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

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

google/gemini-3.1-flash-lite-image-20260630

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation in roughly 4 seconds — about 2.7× faster than Gemini 3

Context window
65,536
Input modalities
image, text
Output modalities
image, text
Capabilities
imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, videoInput, visionInput, webSearch

Benchmarks

  • OpenRouter Benchmarks: 11.616%

Inference prices

Google: Nano Banana (Gemini 2.5 Flash Image)

google/gemini-2.5-flash-image

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations. Aspect ratios can be controlled with the [image_config

Context window
32,768
Input modalities
image, text
Output modalities
image, text
Capabilities
batch, imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, visionInput, webSearch

Benchmarks

  • Vercel AI Gateway: 3.788%

Inference prices

Google: Nano Banana Pro (Gemini 3 Pro Image)

google/gemini-3-pro-image-20260528

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich gr

Context window
131,072
Input modalities
image, text
Output modalities
image, text
Capabilities
batch, imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Vercel AI Gateway: 11.882%

Inference prices

Google: Nano Banana Pro (Gemini 3 Pro Image Preview)

google/gemini-3-pro-image-preview-20251120

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich gr

Context window
65,536
Input modalities
image, text
Output modalities
image, text
Capabilities
imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, visionInput

Inference prices

Google: Veo 3.1

google/veo-3.1-20260320

Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio — including dialogue, ambient effects, and background sound. Supports

Context window
0
Input modalities
text, image
Output modalities
video
Capabilities
multimodal, structuredOutputs, videoOutput, visionInput

Google: Veo 3.1 Fast

google/veo-3.1-fast-20260320

Google's mid-tier video generation model balancing speed and quality. Veo 3.1 Fast generates high-quality video from text or image prompts with native synchronized audio, offering faster turnaround than Veo 3.1 at lower cost. Supports first-frame and last-frame conditioning, mult

Context window
0
Input modalities
text, image
Output modalities
video
Capabilities
multimodal, structuredOutputs, videoOutput, visionInput

Google: Veo 3.1 Lite

google/veo-3.1-lite-20260331

Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration. Veo 3.1 Lite generates 720p and 1080p video from text or image prompts with native synchronized audio at less than 50% of the cost of Veo 3.1 Fast. Supports 4–8 second

Context window
0
Input modalities
text, image
Output modalities
video
Capabilities
multimodal, structuredOutputs, videoOutput, visionInput

hexgrad: Kokoro 82M

hexgrad/kokoro-82m

Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese) using 54 preset voices organized by language and gender. At

Context window
4,096
Input modalities
text
Output modalities
speech
Capabilities
speechOutput

Inference prices

  • Input characters (per 1M) : $0.62 / characters_per_million · openRouter ↗

HeyGen: Avatar IV

heygen/avatar-iv-20260625

HeyGen: Avatar IV is an image-to-video model that animates a single photo into an expressive, lip-synced talking-head video. Rather than only matching mouth shapes to words, it interprets the vocal tone, rhythm, and emotion of the audio to drive head motion, facial expression, an

Context window
0
Input modalities
text, image, audio
Output modalities
video
Capabilities
audioInput, multimodal, videoOutput, visionInput

HeyGen: HeyGen Decision

heygen/heygen-decision-1-20261112

HeyGen Decision 1 is a decision model from HeyGen. It reads text and images and answers a set of named questions in one request, returning typed answers with probabilities: a...

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

Inference prices

HeyGen: HeyGen Decision Turbo

heygen/heygen-decision-1-turbo-20261112

HeyGen Decision 1 Turbo is a lower-cost variant of [HeyGen Decision 1](/heygen/heygen-decision-1) from HeyGen, with the same question types (`noul`, `choice`, and `score`) over text and images. It suits high-volume...

Context window
262,144
Input modalities
text, image
Output modalities
decisions
Capabilities
decisions, multimodal, visionInput

Inference prices

HeyGen: HeyGen Video

heygen/heygen-video-1-20260930

HeyGen Video is a general-purpose video generation model from HeyGen. It renders short clips with synthesized audio (dialogue, ambience, and sound effects) in a single call, working from a text prompt, from a first-frame image, or from a set of image, video, and audio references

Context window
0
Input modalities
text, image, video, audio
Output modalities
video
Capabilities
audioInput, multimodal, videoOutput, visionInput

Benchmarks

  • Vercel AI Gateway: 23.264%

HeyGen: HeyGen Voice

heygen/heygen-voice-1-20261009

HeyGen Voice is a text-to-speech model from HeyGen. It comes with 10 default voices, or bring your own HeyGen key to use voice clones from your own account. It streams 44.1 kHz mono PCM audio, with support for 39 languages and up to 5,000 characters per request.

Context window
0
Input modalities
text
Output modalities
speech
Capabilities
speechOutput

HeyGen: HeyGen Voice Turbo

heygen/heygen-voice-1-turbo-20261009

HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own HeyGen key to use voice clones from your own account. It streams 44.1 kHz mono PCM audio, with support for 39 languages and up to 5,0

Context window
0
Input modalities
text
Output modalities
speech
Capabilities
speechOutput

inclusionAI: Ling 3.2 Flash (free)

inclusionai/ling-3.2-flash-20261113

Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...

Context window
1,048,576
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

Inference.net: Schematron V2 Small

inference-net/schematron-v2-small-20260902

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user promp

Context window
128,000
Input modalities
text
Output modalities
text
Capabilities
promptCaching, structuredOutputs

Inference prices

  • Published price : $0.05 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.05 / input_tokens_per_million · openRouter ↗
  • Published price : $0.23 / output_tokens_per_million · openRouter ↗

Inference.net: Schematron V2 Turbo

inference-net/schematron-v2-turbo-20260902

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.

Context window
128,000
Input modalities
text
Output modalities
text
Capabilities
promptCaching, structuredOutputs

Inference prices

  • Published price : $0.03 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.03 / input_tokens_per_million · openRouter ↗
  • Published price : $0.15 / output_tokens_per_million · openRouter ↗

Intfloat: E5-Base-v2

intfloat/e5-base-v2-20251117

The e5-base-v2 embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, similarity scoring, retrieval and clustering.

Context window
512
Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Benchmarks

  • MTEB: 59.393%

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