OpenRouter via VerticalAPI

Supported models

OpenRouter models routed by VerticalAPI

Pass the model ID below as model in any OpenAI-compatible request. New OpenRouter models are typically supported within 24h of release.

Model ID	Name	Context	Pricing (provider)
`anthropic/claude-sonnet-5`	Claude Sonnet 5 (OR)	1M	$2 / $10 per 1M tok at provider list, passed through
`openai/gpt-5.6-terra`	GPT-5.6 Terra (OR)	1.05M	$2.50 / $15 per 1M tok at provider list, passed through
`deepseek/deepseek-chat-v3`	DeepSeek V3 (OR)	64K	$0.27 / $1.10 per 1M tok
`meta-llama/llama-3.3-70b-instruct`	Llama 3.3 70B (OR)	128K	$0.30 / $0.50 per 1M tok

Pricing reflects OpenRouter's rates — you pay OpenRouter directly. VerticalAPI adds zero markup on tokens.

Quickstart

5-line OpenRouter call via VerticalAPI

Drop-in replacement for the OpenAI SDK. Works with the OpenAI Python client, Node, Go, curl — anything that speaks HTTP.

                openrouter_quickstart.py
                Python
            
from openai import OpenAI

client = OpenAI(
    base_url="https://api.verticalapi.com/v1",
    api_key="vapi_...",
    default_headers={"X-Provider-Key": "sk-or-..."}
)

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4.5",  # OpenRouter
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Why use OpenRouter via VerticalAPI

Four reasons developers route OpenRouter through us

Zero token markup

You pay OpenRouter directly with your own key. VerticalAPI's revenue is the gateway subscription, not a tax on your tokens.

One key, 11 providers

OpenRouter alongside 10 others — Anthropic, Cerebras, DeepInfra, Fireworks, Google AI Studio, Groq, Mistral, OpenAI, OpenRouter, Together, xAI — on the same OpenAI-compatible endpoint, same SDK, switchable per request.

Per-request usage records

Every call is logged with its model, token counts, latency and status code, so you can compare OpenRouter against another provider on identical prompts.

Prompts are never stored

Only metadata is persisted — there is no column for prompt or completion text, so your OpenRouter traffic leaves no content behind on the gateway.

Best for

Where OpenRouter shines

model A/B testing automatic failover rare model access single-key sprawl reduction

Frequently asked questions

What is OpenRouter and what models do they offer?

OpenRouter is an LLM aggregator. The 2026 catalogue spans 300+ models from OpenAI (GPT-5.6 family, GPT-5, o-series), Anthropic (Claude 5 family), Google (Gemini 3.x), Meta (Llama 3.3, 405B), Mistral, DeepSeek, Qwen, Cohere, plus inference specialists (Groq, Together, Fireworks, DeepInfra). All exposed via one OpenAI-compatible endpoint with automatic fallback when a provider is down or rate-limited.

How much does OpenRouter cost in 2026?

OpenRouter adds no markup to inference — its documentation states it passes the underlying providers' pricing through unchanged. The charges are a 5.5% fee when you buy credits with a card (5% by crypto, $0.80 minimum) and, for BYOK, 5% of the equivalent platform cost after the first 1M requests each month. Free-tier models exist (lower-quality open weights). Because the credit fee scales with spend, a flat monthly fee is cheaper past roughly $891 a month of token spend, and a percentage is cheaper below it.

How do I use OpenRouter via VerticalAPI BYOK?

Create a key at openrouter.ai/keys, paste it into VerticalAPI, then point the OpenAI SDK at https://api.verticalapi.com/v1. OpenRouter is OpenAI-compatible, so VerticalAPI passes through, adding observability and the ability to combine OpenRouter alongside direct vendor keys in the same workspace. Billing remains on your OpenRouter account.

What is OpenRouter best for compared to alternatives?

OpenRouter wins for breadth (200+ models in one API), prototyping (try GPT-5 then Claude then Llama with one parameter), and automatic fallback. Compared to going direct to each vendor, OpenRouter adds no inference markup and eliminates 10+ separate accounts; its 5.5% card credit-purchase fee is the cost of that convenience. Compared to a BYOK gateway like VerticalAPI it is less cost-efficient but model selection is broader. The two combine well: use OpenRouter through VerticalAPI to consolidate observability.

Where is OpenRouter hosted / data privacy?

OpenRouter routes through each underlying provider's infrastructure — data residency depends on the model you pick. OpenRouter does not train on prompts and offers a privacy mode that excludes providers known to train. SOC 2 compliance is in progress. Via VerticalAPI BYOK your OpenRouter contract terms remain intact.

Limitations and trade-offs

The 5.5% card credit-purchase fee is a fee on top-ups, not on tokens — it still scales with spend, so at high volume a flat-fee gateway costs less.
Per-route data privacy varies. OpenRouter's provider data-policy filter governs which upstream providers you allow; its own documentation notes that setting does not describe what OpenRouter itself does with prompts, so read its privacy policy directly if that matters to you.
Rate limits are inherited from the underlying provider — fallback helps but quotas still exist.
Enterprise SLAs, dedicated capacity and regional residency are limited next to AWS Bedrock or Azure OpenAI.
Adding a hop (OpenRouter to the underlying provider) increases p99 latency slightly.

Where OpenRouter is heading

BYOK is already supported with a generous free threshold (1M requests per month), so bring-your-own-key is no longer a differentiator between gateways.
Fees are settling on payment and platform charges rather than token markups, which moves the real comparison onto fee shape — flat subscription against percentage of spend.
Expanding catalogue, including more open-weight and regional models.
Better routing intelligence — price-per-quality, latency-aware, multi-region.

All supported LLM providers

Same endpoint, same SDK — just change the model and the BYOK header.

Ship on OpenRouter in 60 seconds

Free tier — bring your own OpenRouter key, zero markup, OpenAI-compatible endpoint.

Get your VerticalAPI key →