Anthropic Claude Models

Claude models are widely used for coding, long-form analysis and agentic workflows. AI Gateway exposes the full Claude lineup through both an Anthropic-compatible endpoint and the OpenAI-compatible API, so existing Claude SDK code works without changes.

Available Models

Live per-model credit pricing is on the Models page.

Quick Start

Anthropic Messages API

Use this endpoint with Anthropic SDK format:

curl https://your-domain.com/api/ai/v1/anthropic/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5-fd",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Review this API design."}]
  }'

OpenAI-compatible

Same Claude models, OpenAI request format:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://your-domain.com/api/ai/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-5-fd",
    messages=[{"role": "user", "content": "Write a migration plan."}]
)
print(response.choices[0].message.content)

Replace your-domain.com with your AI Gateway site domain. Get your API key from the dashboard after sign-up.

Use with Claude Code

AI Gateway works as a backend for Claude Code. Point Claude Code at your Gateway endpoint and API key, then run any Claude model from this catalog.

Why through AI Gateway

• Anthropic + OpenAI dual-format — pick whichever your stack already speaks
• One key across providers — fall back from Claude to GPT or Gemini with a config change
• Credits, not subscriptions — pay per token, top up as needed

Related Pages

• Live model pricing
• Anthropic Messages API reference
• Claude Code integration

Why through AI Gateway

• One unified interface: call every provider through a single OpenAI-compatible base URL
• One key: no per-vendor accounts; credits are shared and never expire
• Per-token billing: cache hits billed at steep discounts
• Flexible switching: change one string to move between models or vendors

About this data

Specs and prices come from the platform live catalog; performance figures from vendor or third-party publications. Updated 2026-10-13.

Why through AI Gateway

• One unified interface: call every provider through a single OpenAI-compatible base URL
• One key: no per-vendor accounts; credits are shared and never expire
• Per-token billing: cache hits billed at steep discounts
• Flexible switching: change one string to move between models or vendors

Capabilities

21 shipping models, context windows from 200K to 1M tokens; tiers: flagship ×11, balanced ×5, deep reasoning ×3, light ×2.

Pricing & billing

Per-token credit billing; cache hits at steep discounts. Live rates on the Models pricing page — numbers intentionally not fixed here.

FAQ

How large is the context window of Anthropic?

1,000,000 Token (1M)

How is it billed?

Per-token credit billing with cache-hit discounts. Live rates on the Models page.

Do I need a provider account?

No. One AI Gateway API key covers this model and every other model on the site.

About this data

Specs and prices come from the platform live catalog; performance figures from vendor or third-party publications. Updated 2026-10-13.

Why through AI Gateway

• One unified interface: call every provider through a single OpenAI-compatible base URL
• One key: no per-vendor accounts; credits are shared and never expire
• Per-token billing: cache hits billed at steep discounts
• Flexible switching: change one string to move between models or vendors

Capabilities

21 shipping models, context windows from 200K to 1M tokens; tiers: flagship ×11, balanced ×5, deep reasoning ×3, light ×2.

Pricing & billing

Per-token credit billing; cache hits at steep discounts. Live rates on the Models pricing page — numbers intentionally not fixed here.

FAQ

How large is the context window of Anthropic?

1,000,000 Token (1M)

How is it billed?

Per-token credit billing with cache-hit discounts. Live rates on the Models page.

Do I need a provider account?

No. One AI Gateway API key covers this model and every other model on the site.

About this data

Specs and prices come from the platform live catalog; performance figures from vendor or third-party publications. Updated 2026-10-13.

Why through AI Gateway

• One unified interface: call every provider through a single OpenAI-compatible base URL
• One key: no per-vendor accounts; credits are shared and never expire
• Per-token billing: cache hits billed at steep discounts
• Flexible switching: change one string to move between models or vendors

Capabilities

21 shipping models, context windows from 200K to 1M tokens; tiers: flagship ×11, balanced ×5, deep reasoning ×3, light ×2.

Pricing & billing

Per-token credit billing; cache hits at steep discounts. Live rates on the Models pricing page — numbers intentionally not fixed here.

FAQ

How large is the context window of Anthropic?

1,000,000 Token (1M)

How is it billed?

Per-token credit billing with cache-hit discounts. Live rates on the Models page.

Do I need a provider account?

No. One AI Gateway API key covers this model and every other model on the site.

About this data

Specs and prices come from the platform live catalog; performance figures from vendor or third-party publications. Updated 2026-10-13.