasoning and long-horizon tasks, including multi-step planning, visual-text reasoning, video understanding, and advanced analysis.

Gemini 2.5 Flash is Google's latest thinking model, designed to tackle increasingly complex problems. It's capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accuracy. Gemini 2.5 Flash: best for balancing reasoning and speed.

Bring any idea to life with state-of-the-art reasoning to help you learn, build, and plan anything. Best for high-volume tasks that need efficiency and intelligence.

Bring any idea to life with state-of-the-art reasoning to help you learn, build, and plan anything. Best for complex tasks and bringing creative concepts to life.

Ultra speed version of gemma-4-31B-it

Speed-optimized MiniMax-M2.7

Ultra speed version of gpt-oss-120b

The latest flagship model in the Qwen family. State-of-the-art results across a comprehensive suite of benchmarks — including knowledge, reasoning, coding, instruction following, human preference alignment, agent tasks, and multilingual understanding.

The latest flagship reasoning model in the Qwen3 family. Further enhanced by multiple innovations like adaptive tool-use and advanced test-time scaling techniques