Anthropic via VerticalAPI

Route to Claude Sonnet, Opus and Haiku through an OpenAI-compatible endpoint. BYOK with your Anthropic key, zero markup on tokens, full prompt caching support.

Start free with your Anthropic key → Read the docs

Endpoint: https://api.verticalapi.com/v1/chat/completions · BYOK header: X-Provider-Key: sk-ant-...

Supported models

Anthropic models routed by VerticalAPI

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

Model ID	Name	Context	Pricing (provider)
`claude-sonnet-4-5`	Claude Sonnet 4.5	200K	$3 / $15 per 1M tok
`claude-opus-4-6`	Claude Opus 4.6	200K	$15 / $75 per 1M tok — flagship
`claude-haiku-4-5`	Claude Haiku 4.5	200K	$0.80 / $4 per 1M tok — fastest
`claude-sonnet-4-5-1m`	Claude Sonnet 4.5 (1M ctx)	1M	Long-context tier — premium pricing

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

Quickstart

5-line Anthropic call via VerticalAPI

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

                anthropic_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-ant-..."}
)

response = client.chat.completions.create(
    model="claude-sonnet-4-5",  # Anthropic
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Why use Anthropic via VerticalAPI

Four reasons developers route Anthropic through us

Zero token markup

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

One key, every provider

Anthropic alongside OpenAI, Anthropic, Gemini and 12 more — same OpenAI-compatible endpoint, same SDK, switchable per-request.

Latency & cost monitoring

Per-request token counts, p50/p95 latency and cost dashboards out of the box. Compare Anthropic to other providers on identical prompts.

Observability built in

Every Anthropic call gets a trace ID, replayable payload and audit log entry. Wire to Datadog or Sentry via OpenTelemetry.

Best for

Where Anthropic shines

long-context analysis agentic coding tool use prompt caching

FAQ

Common questions about Anthropic on VerticalAPI

How is the Anthropic API translated to OpenAI format?

VerticalAPI shapes requests and responses to OpenAI's chat.completions schema. messages[], tools and tool_choice map cleanly. system messages are extracted into Anthropic's top-level system field.

Is prompt caching supported?

Yes — pass cache_control breakpoints in the OpenAI-formatted messages and VerticalAPI forwards them to Anthropic. Cache hits are visible in the dashboard for cost verification.

Do I get the 1M-context tier?

If your Anthropic account has access to the Sonnet 4.5 1M-token context tier, just pass claude-sonnet-4-5-1m as the model. Pricing follows Anthropic's tiered rates.

Which Claude model should I use?

Sonnet 4.5 is the default for general agentic work. Opus 4.6 for hardest reasoning. Haiku 4.5 for low-latency, high-volume work like classification or routing.

Switch providers

All supported LLM providers

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

OpenAI Anthropic Google Gemini Mistral AI Meta Llama xAI Grok Groq Together AI Fireworks AI Perplexity Sonar Cohere AI21 Labs AWS Bedrock Azure OpenAI Google Vertex AI

Ship on Anthropic in 60 seconds

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

Get your VerticalAPI key →