stepfun/step-3.5-flash
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, streaming, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 17
- LMArena: 1,402.661
- OpenCompass LLM: 83.9%
Inference prices
- Published price : $0.09 / input_tokens_per_million · deepInfra ↗
- Published price : $0.30 / output_tokens_per_million · deepInfra ↗
vertexAI/publishers/hf-nvidia/models/llama-3_3-nemotron-super-49b-v1_5@001
- Input modalities
- text
- Output modalities
- text
Benchmarks
Inference prices
- Published price : $0.40 / input_tokens_per_million · deepInfra ↗
- Published price : $0.40 / output_tokens_per_million · deepInfra ↗
vertexAI/publishers/hf-allenai/models/olmo-3.1-32b-instruct@001
- Input modalities
- text
- Output modalities
- text
Benchmarks
Inference prices
- Published price : $0.20 / input_tokens_per_million · deepInfra ↗
- Published price : $0.60 / output_tokens_per_million · deepInfra ↗
nvidiaNim/nvidia/llama-3.1-nemotron-70b-instruct
Benchmarks
- LiveBench: 36.604%
- LMArena: 1,282.663
Inference prices
- Published price : $1.20 / input_tokens_per_million · deepInfra ↗
- Published price : $1.20 / output_tokens_per_million · deepInfra ↗
qwen/qwen-2.5-72b-instruct
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
- Context window
- 32,768
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 7.7
- LMArena: 1,269.026
- Open LLM Leaderboard v2: 47.98%
- OpenRouter Benchmarks: 27.333%
Inference prices
- Published price : $0.36 / input_tokens_per_million · deepInfra ↗
- Published price : $0.40 / output_tokens_per_million · deepInfra ↗
google/gemma-2-27b-it
Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...
- Context window
- 8,192
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
Benchmarks
- LiveBench: 39.883%
- LLM Stats · GitHub archive: 0.518
- LMArena: 1,231.387
- Open LLM Leaderboard v2: 36.174%
- Open Persian LLM Leaderboard: 95.98%
Inference prices
- Published price : $0.27 / input_tokens_per_million · deepInfra ↗
- Published price : $0.27 / output_tokens_per_million · deepInfra ↗
qwen/qwen-2.5-coder-32b-instruct
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...
- Context window
- 32,768
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
Benchmarks
- Artificial Analysis: 6.7
- BigCode Models Leaderboard: 83.2%
- LMArena: 1,230.051
- Open LLM Leaderboard v2: 39.885%
- SWE-bench: 38%
Inference prices
- Published price : $0.06 / input_tokens_per_million · deepInfra ↗
- Published price : $0.15 / output_tokens_per_million · deepInfra ↗
nvidiaNim/nvidia/nemotron-4-340b-instruct
Benchmarks
Inference prices
- Published price : $4.20 / input_tokens_per_million · deepInfra ↗
- Published price : $4.20 / output_tokens_per_million · deepInfra ↗
microsoft/phi-4
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
- Context window
- 16,384
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
Benchmarks
- Artificial Analysis: 5.9
- LMArena: 1,216.694
- Open LLM Leaderboard v2: 30.358%
Inference prices
- Published price : $0.07 / input_tokens_per_million · deepInfra ↗
- Published price : $0.14 / output_tokens_per_million · deepInfra ↗
meta-llama/llama-3.2-3b-instruct
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including Engl
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
Benchmarks
- Artificial Analysis: 5.7
- LMArena: 1,109.541
- Open LLM Leaderboard v2: 24.205%
- OpenRouter Benchmarks: 28.62%
Inference prices
- Published price : $0.02 / input_tokens_per_million · deepInfra ↗
- Published price : $0.02 / output_tokens_per_million · deepInfra ↗
meta-llama/llama-3.2-1b-instruct
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong
- Context window
- 60,000
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Artificial Analysis: 4.8
- LMArena: 1,054.641
- Open LLM Leaderboard v2: 14.443%
- Open Persian LLM Leaderboard: 28.28%
Inference prices
- Published price : $0.01 / input_tokens_per_million · deepInfra ↗
- Published price : $0.01 / output_tokens_per_million · deepInfra ↗
vertexAI/publishers/hf-allenai/models/olmocr-2-7b-1025@001
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput
Inference prices
- Published price : $0.09 / input_tokens_per_million · deepInfra ↗
- Published price : $0.19 / output_tokens_per_million · deepInfra ↗
huggingface/Austism/chronos-hermes-13b-v2
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 56.105%
Inference prices
- Published price : $0.13 / input_tokens_per_million · deepInfra ↗
- Published price : $0.13 / output_tokens_per_million · deepInfra ↗
vertexAI/publishers/hf-baai/models/bge-en-icl@001
- Capabilities
- embeddings
Benchmarks
Inference prices
- Published price : $0.01 / input_tokens_per_million · deepInfra ↗
azureFoundry/HuggingFace/bigcode-starcoder2-15b-instruct-v0.1@1
`bigcode/starcoder2-15b-instruct-v0.1` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1) - [Text Generation I
- Input modalities
- text
- Output modalities
- text
Inference prices
- Published price : $0.15 / input_tokens_per_million · deepInfra ↗
- Published price : $0.15 / output_tokens_per_million · deepInfra ↗
siliconFlow/black-forest-labs/FLUX.1-dev
FLUX.1 [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. It offers cutting-edge output quality, second only to their state-of-the-art model FLUX.1 [pro]. The model features competitive prompt following, matching the pe
- Input modalities
- text
- Output modalities
- image
- Capabilities
- imageOutput, multimodal, visionInput
siliconFlow/black-forest-labs/FLUX.1-Kontext-dev
FLUX.1 Kontext [dev] is a 12 billion parameter image editing model developed by Black Forest Labs. Based on advanced Flow Matching technology, it functions as a diffusion transformer capable of precise image editing based on text instructions. The model's core feature is its powe
- Input modalities
- text, image
- Output modalities
- image
- Capabilities
- imageOutput, multimodal, visionInput
cloudflareWorkersAI/bria/fibo-edit-1.5
FIBO Edit changes one to four input images from a natural-language or structured JSON (VGL) instruction. Add a black-and-white mask to edit only part of a single image, or refer to several images as "image 1", "image 2", and so on to combine them or transfer a style.
- Input modalities
- image, text
- Output modalities
- image
- Capabilities
- imageOutput, multimodal, visionInput