OpenRouter

About OpenRouter

The unified interface for every model. Find the best models & prices for your prompts

Run all your AI workloads securely on one neutral platform, with the best model at the best intelligence per dollar.

600+ models for text, images, video, audio, and more from 80+ providers.

OpenRouter picks the model and provider for each request using live data from across our marketplace, so your responses come back faster, fail less, and only cost what the task needs.

Website ↗Documentation ↗GitHub ↗

Source ↗ · 2026-11-12T03:22:33.650496206Z

Service status

unknown

API Gateway components; excludes web application

Official status page ↗

598 indexed models

598 matching models

Nace.AI: Drex v1.5

nace-ai/drex-v1.5-20261009

Drex v1.5 is a 9B decision model from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for every option in a single forward pass, with no text generation. It is TypeSafe System One compatibl

Context window
131,072
Input modalities
text
Output modalities
decisions
Capabilities
decisions

Inference prices

Nace.AI: Drex v2.0

nace-ai/drex-v2.0-20261009

Drex v2.0 is a 35B mixture-of-experts decision model (3B active) from Nace.AI, the larger successor to [Drex v1.5](https://openrouter.ai/nace-ai/drex-v1.5). Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated proba

Context window
131,072
Input modalities
text
Output modalities
decisions
Capabilities
decisions

Inference prices

Nex AGI: Nex-N2.5-Mini

nex-agi/nex-n2.5-mini-20260908

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file changes, run commands, launch applications, interact with browser and desktop interf

Context window
262,144
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, visionInput

Inference prices

  • Published price : $0.0025 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.02 / input_tokens_per_million · openRouter ↗
  • Published price : $0.10 / output_tokens_per_million · openRouter ↗

Nex AGI: Nex-N2.5-Pro

nex-agi/nex-n2.5-pro-20260907

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file changes, run commands, launch applications, interact with browser and desktop interf

Context window
262,144
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

  • Published price : $0.02 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.08 / input_tokens_per_million · openRouter ↗
  • Published price : $0.25 / output_tokens_per_million · openRouter ↗

Nex AGI: Nex-N2.6

nex-agi/nex-n2.6-20261110

Nex-N2.6 is an agentic model from Nex AGI, built on [GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash-BF16) with about 321B parameters. It is suited for computer use, coding, and long-horizon tasks that involve tools. Compared with [Nex-N2.5-Pro](/nex-agi/nex-n2.5-pro)

Context window
262,144
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

  • Published price : $0.02 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.12 / input_tokens_per_million · openRouter ↗
  • Published price : $0.40 / output_tokens_per_million · openRouter ↗

Nous: Hermes 4 405B

nousresearch/hermes-4-405b

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with <think>...</think> traces or respond directly, offering flexibility between speed

Context window
131,072
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs

Benchmarks

  • Artificial Analysis: 7.5

Inference prices

  • Published price : $0.20 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $1.00 / input_tokens_per_million · openRouter ↗
  • Published price : $3.00 / output_tokens_per_million · openRouter ↗

NVIDIA: Llama Nemotron Embed VL 1B V2 (free)

nvidia/llama-nemotron-embed-vl-1b-v2-20260224

The Llama Nemotron Embed VL 1B V2 embedding model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text combined. Documents can be retrieved given a user query in text form. The model supports image

Context window
131,072
Input modalities
text, image
Output modalities
embeddings
Capabilities
embeddings, multimodal, visionInput

Benchmarks

  • MTEB: 65.999%

Inference prices

NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)

nvidia/llama-nemotron-rerank-vl-1b-v2

Llama Nemotron Rerank VL 1B V2 is a 1.7B multimodal reranking model from NVIDIA. It evaluates the relevance of document images and text against user queries, designed for vision RAG pipelines handling charts, tables, infographics, and mixed-media documents. Functions as a cross-e

Context window
10,240
Input modalities
text, image
Output modalities
rerank
Capabilities
multimodal, rerank, visionInput

Benchmarks

  • MTEB: 53.41%

NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B

nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b-20260813

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice agents, and multilingual transcrip

Context window
0
Input modalities
audio
Output modalities
transcription
Capabilities
audioInput

Inference prices

NVIDIA: Nemotron 3.5 Content Safety

nvidia/nemotron-3.5-content-safety-20260604

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classifica

Context window
131,072
Input modalities
text, image
Output modalities
text
Capabilities
moderation, multimodal, reasoning, toolCalling, visionInput

Inference prices

NVIDIA: Nemotron 3.5 Embed 1B (free)

nvidia/nemotron-3.5-embed-1b-20261021

Nemotron 3.5 Embed 1B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be text, an image, or both. It returns 2048-dim vectors that can be truncated, and sh

Context window
32,768
Input modalities
text, image
Output modalities
embeddings
Capabilities
embeddings, multimodal, visionInput

Inference prices

NVIDIA: Nemotron 3.5 Embed 8B (free)

nvidia/nemotron-3.5-embed-8b-20261021

Nemotron 3.5 Embed 8B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be text, an image, or both. It returns 4096-dim vectors that can be truncated, and sh

Context window
32,768
Input modalities
text, image
Output modalities
embeddings
Capabilities
embeddings, multimodal, visionInput

Inference prices

NVIDIA: Nemotron 3.5 Rerank 8B (free)

nvidia/nemotron-3.5-rerank-8b-20261021

Context window
32,768
Input modalities
text, image
Output modalities
rerank
Capabilities
multimodal, rerank, visionInput

NVIDIA: Nemotron 3.5 Transcribe

nvidia/nemotron-3.5-transcribe-20261028

Nemotron 3.5 Transcribe is an open-weight speech recognition model from NVIDIA, a 30B mixture-of-experts with about 4B active parameters. It transcribes recordings of up to one hour in 40 languages, with speaker attribution, speech translation, and prompt-guided vocabulary and st

Context window
0
Input modalities
audio
Output modalities
transcription
Capabilities
audioInput

Benchmarks

  • Open ASR Leaderboard: 5.27%

NVIDIA: Nemotron 3 Embed 1B (free)

nvidia/nemotron-3-embed-1b-20260716

NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval workflows, retaining more than 95% of the 8B model’s accuracy in a smaller

Context window
4,096
Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Inference prices

NVIDIA: Parakeet TDT 0.6B v3

nvidia/parakeet-tdt-0.6b-v3

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across all official EU languages and achieves a 6.34%

Context window
0
Input modalities
audio
Output modalities
transcription
Capabilities
audioInput

Benchmarks

  • Open ASR Leaderboard: 1,719.32

Inference prices

NVIDIA: Switchyard

nvidia/switchyard

Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...

Context window
1,000,000
Input modalities
text
Output modalities
text

OpenAI: GPT-3.5 Turbo 16k

openai/gpt-3.5-turbo-16k

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.

Context window
16,385
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace