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…

🚀 New models by Bria.ai, generate and edit images at scale 🚀

Browse deepinfra models:

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

View All

featured

text-generation

automatic-speech-recognition

text-to-speech

embeddings

text-to-image

text-to-video

reranker

zero-shot-image-classification

multimodal

text-generation

deepseek-ai/

DeepSeek-R1

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.

fp4

160k

$0.70/$2.40 in/out Mtoken

text-generation

deepseek-ai/

DeepSeek-R1-Distill-Qwen-32B

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.

fp8

128k

$0.27 / Mtoken

text-generation

deepseek-ai/

DeepSeek-R1-Turbo

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.

fp4

40k

$1.00/$3.00 in/out Mtoken

text-generation

google/

gemini-1.5-flash

Gemini 1.5 Flash is Google's foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video. It's adept at processing visual and text inputs such as photographs, documents, infographics, and screenshots. Gemini 1.5 Flash is designed for high-volume, high-frequency tasks where cost and latency matter.

976k

Deprecated

text-generation

google/

gemini-1.5-flash-8b

976k

Deprecated

text-generation

google/

gemini-2.0-flash-001

976k

$0.10/$0.40 in/out Mtoken

text-generation

meta-llama/

Llama-3.2-11B-Vision-Instruct

Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question answering, bridging the gap between language generation and visual reasoning. Pre-trained on a massive dataset of image-text pairs, it performs well in complex, high-accuracy image analysis. Its ability to integrate visual understanding with language processing makes it an ideal solution for industries requiring comprehensive visual-linguistic AI applications, such as content creation, AI-driven customer service, and research.

bfloat16

128k

$0.049 / Mtoken

text-generation

meta-llama/

Llama-3.2-3B-Instruct

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)

bfloat16

128k

$0.02 / Mtoken

text-generation

meta-llama/

Llama-Guard-3-8B

Llama Guard 3 is a Llama-3.1-8B pretrained model, 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 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.

bfloat16

128k

$0.055 / Mtoken

text-generation

meta-llama/

Meta-Llama-3-8B-Instruct

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.

bfloat16

$0.03/$0.06 in/out Mtoken

text-generation

meta-llama/

Meta-Llama-3.1-70B-Instruct

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

bfloat16

128k

$0.40 / Mtoken

text-generation

meta-llama/

Meta-Llama-3.1-70B-Instruct-Turbo

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

fp8

128k

$0.10/$0.28 in/out Mtoken

text-generation

meta-llama/

Meta-Llama-3.1-8B-Instruct

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

bfloat16

128k

$0.03/$0.05 in/out Mtoken

text-generation

meta-llama/

Meta-Llama-3.1-8B-Instruct-Turbo

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

fp8

128k

$0.02/$0.03 in/out Mtoken

text-generation

microsoft/

WizardLM-2-8x22B

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to those leading proprietary models.

bfloat16

64k

$0.48 / Mtoken

text-generation

mistralai/

Mistral-Nemo-Instruct-2407

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

fp8

128k

$0.02/$0.04 in/out Mtoken

text-generation

mistralai/

Mistral-Small-24B-Instruct-2501

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.

fp8

32k

$0.05/$0.08 in/out Mtoken

text-generation

mistralai/

Mixtral-8x7B-Instruct-v0.1

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.

fp8

32k

$0.40 / Mtoken

text-generation

moonshotai/

Kimi-K2-Instruct

Kimi K2 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 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks.

mixed: fp8/fp4

128k

$0.50/$2.00 in/out Mtoken

text-generation

nvidia/

Llama-3.1-Nemotron-70B-Instruct

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.

fp8

128k

$0.60 / Mtoken

text-generation

nvidia/

Llama-3.3-Nemotron-Super-49B-v1.5

Llama-3.3-Nemotron-Super-49B-v1.5 is a large language model (LLM) optimized for advanced reasoning, conversational interactions, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta's Llama-3.3-70B-Instruct, it employs a Neural Architecture Search (NAS) approach, significantly enhancing efficiency and reducing memory requirements.

fp8

128k

$0.10/$0.40 in/out Mtoken

text-generation

nvidia/

NVIDIA-Nemotron-Nano-9B-v2

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.

bfloat16

128k

$0.04/$0.16 in/out Mtoken

Company

Latest Models

openai/whisper-tiny openchat/openchat_3.5 Phind/Phind-CodeLlama-34B-v2 Gryphe/MythoMax-L2-13b bigcode/starcoder2-15b

Featured Models

meta-llama/Llama-4-Scout-17B-16E-Instruct deepseek-ai/DeepSeek-V3 openai/gpt-oss-20b Qwen/QwQ-32B canopylabs/orpheus-3b-0.1-ft