OpenRouter API Pricing (2026)
AI model aggregator providing unified API access to 200+ models from OpenAI, Anthropic, Google, Meta, Qwen, and more with transparent per-token pricing and automatic fallback routing. Founded in 2023 and headquartered in San Francisco, CA, OpenRouter offers 9 active models through their API. All pricing data below is sourced directly from the OpenRouter pricing page and is updated regularly.
Prices verified Mar 10, 2026
OpenRouter Model Pricing — All Models
All prices are in USD per 1 million tokens ($/M tokens). Input tokens are the text you send to the model; output tokens are the generated response.
| Model | Tier | Input | Output | Cached Input | Batch Input | Batch Output |
|---|---|---|---|---|---|---|
Qwen3.5 Plus (OpenRouter) Alibaba's Qwen3.5 Plus model via OpenRouter. Powerful large-scale model with 1M context window, strong coding and multilingual capabilities at a low per-token price. | Mid | $0.26/M | $1.56/M | — | — | — |
Qwen3.5 Flash (OpenRouter) Alibaba's Qwen3.5 Flash — a fast, cost-efficient model with a 1M token context window. Ideal for high-volume tasks where speed and price matter most. | Budget | $0.10/M | $0.40/M | — | — | — |
MiniMax M2.5 (OpenRouter) MiniMax's M2.5 model via OpenRouter. High-capability model with a 196K context window, competitive on creative and instruction-following tasks. | Mid | $0.27/M | $0.95/M | — | — | — |
Kimi K2.5 (OpenRouter) Moonshot AI's Kimi K2.5 via OpenRouter. A capable mid-tier model with strong multilingual and reasoning abilities, available across a 262K context window. | Mid | $0.45/M | $2.20/M | — | — | — |
Amazon Nova 2 Lite (OpenRouter) Amazon's Nova 2 Lite via OpenRouter. A cost-effective multimodal model with a 1M token context window, suited for document processing and customer-facing applications. | Budget | $0.30/M | $2.50/M | — | — | — |
ByteDance Seed-2.0-Lite (OpenRouter) ByteDance's Seed-2.0-Lite via OpenRouter. A lightweight model with 262K context window, competitive for text and instruction-following tasks at a low price point. | Budget | $0.25/M | $2.00/M | — | — | — |
Inception Mercury 2 (OpenRouter) Inception AI's Mercury 2 via OpenRouter. A diffusion-based language model offering unique generation characteristics with a 128K context window. | Budget | $0.25/M | $0.75/M | — | — | — |
ByteDance Seed-2.0-Mini (OpenRouter) ByteDance's Seed-2.0-Mini via OpenRouter. A compact, ultra-low-cost model with a 262K context window, ideal for budget-conscious workloads. | Budget | $0.10/M | $0.40/M | — | — | — |
Xiaomi MiMo-V2-Flash (OpenRouter) Xiaomi's MiMo-V2-Flash via OpenRouter. An extremely low-cost model with a 262K context window, optimized for fast and efficient inference. | Budget | $0.09/M | $0.29/M | — | — | — |
Prices last verified: 2026-03-10. Always confirm on the official pricing page before production use.
OpenRouter Model Capabilities
Key technical capabilities across all OpenRouter models. Use this table to identify which models support the features your application requires.
| Model | Context | Max Output | Vision | Functions | JSON Mode | Caching | Batch API | Reasoning |
|---|---|---|---|---|---|---|---|---|
| Qwen3.5 Plus (OpenRouter) | 1,000,000 | 65,536 | — | ✓ | ✓ | — | — | — |
| Qwen3.5 Flash (OpenRouter) | 1,000,000 | 65,536 | — | ✓ | ✓ | — | — | — |
| MiniMax M2.5 (OpenRouter) | 196,608 | 65,536 | — | ✓ | ✓ | — | — | — |
| Kimi K2.5 (OpenRouter) | 262,144 | 65,535 | — | ✓ | ✓ | — | — | — |
| Amazon Nova 2 Lite (OpenRouter) | 1,000,000 | 5,120 | ✓ | ✓ | ✓ | — | — | — |
| ByteDance Seed-2.0-Lite (OpenRouter) | 262,144 | 131,072 | — | ✓ | ✓ | — | — | — |
| Inception Mercury 2 (OpenRouter) | 128,000 | 50,000 | — | — | — | — | — | — |
| ByteDance Seed-2.0-Mini (OpenRouter) | 262,144 | 65,536 | — | ✓ | ✓ | — | — | — |
| Xiaomi MiMo-V2-Flash (OpenRouter) | 262,144 | 65,536 | — | ✓ | ✓ | — | — | — |
When to Choose OpenRouter
Cost-sensitive workloads
Use Xiaomi MiMo-V2-Flash (OpenRouter) — OpenRouter's most affordable model at $0.09/M input / $0.29/M output. Estimated cost at 100K requests/month: $23.50.
High-volume pipelines
OpenRouter models are well-suited for high-throughput workloads. Consider batch API (where supported) for an additional 50% cost reduction on asynchronous pipelines. Check the pricing table above for batch pricing availability.
Compare OpenRouter Models vs Competitors
See detailed cost comparisons between OpenRouter models and models from other providers, including side-by-side pricing tables and monthly cost projections.
Frequently Asked Questions: OpenRouter API Pricing
What is the cheapest OpenRouter model?
The cheapest OpenRouter model by input token price is Xiaomi MiMo-V2-Flash (OpenRouter), priced at $0.09/M for input tokens and $0.29/M for output tokens. It is best suited for high-volume, cost-sensitive workloads where speed and price matter most.
What is the most capable OpenRouter model?
Qwen3.5 Plus (OpenRouter) is OpenRouter's most capable model, classified as a mid-tier model. It supports a context window of 1,000,000 tokens and is priced at $0.26/M input / $1.56/M output per million tokens.
How does OpenRouter API pricing work?
OpenRouter charges per token consumed — separately for input tokens (the text you send) and output tokens (the text the model generates). Prices are listed in USD per 1 million tokens ($/M). OpenRouter was founded in 2023 and is headquartered in San Francisco, CA. All pricing shown here is sourced from the official OpenRouter pricing page.
Does OpenRouter offer batch API pricing?
OpenRouter's current model lineup does not include batch API pricing at this time. For cost reduction on high-volume workloads, consider prompt caching (where supported) or running multiple concurrent requests with standard pricing.
Which OpenRouter models support vision / image inputs?
1 OpenRouter model support vision (image input): Amazon Nova 2 Lite (OpenRouter). These models can analyze images, charts, screenshots, and documents alongside text prompts.
OpenRouter pricing data last verified: 2026-03-10. Prices may change — verify on the official OpenRouter pricing page before production use.