We use essential cookies to make our site work. With your consent, we may also use non-essential cookies to improve user experience and analyze website traffic…

Browse deepinfra models:

All categories and models you can try out and directly use in deepinfra:
Search

Category/text-generation

Text generation AI models can generate coherent and natural-sounding human language text, making them useful for a variety of applications from language translation to content creation.

There are several types of text generation AI models, including rule-based, statistical, and neural models. Neural models, and in particular transformer-based models like GPT, have achieved state-of-the-art results in text generation tasks. These models use artificial neural networks to analyze large text corpora and learn the patterns and structures of language.

While text generation AI models offer many exciting possibilities, they also present some challenges. For example, it's essential to ensure that the generated text is ethical, unbiased, and accurate, to avoid potential harm or negative consequences.

deepseek-ai/DeepSeek-R1-Distill-Llama-70B cover image
featured
fp8
128k
$0.10/$0.40 in/out Mtoken
  • text-generation

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.

deepseek-ai/DeepSeek-V3 cover image
featured
fp8
160k
$0.38/$0.89 in/out Mtoken
  • text-generation

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.

meta-llama/Llama-3.3-70B-Instruct-Turbo cover image
featured
fp8
128k
$0.07/$0.25 in/out Mtoken
  • text-generation

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.

meta-llama/Llama-3.3-70B-Instruct cover image
featured
bfloat16
128k
$0.23/$0.40 in/out Mtoken
  • text-generation

Llama 3.3-70B is a multilingual LLM trained on a massive dataset of 15 trillion tokens, fine-tuned for instruction-following and conversational dialogue. 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.

mistralai/Mistral-Small-24B-Instruct-2501 cover image
featured
fp8
32k
$0.06/$0.12 in/out Mtoken
  • text-generation

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.

microsoft/phi-4 cover image
featured
bfloat16
16k
$0.07/$0.14 in/out Mtoken
  • text-generation

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.

Austism/chronos-hermes-13b-v2 cover image
fp16
4k
Replaced
  • text-generation

This offers the imaginative writing style of chronos while still retaining coherency and being capable. Outputs are long and utilize exceptional prose. Supports a maxium context length of 4096. The model follows the Alpaca prompt format.

Gryphe/MythoMax-L2-13b-turbo cover image
fp8
4k
Replaced
  • text-generation

Faster version of Gryphe/MythoMax-L2-13b running on multiple H100 cards in fp8 precision. Up to 160 tps.

KoboldAI/LLaMA2-13B-Tiefighter cover image
fp16
4k
Replaced
  • text-generation

LLaMA2-13B-Tiefighter is a highly creative and versatile language model, fine-tuned for storytelling, adventure, and conversational dialogue. It combines the strengths of multiple models and datasets, including retro-rodeo and choose-your-own-adventure, to generate engaging and imaginative content. With its ability to improvise and adapt to different styles and formats, Tiefighter is perfect for writers, creators, and anyone looking to spark their imagination.

NousResearch/Hermes-3-Llama-3.1-405B cover image
fp8
128k
$0.70/$0.80 in/out Mtoken
  • text-generation

Hermes 3 is a cutting-edge language model that offers advanced capabilities in roleplaying, reasoning, and conversation. It's a fine-tuned version of the Llama-3.1 405B foundation model, designed to align with user needs and provide powerful control. Key features include reliable function calling, structured output, generalist assistant capabilities, and improved code generation. Hermes 3 is competitive with Llama-3.1 Instruct models, with its own strengths and weaknesses.

NovaSky-AI/Sky-T1-32B-Preview cover image
fp16
32k
$0.12/$0.18 in/out Mtoken
  • text-generation

This is a 32B reasoning model trained from Qwen2.5-32B-Instruct with 17K data. The performance is on par with o1-preview model on both math and coding.

Phind/Phind-CodeLlama-34B-v2 cover image
fp16
4k
Replaced
  • text-generation

Phind-CodeLlama-34B-v2 is an open-source language model that has been fine-tuned on 1.5B tokens of high-quality programming-related data and achieved a pass@1 rate of 73.8% on HumanEval. It is multi-lingual and proficient in Python, C/C++, TypeScript, Java, and more. It has been trained on a proprietary dataset of instruction-answer pairs instead of code completion examples. The model is instruction-tuned on the Alpaca/Vicuna format to be steerable and easy-to-use. It accepts the Alpaca/Vicuna instruction format and can generate one completion for each prompt.

Qwen/QVQ-72B-Preview cover image
bfloat16
31k
Replaced
  • text-generation

QVQ-72B-Preview is an experimental research model developed by the Qwen team, focusing on enhancing visual reasoning capabilities. QVQ-72B-Preview has achieved remarkable performance on various benchmarks. It scored a remarkable 70.3% on the Multimodal Massive Multi-task Understanding (MMMU) benchmark

Qwen/QwQ-32B-Preview cover image
bfloat16
32k
Replaced
  • text-generation

QwQ is an experimental research model developed by the Qwen Team, designed to advance AI reasoning capabilities. This model embodies the spirit of philosophical inquiry, approaching problems with genuine wonder and doubt. QwQ demonstrates impressive analytical abilities, achieving scores of 65.2% on GPQA, 50.0% on AIME, 90.6% on MATH-500, and 50.0% on LiveCodeBench. With its contemplative approach and exceptional performance on complex problems.

Qwen/Qwen2-72B-Instruct cover image
bfloat16
32k
Replaced
  • text-generation

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

Qwen/Qwen2-7B-Instruct cover image
bfloat16
32k
Replaced
  • text-generation

The 7 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.

Qwen/Qwen2.5-72B-Instruct cover image
fp8
32k
$0.12/$0.39 in/out Mtoken
  • text-generation

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.