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-Super-120B-A12B

GLM-5 is an advanced, open-source large language model designed for developers tackling the toughest challenges. It excels at long-context reasoning, multi-step tool orchestration, and complex systems engineering, making it the ideal choice for powering sophisticated agents and applications that require high-level cognitive tasks.

GLM-5

  Qwen3-TTS is an advanced text-to-speech model by Alibaba's Qwen team, delivering stable, expressive, and low-latency speech generation across 10 languages.                                                                                                                                                                                                                                                                                                                                           Key capabilities:                                                                                                                                                                                                                                  - 9 preset voices — Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna, Sohee — covering diverse genders, ages, and accents                                                                                                              - Voice cloning — clone any voice from a short (~3s) audio sample via the voice_id parameter   - Instruction control — adjust tone, emotion, and speaking style with natural language (e.g. "speak slowly and calmly", "excited tone")   - 10 languages — English, Chinese, Japanese, Korean, German, French, Russian, Spanish, Italian, Portuguese   - Streaming support — real-time PCM streaming with ~97ms first-byte latency   - Multiple output formats — WAV, MP3, FLAC, PCM    Built on a 1.7B parameter architecture using discrete multi-codebook language modeling for end-to-end speech synthesis without cascading errors. Uses a custom 12Hz acoustic tokenizer that preserves paralinguistic information and   environmental audio details.

Qwen3-TTS

● Qwen3-TTS-VoiceDesign is a voice design variant of Qwen3-TTS by Alibaba's Qwen team. Instead of selecting from preset voices, you describe the voice you want in natural language — and the model generates speech in that voice.                                                                                                                                                                                                                                                                     Key capabilities:                                                                                                                                                                                                                                  - Natural language voice control — describe any voice with free text (e.g. "a deep male voice with a calm, authoritative presence", "a young cheerful female with a warm and friendly tone")   - 10 languages — English, Chinese, Japanese, Korean, German, French, Russian, Spanish, Italian, Portuguese                                                                                                                                         - Streaming support — real-time PCM streaming   - Multiple output formats — WAV, MP3, FLAC, PCM    Built on the same 1.7B parameter architecture as Qwen3-TTS, using discrete multi-codebook language modeling and a custom 12Hz acoustic tokenizer for high-quality end-to-end speech synthesis.

Qwen3-TTS-VoiceDesign

MiniMax M2.5 is SOTA in coding, agentic tool use and search, office work, and a range of other economically valuable tasks, boasting scores of 80.2% in SWE-Bench Verified, 51.3% in Multi-SWE-Bench, and 76.3% in BrowseComp (with context management).

MiniMax-M2.5

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.

Qwen3-Max

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

Qwen3-Max-Thinking

Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.

Kimi-K2.5

GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

GLM-4.7-Flash

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-3-Nano-30B-A3B

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.

DeepSeek-V3.2

Chatterbox is a family of three state-of-the-art, open-source text-to-speech models by Resemble AI.  We are excited to introduce Chatterbox-Turbo, our most efficient model yet. Built on a streamlined 350M parameter architecture, Turbo delivers high-quality speech with less compute and VRAM than our previous models. We have also distilled the speech-token-to-mel decoder, previously a bottleneck, reducing generation from 10 steps to just one, while retaining high-fidelity audio output.  Paralinguistic tags are now native to the Turbo model, allowing you to use [cough], [laugh], [chuckle], and more to add distinct realism. While Turbo was built primarily for low-latency voice agents, it excels at narration and creative workflows.  If you like the model but need to scale or tune it for higher accuracy, check out our competitively priced TTS service (link).

chatterbox-turbo

The fastest model of the Flux 2 family. Frontier visual intelligence — state-of-the-art image generation and editing from Black Forest Labs

FLUX-2-klein-4b

The best quality-to-latency ratio, production apps model of the Flux 2 family. Frontier visual intelligence — state-of-the-art image generation and editing from Black Forest Labs

FLUX-2-klein-9b

Developed by Anthropic, Claude is a family of highly performant, trustworthy AI models built for complex reasoning, advanced coding, and nuanced language understanding. The latest Claude 4 generation delivers breakthrough capabilities in analytical thinking, with Claude 4 Opus setting new standards for intelligence and Claude 4 Sonnet providing exceptional performance with remarkable efficiency.

Claude models excel at understanding context, following complex instructions, and maintaining coherent conversations across extended interactions. With advanced features like extended thinking for deeper reasoning, prompt caching that reduces costs by up to 90%, vision capabilities for image analysis, and robust safety measures, Claude is designed for enterprise applications that demand both sophistication and reliability.

Available with comprehensive API features including streaming responses, batch processing for 50% cost savings, multilingual support across dozens of languages, and flexible context windows up to 200K tokens (1M in beta), Claude is perfect for building intelligent applications like customer support agents, content analysis systems, coding assistants, and complex reasoning workflows that require both accuracy and trustworthiness.

Claude AI family: Claude 4 Opus for complex reasoning, Claude 4 Sonnet for balanced performance, plus advanced capabilities like extended thinking, prompt caching, vision analysis, and enterprise-grade safety APIs.

Claude AI APIs via DeepInfra

claude

Developed by Anthropic, Claude is a family of highly performant, trustworthy AI models built for complex reasoning, advanced coding, and nuanced language understanding

DeepInfra provides access to Anthropic's latest Claude models, featuring the most advanced reasoning capabilities and balanced performance options, all with enterprise-grade safety and reliability.

Claude

DeepSeek develops advanced foundation models optimized for computational efficiency and strong generalization across diverse tasks. The architecture incorporates recent advances in transformer-based systems, delivering robust performance in both zero-shot and fine-tuned scenarios. Models are pretrained on rigorously filtered multilingual corpora with specialized optimizations for mathematical reasoning and algorithmic tasks. The inference stack achieves competitive throughput while maintaining low latency, making it suitable for production deployment. Researchers and engineers can leverage these models for tasks ranging from natural language processing to complex analytical problem-solving.

deepseek

DeepSeek's models are a suite of advanced AI systems that prioritize efficiency, scalability, and real-world applicability.

DeepSeek

Developed by Black Forest Labs (the original creators behind Stable Diffusion), Flux is a family of state-of-the-art image generation and editing models that deliver exceptional visual quality with breakthrough prompt accuracy and photorealism. Built on advanced 12 billion parameter architecture, Flux models excel at understanding exactly what you want to create or modify.
FLUX 2 represents the next generation of the Flux family, introducing significantly improved image quality, faster generation, and more precise prompt following. The lineup includes Max for ultimate quality, Pro for production workflows, and Klein variants (9B and 4B) optimized for speed and efficiency — making high-quality image generation accessible at every scale.
Flux offers specialized variants for every need: from open-source to commercial licensing, Flux is perfect for developers building creative applications, product visualization tools, and next-generation image editing experiences.

Flux AI image generation family: FLUX.1 Kontext for in-context editing, FLUX.1 Pro/Dev for text-to-image synthesis, plus comprehensive editing tools and state-of-the-art visual generation APIs.

Flux Image Generation APIs via DeepInfra

flux

Developed by Black Forest Labs, Flux is a family of state-of-the-art image generation and editing models that deliver exceptional visual quality with breakthrough prompt accuracy and photorealism.

DeepInfra provides access to Black Forest Labs' complete Flux ecosystem, offering everything from lightning-fast generation to sophisticated in-context editing capabilities with industry-leading prompt adherence and visual quality.

Flux

Developed by Google DeepMind, Gemini is a family of state-of-the-art thinking models with native multimodal capabilities, designed for advanced reasoning, complex problem-solving, and comprehensive understanding across text, audio, video, and images. Built with revolutionary thinking architecture, Gemini models reason through problems step-by-step before responding, delivering enhanced accuracy and performance for sophisticated applications.

Gemini 2.5 Pro sets new standards for complex reasoning and coding excellence, while Gemini 2.5 Flash provides optimal price-performance for high-volume tasks. With massive context windows up to 1 million tokens, native multimodal processing that handles hours of video and audio, and transparent reasoning capabilities that show step-by-step thinking processes, Gemini excels at document analysis, code generation, scientific research, and agentic workflows.

Perfect for building intelligent applications that require deep reasoning, multimodal understanding, long-context processing, and transparent AI decision-making with Google's enterprise-grade reliability and performance.


Gemini AI family: Advanced thinking models with native multimodal processing for text, audio, video, and image understanding APIs

Gemini AI Model APIs via DeepInfra

gemini

Developed by Google DeepMind, Gemini is a family of state-of-the-art thinking models with native multimodal capabilities

DeepInfra provides access to Google's latest Gemini models, featuring advanced thinking capabilities, native multimodal processing, and industry-leading performance for complex reasoning and development tasks.

Gemini

Developed by Meta, Llama (Large Language Model Meta AI) is a family of state-of-the-art open-weight models designed for efficiency and performance. The latest versions feature Mixture-of-Experts (MoE) architectures, enabling cost-effective inference by dynamically activating subsets of parameters. With support for multimodal inputs (text + images) and extended context windows (up to 10M tokens), Llama excels in tasks like code generation, multilingual understanding, and long-form reasoning. The models support FP8 quantization and batch inference, ensuring low-latency, high-throughput performance for production workloads. With permissive licensing and robust tooling (e.g., Llama Guard for safety), Llama is ideal for developers seeking powerful, customizable AI with minimal overhead.

llama

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences.

Llama 4

Meta Llama 3 are a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes.

Llama 3

Llama

Developed by Mistral AI, a leading French research lab, Mistral is a family of open-source AI models built for multilingual excellence, advanced reasoning, and cost-effective performance. These models excel at complex reasoning, mathematics, coding, and specialized tasks while offering complete transparency and deployment freedom through open-source licensing.

Mistral Small 3.2 delivers breakthrough efficiency with native fluency in European languages, while specialized variants handle specific needs: Devstral for coding, Voxtral for audio processing, and Mixtral for high-performance tasks. With Apache 2.0 licensing, extensive context windows up to 128K tokens, and comprehensive customization options, Mistral provides enterprise-grade capabilities without vendor lock-in.

Perfect for building multilingual applications, coding assistants, and reasoning systems where you need both powerful performance and complete control over your AI deployment.

Mistral AI model family: Mistral Small 3.2 for efficient performance, Mixtral for specialized tasks, Devstral for coding, plus multilingual reasoning, mathematics, and open-source flexibility APIs.

Mistral AI Model APIs via DeepInfra

mistral

Developed by Mistral AI, a leading French research lab, Mistral is a family of open-source AI models built for multilingual excellence, advanced reasoning, and cost-effective performance

DeepInfra provides access to Mistral AI's comprehensive open-source model ecosystem, from efficient small models to specialized coding and audio processing variants, all with complete Apache 2.0 licensing freedom.

Mistral

Voxtral is a family of audio models with state-of-the-art speech to text capabilities.

Voxtral

[NVIDIA NemotronTM](https://www.nvidia.com/en-us/ai-data-science/foundation-models/nemotron/) is a family of open models, datasets, and training recipes engineered for high performance, efficiency and customization. Nemotron models support synthetic data workflows and supervised fine-tuning — and are equally optimized for real-time inference, reasoning agents, and production AI systems.

nemotron

NVIDIA Nemotron is a family of open models customized for efficiency, accuracy, and specialized workloads.

The Nemotron family spans Nano, Super, and specialized instruct variants, enabling you to balance accuracy, reasoning depth, latency, and cost for your specific workload.
- **Nano** for maximum efficiency and stable inference
- **Super** for multi-agent systems and advance reasoning
- **Instruct variants** for instruction-following and conversational workloads

Nemotron

Developed by Alibaba Group's Qwen Team, Qwen is a family of state-of-the-art large language and multimodal models designed for comprehensive AI capabilities and multilingual performance. The latest Qwen3 generation features balanced model architectures including reintroduced Mixture-of-Experts (MoE) variants (Qwen3-30B-A3B and Qwen3-235B-A22B) alongside dense models up to 32B parameters, enabling efficient resource utilization through dynamic parameter activation. 

With support for 119 languages and dialects, hybrid thinking modes that seamlessly alternate between reasoning and instruction-following without model switching, and extended context windows (up to 1M tokens in Qwen3-2507), Qwen excels in tasks like multilingual understanding, code generation, agentic workflows, and complex problem-solving. The models utilize advanced Byte-level Byte Pair Encoding with a 151,646-token vocabulary, structured ChatML formatting for conversational interactions, and robust tool calling capabilities with parallel execution support. 

Available in both proprietary and open-weight versions with flexible licensing, comprehensive model variants (Base, Instruct, Thinking, and hybrid modes), and enhanced Model Context Protocol support, Qwen is ideal for developers seeking powerful, multilingual AI systems with sophisticated reasoning capabilities and minimal deployment complexity.

Qwen AI model family: Qwen3 language models, specialized coding & reasoning models, plus state-of-the-art embedding & reranking APIs for search and RAG applications.

Qwen Model APIs via DeepInfra

qwen

Qwen series offers a comprehensive suite of dense and mixture-of-experts models.

DeepInfra provides access to Qwen's latest generation of large language models, offering both specialized coding models and general-purpose AI systems with advanced reasoning capabilities.

Qwen

Bria Background Generation allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use.

Seedream 4.0 is a SOTA multimodal image creation model built on leading architecture. It breaks through the boundaries of traditional text-to-image models by natively supporting text, single-image, and multi-image inputs. Users can freely combine text and images to achieve diverse creative modes within a single model—such as multi-image blending, image editing, and sequentially batch image generation, featuring subject consistency, making image creation more free and controllable.

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).

Identify and segment objects across video frames using specific coordinate points. Just point in the right direction and the model will figure out by itself which object should be masked.

Qwen-Image-Edit is a next-generation image editing model built on top of Qwen-Image, designed for both semantic and appearance-level edits. It excels at tasks like precise text modifications, style transfers, viewpoint transformations, and element adjustments while preserving overall visual consistency.

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs  The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.

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.

New model named Chatterbox by Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations.  Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out.

Mixtral is mixture of expert large language model (LLM) from Mistral AI. This is state of the art machine learning model using a mixture 8 of experts (MoE) 7b models. During inference 2 expers are selected. This architecture allows large models to be fast and cheap at inference. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks.

The latest image model, delivering better editing consistency, improved multi-image fusion, finer detail control, natural small text and faces, and harmonious, aesthetic visuals.

The new top-tier image model from Black Forest Labs, significantly pushing image quality and editing consistency

The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc.

The Multilingual-E5-large model is a 24-layer text embedding model with an embedding size of 1024, trained on a mixture of multilingual datasets and supporting 100 languages.

Qwen3-Coder-480B-A35B-Instruct is the Qwen3's most agentic code model, featuring Significant Performance on Agentic Coding, Agentic Browser-Use and other foundational coding tasks, achieving results comparable to Claude Sonnet.

This is the instruction fine-tuned version of Mixtral-8x22B - the latest and largest mixture of experts large language model (LLM) from Mistral AI. This state of the art machine learning model uses a mixture 8 of experts (MoE) 22b models. During inference 2 experts are selected. This architecture allows large models to be fast and cheap at inference.

09/04 🔥 Introducing Chatterbox Multilingual in 23 Languages!  We're excited to introduce Chatterbox and Chatterbox Multilingual, Resemble AI's production-grade open source TTS models. Chatterbox Multilingual supports Arabic, Danish, German, Greek, English, Spanish, Finnish, French, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese, Russian, Swedish, Swahili, Turkish, Chinese out of the box. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations.

Voxtral Mini is an enhancement of Ministral 3B, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.

The DeepSeek R1 0528 turbo model is a state of the art reasoning model that can generate very quick responses

L3.3-70B-Euryale-v2.3 is a model focused on creative roleplay from Sao10k

Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k.  This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.

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.

The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.

The Phi-3-Medium-4K-Instruct is a powerful and lightweight language model with 14 billion parameters, trained on high-quality data to excel in instruction following and safety measures. It demonstrates exceptional performance across benchmarks, including common sense, language understanding, and logical reasoning, outperforming models of similar size.

Identify and segment objects across video frames using a text prompt. The easiest way to create a mask to modify your videos.

olmOCR is a specialized AI tool that converts PDF documents into clean, structured text while preserving important formatting and layout information. What makes olmOCR particularly valuable for developers is its ability to handle challenging PDFs that traditional OCR tools struggle with—including complex layouts, poor-quality scans, handwritten text, and documents with mixed content types. Built on a fine-tuned 7B vision-language model, olmOCR provides enterprise-grade PDF processing at a fraction of the cost of proprietary solutions.

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.

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.  Our model enables highly natural speech generation from text prompts when given a speaker embedding or audio prefix, and can accurately perform speech cloning when given a reference clip spanning just a few seconds. The conditioning setup also allows for fine control over speaking rate, pitch variation, audio quality, and emotions such as happiness, fear, sadness, and anger. The model outputs speech natively at 44kHz.

Gemma is a family of lightweight, state-of-the-art open models from Google. Gemma-2-27B delivers the best performance for its size class, and even offers competitive alternatives to models more than twice its size. 

Black Forest Labs' first flagship model based on Flux latent rectified flow transformers

Whisper is a set of multi-lingual, robust speech recognition models trained by OpenAI that achieve state-of-the-art results in many languages. Whisper models were trained to predict approximate timestamps on speech segments (most of the time with 1-second accuracy), but they cannot originally predict word timestamps. This version has implementation to predict word timestamps and provide a more accurate estimation of speech segments when transcribing with Whisper models.

We introduce StarCoder2-15B-Instruct-v0.1, the very first entirely self-aligned code Large Language Model (LLM) trained with a fully permissive and transparent pipeline. Our open-source pipeline uses StarCoder2-15B to generate thousands of instruction-response pairs, which are then used to fine-tune StarCoder-15B itself without any human annotations or distilled data from huge and proprietary LLMs.

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

The Dolphin 2.6 Mixtral 8x7b model is a finetuned version of the Mixtral-8x7b model, trained on a variety of data including coding data, for 3 days on 4 A100 GPUs. It is uncensored and requires trust_remote_code. The model is very obedient and good at coding, but not DPO tuned. The dataset has been filtered for alignment and bias. The model is compliant with user requests and can be used for various purposes such as generating code or engaging in general chat.

🥳 For a limited time, Fibo Edit is free on DeepInfra 🥳  YOUR AI, YOUR RULES. Visual Generation for Production-Grade. FIBO Edit. An open-source image editing model with native masking and a lightweight 8B architecture.

FLUX.1 Redux [dev] is an image variation generation adapter for all FLUX.1 base models. It enables users to refine images with slight variations and supports text-based restyling via API. Integrated with FLUX1.1 [pro] Ultra, it allows for high-quality 4-megapixel outputs. The model can be used with Diffusers in Python for efficient image generation. While powerful, it has ethical and factual limitations and is governed by a non-commercial license.

Latest version of the Airoboros model fine-tunned version of llama-2-70b using the Airoboros dataset. This model is currently running jondurbin/airoboros-l2-70b-2.2.1 

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.  Other benchmark results include:  AIME 2024: 72.6 | MATH-500: 94.3 | CodeForces Rating: 1691.

Veo 3 Fast is a speed-optimized version of the Veo 3 model, designed for rapid video creation. While maintaining high quality, it delivers results in a fraction of the time, making it ideal for quick iterations and dynamic content generation.

Reflection Llama-3.1 70B is trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.  The model was trained on synthetic data.

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.

Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries. This model reaches Arena Hard of 85.0, AlpacaEval 2 LC of 57.6 and GPT-4-Turbo MT-Bench of 8.98, which are known to be predictive of LMSys Chatbot Arena Elo.  As of 16th Oct 2024, this model is #1 on all three automatic alignment benchmarks (verified tab for AlpacaEval 2 LC), edging out strong frontier models such as GPT-4o and Claude 3.5 Sonnet.

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.

Openchat 3.6 is a LLama-3-8b fine tune that outperforms it on multiple benchmarks.

A LLM-based embedding model with in-context learning capabilities that achieves SOTA performance on BEIR and AIR-Bench. It leverages few-shot examples to enhance task performance.

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

We introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. 

CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes.

A generalist / roleplaying model merge based on Llama 3. Sao10K has carefully selected the values based on extensive personal experimentation and has fine-tuned them to create a customized recipe.

The Multilingual-E5 models, initialized from XLM-RoBERTa, support up to 512 tokens per input — any longer text will be silently truncated. To ensure optimal performance, always prefix inputs with “query:” or “passage:”, as the model was explicitly trained with this format.

This model is a multilingual version of the OpenAI CLIP-ViT-B32 model, which maps text and images to a common dense vector space. It includes a text embedding model that works for 50+ languages and an image encoder from CLIP. The model was trained using Multilingual Knowledge Distillation, where a multilingual DistilBERT model was trained as a student model to align the vector space of the original CLIP image encoder across many languages.

Veo 3.1 is the latest text-to-video model from Google that generates high-fidelity, cinematic videos with synchronized audio from a simple text prompt. It excels at creating realistic and imaginative scenes with a deep understanding of natural language and visual dynamics.

Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, generating text outputs, and comes with 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning, direct preference optimization and RLHF (Reinforcement Learning from Human Feedback) to support precise instruction adherence and safety measures. The languages that each modal supports are the following: - Text: Arabic, Chinese, Czech, Danish, Dutch, English, Finnish, French, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, Turkish, Ukrainian - Vision: English - Audio: English, Chinese, German, French, Italian, Japanese, Spanish, Portuguese

Bria Eraser enables precise removal of unwanted objects from images while maintaining high-quality outputs. Trained exclusively on licensed data for safe and risk-free commercial use

We present a sentence similarity model based on the Sentence Transformers architecture, which maps sentences to a 384-dimensional dense vector space. The model uses a pre-trained BERT encoder and applies mean pooling on top of the contextualized word embeddings to obtain sentence embeddings. We evaluate the model on the Sentence Embeddings Benchmark.

The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out)

Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and extends context capabilities up to 128K tokens while maintaining top-tier text performance. Its 24 billion parameters and instruction fine-tuning deliver fast, local deployment for both text and vision tasks.

Bria Blur Background softens and de-emphasizes image backgrounds while keeping the subject sharp and clear for professional-quality results. Trained fully on licensed data, it delivers safe, natural, and commercial-ready outputs.

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.

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.

WizardLM-2 7B is the smaller variant of Microsoft AI's latest Wizard model. It is the fastest and achieves comparable performance with existing 10x larger open-source leading models

Phi-4-reasoning-plus is a state-of-the-art open-weight reasoning model finetuned from Phi-4 using supervised fine-tuning on a dataset of chain-of-thought traces and reinforcement learning. The supervised fine-tuning dataset includes a blend of synthetic prompts and high-quality filtered data from public domain websites, focused on math, science, and coding skills as well as alignment data for safety and Responsible AI. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning. Phi-4-reasoning-plus has been trained additionally with Reinforcement Learning, hence, it has higher accuracy but generates on average 50% more tokens, thus having higher latency.

A sentence transformation model that has been trained on a wide range of datasets, including but not limited to S2ORC, WikiAnwers, PAQ, Stack Exchange, and Yahoo! Answers. Our model can be used for various NLP tasks such as clustering, sentiment analysis, and question answering.

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.

Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder’s roles in understanding and generation, but also enhances the framework’s flexibility. Janus-Pro surpasses previous unified model and matches or exceeds the performance of task-specific models. The simplicity, high flexibility, and effectiveness of Janus-Pro make it a strong candidate for next-generation unified multimodal models.

Gemma is a family of lightweight, state-of-the-art open models from Google. The 9B Gemma 2 model delivers class-leading performance, outperforming Llama 3 8B and other open models in its size category.

Blazing-fast, high-quality images rendered at five times the speed of Flux. Perfect for mood boards and mass ideation, this model excels in both realism and prompt adherence.

The llama-nemotron-rerank-vl-1b-v2 is a 1.7B parameter multimodal reranking model designed to evaluate and order the relevance of document images and text against specific user queries. It excels at understanding complex visual content like charts, tables, and infographics.

Real-time AI video generation from text, images, and audio. Supports up to 1080p at 48 FPS with built-in audio generation, draft mode for 4x faster previews, and prompt upsampling.

DeepSeek-R1-Distill-Llama-70B is a highly efficient language model that leverages knowledge distillation to achieve state-of-the-art performance. This model distills the reasoning patterns of larger models into a smaller, more agile architecture, resulting in exceptional results on benchmarks like AIME 2024, MATH-500, and LiveCodeBench. With 70 billion parameters, DeepSeek-R1-Distill-Llama-70B offers a unique balance of accuracy and efficiency, making it an ideal choice for a wide range of natural language processing tasks. 

Compared with GLM-4.5, GLM-4.6 brings several key improvements:  Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages. Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability. More capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks. Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.

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

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B)

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.

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

Wan2.6 text to image, Upgraded visual quality, aesthetics, and instruction-following deliver precise style control, realistic portraits, long-text understanding, and broad historical/cultural IP coverage, enabling high-quality, highly expressive visual generation.

P-Image-Edit is a high-precision image editing model that applies complex transformations, insertions, removals, and style adjustments in under a second. It delivers state-of-the-art accuracy, clean boundaries, and reliable prompt alignment, making multi-step edits fast, consistent, and production-ready.

Bria GenFill enables high-quality object addition or visual transformation. Trained exclusively on licensed data for safe and risk-free commercial use.

LLaMa 2 is a collections of LLMs trained by Meta. This is the 70B chat optimized version. This endpoint has per token pricing.

Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes.

Enhanced industrial design and geometric reasoning, improved character consistency, reduced offset issues, and integrated LoRA capabilities

An all-round image generation model that supports joint text–image reasoning, multi-image creative fusion, commercial-grade consistency, aesthetic style transfer, and precise control of framing and lighting, significantly enhancing consistency, controllability, and expressiveness in image generation.

Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper "Robust Speech Recognition via Large-Scale Weak Supervision" by Alec Radford  et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting. Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3. In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4. As a result, the model is way faster, at the expense of a minor quality degradation.

The 72 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.

You can POST to our OpenAI Chat Completions compatible endpoint.

#### Simple messages and prompts

Given a list of messages from a conversation, the model will return a response.

```bash
curl "https://api.deepinfra.com/v1/openai/chat/completions" \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
 -d '{
 "model": "Qwen/Qwen2-72B-Instruct",
 "messages": [
 {
 "role": "user",
 "content": "Hello!"
 }
 ]
 }'
```

To which you'd get something like:

```json
{
 "id": "chatcmpl-guMTxWgpFf",
 "object": "chat.completion",
 "created": 1694623155,
 "model": "Qwen/Qwen2-72B-Instruct",
 "choices": [
 {
 "index": 0,
 "message": {
 "role": "assistant",
 "content": " Hello! It's nice to meet you. Is there something I can help you with or would you like to chat for a bit?"
 },
 "finish_reason": "stop"
 }
 ],
 "usage": {
 "prompt_tokens": 15,
 "completion_tokens": 16,
 "total_tokens": 31,
 "estimated_cost": 0.0000268
 }
}
```

#### Conversations

To create a longer chat-like conversation you just have to add each response message and each of the user messages to every request. This way the model will have the context and will be able to provide better answers. You can tweak it even further by providing a system message.

```bash
curl "https://api.deepinfra.com/v1/openai/chat/completions" \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
 -d '{
 "model": "Qwen/Qwen2-72B-Instruct",
 "messages": [
 {
 "role": "system",
 "content": "Respond like a michelin starred chef."
 },
 {
 "role": "user",
 "content": "Can you name at least two different techniques to cook lamb?"
 },
 {
 "role": "assistant",
 "content": "Bonjour! Let me tell you, my friend, cooking lamb is an art form, and I'"'"'m more than happy to share with you not two, but three of my favorite techniques to coax out the rich, unctuous flavors and tender textures of this majestic protein. First, we have the classic \"Sous Vide\" method. Next, we have the ancient art of \"Sous le Sable\". And finally, we have the more modern technique of \"Hot Smoking.\""
 },
 {
 "role": "user",
 "content": "Tell me more about the second method."
 }
 ]
 }'
```

The conversation above might return something like the following

```json
{
 "id": "chatcmpl-b23a3fb60cde42ce8f24bb980b4dee87",
 "object": "chat.completion",
 "created": 1715688169,
 "model": "Qwen/Qwen2-72B-Instruct",
 "choices": [
 {
 "index": 0,
 "message": {
 "role": "assistant",
 "content": "Sous le Sable, my friend! It's an ancient technique that's been used for centuries in the Middle East and North Africa. The name itself..."
 },
 "finish_reason": "stop"
 }
 ],
 "usage": {
 "prompt_tokens": 149,
 "total_tokens": 487,
 "completion_tokens": 338,
 "estimated_cost": 0.00035493
 }
}
```

The longer the conversation gets, the more time it takes the model to generate the response. The number of messages that you can have in a conversation is limited by the context size of a model. Larger models also usually take more time to respond.

 

### Streaming

You can turn any of the requests above into a streaming request by passing `"stream": true`:

```bash
curl "https://api.deepinfra.com/v1/openai/chat/completions" \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
 -d '{
 "model": "Qwen/Qwen2-72B-Instruct",
 "stream": true,
 "messages": [
 {
 "role": "user",
 "content": "Hello!"
 }
 ]
 }'
```

to which you'd get a sequence of [SSE](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events) events, finishing with `[DONE]`.

```
data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "Qwen/Qwen2-72B-Instruct", "choices": [{"index": 0, "delta": {"role": "assistant", "content": " "}, "finish_reason": null}]}

data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "Qwen/Qwen2-72B-Instruct", "choices": [{"index": 0, "delta": {"role": "assistant", "content": " Hi"}, "finish_reason": null}]}

data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "Qwen/Qwen2-72B-Instruct", "choices": [{"index": 0, "delta": {"role": "assistant", "content": "!"}, "finish_reason": null}]}

data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "Qwen/Qwen2-72B-Instruct", "choices": [{"index": 0, "delta": {"role": "assistant", "content": ""}, "finish_reason": null}]}

data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "Qwen/Qwen2-72B-Instruct", "choices": [{"index": 0, "delta": {"role": "assistant", "content": "</s>"}, "finish_reason": null}]}

data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "Qwen/Qwen2-72B-Instruct", "choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}]}

data: [DONE]
```

You can use the official openai python client to run inferences with us

```python
# Assume openai>=1.0.0
from openai import OpenAI

# Create an OpenAI client with your deepinfra token and endpoint
openai = OpenAI(
 api_key="$DEEPINFRA_TOKEN",
 base_url="https://api.deepinfra.com/v1/openai",
)

chat_completion = openai.chat.completions.create(
 model="Qwen/Qwen2-72B-Instruct",
 messages=[{"role": "user", "content": "Hello"}],
)

print(chat_completion.choices[0].message.content)
print(chat_completion.usage.prompt_tokens, chat_completion.usage.completion_tokens)

# Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?
# 11 25
```

#### Conversations

To create a longer chat-like conversation you just have to add each response message and each of the user messages to every request. This way the model will have the context and will be able to provide better answers. You can tweak it even further by providing a system message.

```python
# Assume openai>=1.0.0
from openai import OpenAI

# Create an OpenAI client with your deepinfra token and endpoint
openai = OpenAI(
 api_key="$DEEPINFRA_TOKEN",
 base_url="https://api.deepinfra.com/v1/openai",
)

chat_completion = openai.chat.completions.create(
 model="Qwen/Qwen2-72B-Instruct",
 messages=[
 {"role": "system", "content": "Respond like a michelin starred chef."},
 {"role": "user", "content": "Can you name at least two different techniques to cook lamb?"},
 {"role": "assistant", "content": "Bonjour! Let me tell you, my friend, cooking lamb is an art form, and I'm more than happy to share with you not two, but three of my favorite techniques to coax out the rich, unctuous flavors and tender textures of this majestic protein. First, we have the classic \"Sous Vide\" method. Next, we have the ancient art of \"Sous le Sable\". And finally, we have the more modern technique of \"Hot Smoking.\""},
 {"role": "user", "content": "Tell me more about the second method."},
 ],
)

print(chat_completion.choices[0].message.content)
print(chat_completion.usage.prompt_tokens, chat_completion.usage.completion_tokens)

# Sous le Sable! It's an ancient technique that never goes out of style, n'est-ce pas? Literally ...
# 149 324
```

The longer the conversation gets, the more time it takes the model to generate the response. The number of messages that you can have in a conversation is limited by the context size of a model. Larger models also usually take more time to respond.

 

### Streaming

Streaming any of the chat completions above is supported by adding the `stream=True` option.


```python
from openai import OpenAI

# Create an OpenAI client with your deepinfra token and endpoint
openai = OpenAI(
 api_key="$DEEPINFRA_TOKEN",
 base_url="https://api.deepinfra.com/v1/openai",
)

chat_completion = openai.chat.completions.create(
 model="Qwen/Qwen2-72B-Instruct",
 messages=[{"role": "user", "content": "Hello"}],
 stream=True,
)

for event in chat_completion:
 if event.choices[0].finish_reason:
 print(event.choices[0].finish_reason, event.usage["prompt_tokens"], event.usage["completion_tokens"])
 else:
 print(event.choices[0].delta.content)

# Hello
# !
# It
# 's
# nice
# ...
# 11 25
```

You can use JavaScript in the browser or in node.js to make requests

```bash
npm install openai
```

then

```javascript
import OpenAI from "openai";

const openai = new OpenAI({
 baseURL: 'https://api.deepinfra.com/v1/openai',
 apiKey: "$DEEPINFRA_TOKEN",
});

async function main() {
 const completion = await openai.chat.completions.create({
 messages: [{ role: "user", content: "Hello" }],
 model: "Qwen/Qwen2-72B-Instruct",
 });

 console.log(completion.choices[0].message.content);
 console.log(completion.usage.prompt_tokens, completion.usage.completion_tokens);
}

main();

// Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?
// 11 25
```

#### Conversations

To create a longer chat-like conversation you just have to add each response message and each of the user messages to every request. This way the model will have the context and will be able to provide better answers. You can tweak it even further by providing a system message.

```javascript
import OpenAI from "openai";

const openai = new OpenAI({
 baseURL: 'https://api.deepinfra.com/v1/openai',
 apiKey: "$DEEPINFRA_TOKEN",
});

async function main() {
 const completion = await openai.chat.completions.create({
 messages: [
 {role: "system", content: "Respond like a michelin starred chef."},
 {role: "user", content: "Can you name at least two different techniques to cook lamb?"},
 {role: "assistant", content: "Bonjour! Let me tell you, my friend, cooking lamb is an art form, and I'm more than happy to share with you not two, but three of my favorite techniques to coax out the rich, unctuous flavors and tender textures of this majestic protein. First, we have the classic \"Sous Vide\" method. Next, we have the ancient art of \"Sous le Sable\". And finally, we have the more modern technique of \"Hot Smoking.\""},
 {role: "user", "content": "Tell me more about the second method."}
 ],
 model: "Qwen/Qwen2-72B-Instruct",
 });

 console.log(completion.choices[0].message.content);
 console.log(completion.usage.prompt_tokens, completion.usage.completion_tokens);
}

main();

// Sous le Sable, my friend! This traditional technique hails from the ancient Mediterranean, wher...
// 149 324
```

The longer the conversation gets, the more time it takes the model to generate the response. The number of messages that you can have in a conversation is limited by the context size of a model. Larger models also usually take more time to respond.

 

### Streaming

Streaming any of the chat completions above is supported by adding the `stream: true` option.

```javascript
import OpenAI from "openai";

const openai = new OpenAI({
 baseURL: 'https://api.deepinfra.com/v1/openai',
 apiKey: "$DEEPINFRA_TOKEN",
});

async function main() {
 const completion = await openai.chat.completions.create({
 messages: [{ role: "user", content: "Hello" }],
 model: "Qwen/Qwen2-72B-Instruct",
 stream: true,
 });

 for await (const chunk of completion) {
 if (chunk.choices[0].finish_reason) {
 console.log(chunk.choices[0].finish_reason, chunk.usage.prompt_tokens, chunk.usage.completion_tokens);
 } else {
 console.log(chunk.choices[0].delta.content);
 }
 }
}

main();

// Hello
// !
// It
// 's
// nice
// ...
// 11 25
```

The [AI SDK](https://sdk.vercel.ai/) by Vercel makes it very easy to do inference.

```bash
npm install ai @ai-sdk/deepinfra
```

then

```javascript
import { createDeepInfra } from "@ai-sdk/deepinfra";
import { generateText } from "ai";

const deepinfra = createDeepInfra({
 apiKey: "$DEEPINFRA_TOKEN",
});

const { text, usage, finishReason } = await generateText({
 model: deepinfra("Qwen/Qwen2-72B-Instruct"),
 prompt: "Write a vegetarian lasagna recipe for 4 people.",
});

console.log(text);
console.log(usage);
console.log(finishReason);
```

#### Conversations

To create a longer chat-like conversation you just have to add each response message and each of the user messages to every request. This way the model will have the context and will be able to provide better answers. You can tweak it even further by providing a system message.

```javascript
import { createDeepInfra } from "@ai-sdk/deepinfra";
import { generateText } from "ai";

const deepinfra = createDeepInfra({
 apiKey: "$DEEPINFRA_TOKEN",
});

const { text, usage, finishReason } = await generateText({
 model: deepinfra("Qwen/Qwen2-72B-Instruct"),
 messages: [
 { role: "system", content: "Respond like a michelin starred chef." },
 {
 role: "user",
 content: "Can you name at least two different techniques to cook lamb?",
 },
 {
 role: "assistant",
 content:
 'Bonjour! Let me tell you, my friend, cooking lamb is an art form, and I\'m more than happy to share with you not two, but three of my favorite techniques to coax out the rich, unctuous flavors and tender textures of this majestic protein. First, we have the classic "Sous Vide" method. Next, we have the ancient art of "Sous le Sable". And finally, we have the more modern technique of "Hot Smoking."',
 },
 { role: "user", content: "Tell me more about the second method." },
 ],
});

console.log(text);
console.log(usage);
console.log(finishReason);
```

The longer the conversation gets, the more time it takes the model to generate the response. The number of messages that you can have in a conversation is limited by the context size of a model. Larger models also usually take more time to respond.

 

### Streaming

Streaming text responses is easy just replace `generateText` with `streamText` and read the response chunk by chunk

```javascript
import { createDeepInfra } from "@ai-sdk/deepinfra";
import { streamText } from "ai";

const deepinfra = createDeepInfra({
 apiKey: "$DEEPINFRA_TOKEN",
});

const result = streamText({
 model: deepinfra("meta-llama/Llama-3.3-70B-Instruct-Turbo"),
 prompt: "Invent a new holiday and describe its traditions.",
 system:
 "You are a professional writer. You write simple, clear, and concise content.",
});

for await (const textPart of result.textStream) {
 console.log(textPart);
}

console.log(await result.usage);
console.log(await result.finishReason);
```

It works for conversations, too.

This is an advanced and more complex API. We strongly recommend that you use OpenAI Chat Completions instead.

#### Simple prompt

To query this model you need to provide a properly formatted input string.

```bash
curl "https://api.deepinfra.com/v1/inference/Qwen/Qwen2-72B-Instruct" \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
 -d '{
 "input": "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nHello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
 "stop": []
 }'
```

That will respond with

```json
{
 "request_id": "RWZDRhS5kdoM1XWwXLEshynO",
 "inference_status": {
 "status": "succeeded",
 "runtime_ms": 243,
 "cost": 0.0000436,
 "tokens_input": 12,
 "tokens_generated": 25
 },
 "results": [
 {
 "generated_text": "Hello! It's nice to meet you. Is there something I can help you with or would you like to chat for a bit?"
 }
 ],
 "num_tokens": 25,
 "num_input_tokens":12
}
```

#### Conversations

The OpenAI Chat Completions API is better suited for chat-like conversations, use it instead.

To query this model you need to provide a properly formatted input string.

However, you can still do it if you really need to. You have to add each response and each of the user prompts to every request.
You need a properly formatted input string to make it understand the current context. See the example below for some of them.
You can tweak it even further by providing a system message.

```bash
curl "https://api.deepinfra.com/v1/inference/Qwen/Qwen2-72B-Instruct" \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
 -d '{
 "input": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nRespond like a michelin starred chef.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nCan you name at least two different techniques to cook lamb?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nBonjour! Let me tell you, my friend, cooking lamb is an art form, and I'"'"'m more than happy to share with you not two, but three of my favorite techniques to coax out the rich, unctuous flavors and tender textures of this majestic protein. First, we have the classic \"Sous Vide\" method. Next, we have the ancient art of \"Sous le Sable\". And finally, we have the more modern technique of \"Hot Smoking.\"<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nTell me more about the second method.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
 "stop": []
 }'
```

The conversation above might return something like the following

```json
{
 "request_id": "RWZDRhS5kdoM1XWwXLEshynO",
 "inference_status": {
 "status": "succeeded",
 "runtime_ms": 243,
 "cost": 0.000436,
 "tokens_input": 149,
 "tokens_generated": 338
 },
 "results": [
 {
 "generated_text": "Sous le Sable, my friend! It's an ancient technique that's been used for centuries in the Middle East and North Africa. The name itself..."
 }
 ],
 "num_tokens": 338,
 "num_input_tokens": 149
}
```

The longer the conversation gets, the more time it takes the model to generate the response. The conversation is limited by the context size of a model. Larger models also usually take more time to respond.

 

### Streaming


To do a streaming request, just pass `"stream": true`:

```bash
curl "https://api.deepinfra.com/v1/inference/Qwen/Qwen2-72B-Instruct" \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
 -d '{
 "input": "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nHello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
 "stop": [],
 "stream": true
 }'
```

which outputs:

```json
data: {"token": {"id": null, "text": "Hello", "logprob": 0.0, "special": false}, "generated_text": "", "details": null, "estimated_cost": null}

data: {"token": {"id": null, "text": "!", "logprob": 0.0, "special": false}, "generated_text": "", "details": null, "estimated_cost": null}

data: {"token": {"id": null, "text": " It", "logprob": 0.0, "special": false}, "generated_text": "", "details": null, "estimated_cost": null}

data: {"token": {"id": null, "text": "'s", "logprob": 0.0, "special": false}, "generated_text": "", "details": null, "estimated_cost": null}

....

data: {"token": {"id": null, "text": "", "logprob": 0.0, "special": false}, "generated_text": null, "details": {"finish_reason": "stop"}, "num_output_tokens": 25, "num_input_tokens": 12, "estimated_cost": 0.0000386}
```

#### Input format

You can see below the basic format of the input. Bear in mind that newlines often matter.

```text
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

Hello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

Conversation prompts contain the history of the exchanged prompts and responses.

```text
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

First question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

First answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Second question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Second answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Final question<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

If you want to add system prompt, it is done like this

```text
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

System prompt<|eot_id|><|start_header_id|>user<|end_header_id|>

First question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

First answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Second question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Second answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Final question<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

You can use our command-line tool [deepctl](/docs/getting-started) to run inferences:

This is an advanced and more complex API. We strongly recommend that you use OpenAI Chat Completions instead.

#### Simple prompt

To query this model you need to provide a properly formatted input string.

```bash
deepctl infer \
 -m 'Qwen/Qwen2-72B-Instruct' \
 -i 'input="<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nHello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"' \
 -i 'stop=[]'
```

That will respond with

```json
{
 "inference_status": {
 "status": "succeeded",
 "runtime_ms": 243,
 "cost": 0.0000436,
 "tokens_input": 12,
 "tokens_generated": 25
 },
 "results": [
 {
 "generated_text": "Hello! It's nice to meet you. Is there something I can help you with or would you like to chat for a bit?"
 }
 ],
 "num_tokens": 25,
 "num_input_tokens":12
}
```

#### Conversations

The OpenAI Chat Completions API is better suited for chat-like conversations, use it instead.

To query this model you need to provide a properly formatted input string.

However, you can still do it if you really need to. You have to add each response and each of the user prompts to every request.
You need a properly formatted input string to make it understand the current context. See the example below for some of them.
You can tweak it even further by providing a system message.

```bash
deepctl infer \
 -m 'Qwen/Qwen2-72B-Instruct' \
 -i 'input="<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nRespond like a michelin starred chef.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nCan you name at least two different techniques to cook lamb?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nBonjour! Let me tell you, my friend, cooking lamb is an art form, and I'"'"'m more than happy to share with you not two, but three of my favorite techniques to coax out the rich, unctuous flavors and tender textures of this majestic protein. First, we have the classic \"Sous Vide\" method. Next, we have the ancient art of \"Sous le Sable\". And finally, we have the more modern technique of \"Hot Smoking.\"<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nTell me more about the second method.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"' \
 -i 'stop=[]'
```

The conversation above might return something like the following

```json
{
 "inference_status": {
 "status": "succeeded",
 "runtime_ms": 243,
 "cost": 0.000436,
 "tokens_input": 149,
 "tokens_generated": 338
 },
 "results": [
 {
 "generated_text": "Sous le Sable, my friend! It's an ancient technique that's been used for centuries in the Middle East and North Africa. The name itself..."
 }
 ],
 "num_tokens": 338,
 "num_input_tokens": 149
}
```

The longer the conversation gets, the more time it takes the model to generate the response. The conversation is limited by the context size of a model. Larger models also usually take more time to respond.

#### Input format

You can see below the basic format of the input. Bear in mind that newlines often matter.

```text
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

Hello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

Conversation prompts contain the history of the exchanged prompts and responses.

```text
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

First question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

First answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Second question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Second answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Final question<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

If you want to add system prompt, it is done like this

```text
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

System prompt<|eot_id|><|start_header_id|>user<|end_header_id|>

First question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

First answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Second question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Second answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Final question<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

We recommend using our NodeJS client https://github.com/deepinfra/deepinfra-node.

You can install it with

```bash
npm install deepinfra
```

#### Simple prompt

To query this model you need to provide a properly formatted input string.

```javascript
import { TextGeneration } from "deepinfra";

const DEEPINFRA_API_KEY = '$DEEPINFRA_TOKEN';
const MODEL_URL = 'https://api.deepinfra.com/v1/inference/Qwen/Qwen2-72B-Instruct';

async function main() {
 const client = new TextGeneration(MODEL_URL, DEEPINFRA_API_KEY);
 const res = await client.generate({
 "input": "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nHello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
 "stop": []
 });
 console.log(res.results[0].generated_text);
}

main();

// Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?
```

#### Conversations

The OpenAI Chat Completions API is better suited for chat-like conversations, use it instead.

However, you can still do it if you really need to. You have to add each response and each of the user prompts to every request.
You need a properly formatted input string to make it understand the current context. See the example below for some of them.
You can tweak it even further by providing a system message.

```javascript
import { TextGeneration } from "deepinfra";

const DEEPINFRA_API_KEY = '$DEEPINFRA_TOKEN';
const MODEL_URL = 'https://api.deepinfra.com/v1/inference/Qwen/Qwen2-72B-Instruct';

async function main() {
 const client = new TextGeneration(MODEL_URL, DEEPINFRA_API_KEY);
 const res = await client.generate({
 "input": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nRespond like a michelin starred chef.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nCan you name at least two different techniques to cook lamb?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nBonjour! Let me tell you, my friend, cooking lamb is an art form, and I'm more than happy to share with you not two, but three of my favorite techniques to coax out the rich, unctuous flavors and tender textures of this majestic protein. First, we have the classic \"Sous Vide\" method. Next, we have the ancient art of \"Sous le Sable\". And finally, we have the more modern technique of \"Hot Smoking.\"<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nTell me more about the second method.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
 "stop": []
 });
 console.log(res.results[0].generated_text);
}

main();

// Sous le Sable! It's an ancient technique that never goes out of style, n'est-ce pas? Literally ...
```

The longer the conversation gets, the more time it takes the model to generate the response.
The number of messages that you can have in a conversation is limited by the context size of a model.
Larger models also usually take more time to respond.

#### Input format

You can see below the basic format of the input. Bear in mind that newlines often matter.

```text
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

Hello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

Conversation prompts contain the history of the exchanged prompts and responses.

```text
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

First question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

First answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Second question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Second answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Final question<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

If you want to add system prompt, it is done like this

```text
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

System prompt<|eot_id|><|start_header_id|>user<|end_header_id|>

First question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

First answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Second question<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Second answer<|eot_id|><|start_header_id|>user<|end_header_id|>

Final question<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

input

maximum length of the newly generated generated text.If explicitly set to None it will be the model's max context length minus input length or 16384, whichever is smaller

max_new_tokens

temperature to use for sampling. 0 means the output is deterministic. Values greater than 1 encourage more diversity

temperature

Sample from the set of tokens with highest probability such that sum of probabilies is higher than p. Lower values focus on the most probable tokens.Higher values sample more low-probability tokens

top_p

Float that represents the minimum probability for a token to be considered, relative to the probability of the most likely token. Must be in [0, 1]. Set to 0 to disable this.

min_p

Sample from the best k (number of) tokens. 0 means off

top_k

repetition penalty. Value of 1 means no penalty, values greater than 1 discourage repetition, smaller than 1 encourage repetition.

repetition_penalty

Up to 16 strings that will terminate generation immediately

stop

Number of output sequences to return. Incompatible with streaming

num_responses

Optional nested object with "type" set to "json_object"

response_format

Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

presence_penalty

Positive values penalize new tokens based on how many times they appear in the text so far, increasing the model's likelihood to talk about new topics.

frequency_penalty

A unique identifier representing your end-user, which can help monitor and detect abuse. Avoid sending us any identifying information. We recommend hashing user identifiers.

user

Seed for random number generator. If not provided, a random seed is used. Determinism is not guaranteed.

seed

A key to identify prompt cache for reuse across requests. If provided, the prompt will be cached and can be reused in subsequent requests with the same key.

prompt_cache_key

The webhook to call when inference is done, by default you will get the output in the response of your inference request