OpenRouter

Researched 1d agoAggregatorTier 2

OpenRouter, Inc.

CodingRAGAgentsLong contextVisionClassificationJSON / Tool useaggregatormulti-providerapi

OpenRouter offers 474 tracked models (412 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.

Covers 7 workload areas across 474 tracked models; last verified 2026-11-14.

Use it for

  • Teams comparing token and batch pricing across this provider's models
  • Operators routing coding, rag, and agents workloads through this API
  • Batch buyers auditing discount coverage model-by-model

Do not use it for

  • Final benchmark picks without opening the relevant model detail page

Tracked models

474

Models available through this provider

Priced output routes

412

Models with output token pricing tracked

Cheapest output

$0.050

L3 8B Lunaris on this route

Batch-ready models

3

Models with discounted batch pricing

Latest model release

2026-11-13

2d since newest release

Freshness

2026-11-14

Researched 1d ago

fresh

Information

TypeAggregator
TierTier 2
Models474
CompanyOpenRouter, Inc.
Founded2023
New York, NY, USA

OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.

Where this host wins

  • Coding: 146 tracked models with SWE-bench / HumanEval-style scores.
  • RAG: 225 tracked models with ruler / needle retrieval benchmarks.
  • Agentic: 207 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
  • Long-context: 251 tracked models with context-token or InfiniteBench-class signal.

Getting started

Verify: quotas and regions in the linked vendor documentation.

Platform Overview

OpenRouter provides a unified interface for Large Language Models with better pricing, improved uptime, and no subscription requirements. Route across providers for cost optimization and reliability.

Tracked catalog
179 API-refreshed rows
Scope
Local catalog; not exhaustive versus the live feed

Available Models(474)

View all →

All models available as Serverless

ModelPer hour of audioList priceBatch input (per 1M)Batch output (per 1M)
Recraft V4.1 Flash V2—$0.007/image——
Gemini 4 Hydrogen————
ERNIE 5.5 Flash Preview————
Gemini Decision 1————
MiniMax H3 Image————
MiniMax H3 Image Highspeed————
Nex-N2.6————
Claude Fable 5.2————
Muse Ember————
Gemini Omni 1.2 Flash————
View full catalog →

Where else to run this