Cache read
Reusing a cached prompt prefix is billed well below the standard input rate for the same model.
Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.
LLM API Pricing
Claude API Pricing in 2026
Anthropic bills Claude models per million tokens, with separate input and output rates. The table below lists Anthropic's official rates next to RunAPI's for each current Claude model — same API, same output, one key.
Updated June 18, 2026 RunAPI Editorial
Model-by-model breakdown
How much does each Claude model cost per million tokens?
The table shows official Anthropic pricing alongside RunAPI pricing from the current price list. No volume commits, no subscriptions.
| Model | Official input /M | Official output /M | RunAPI input /M | RunAPI output /M |
|---|---|---|---|---|
| claude-fable-5 | $10.00 | $50.00 | $8.00 20% OFF | $40.00 |
| claude-fable-5-1 | $10.00 | $50.00 | $8.00 20% OFF | $40.00 |
| claude-haiku-4-5-20251001 | $1.00 | $5.00 | $0.80 20% OFF | $4.00 |
| claude-haiku-5-5 Higher rate on long prompts | $0.10 | $0.50 | $0.08 20% OFF | $0.40 |
| claude-opus-4-1-20250805 | $15.00 | $75.00 | $12.00 20% OFF | $60.00 |
| claude-opus-4-5-20251101 | $5.00 | $25.00 | $4.00 20% OFF | $20.00 |
| claude-opus-4-6 | $5.00 | $25.00 | $4.00 20% OFF | $20.00 |
| claude-opus-4-7 | $5.00 | $25.00 | $4.00 20% OFF | $20.00 |
| claude-opus-4-8 | $5.00 | $25.00 | $4.00 20% OFF | $20.00 |
| claude-opus-5 | $5.00 | $25.00 | $4.00 20% OFF | $20.00 |
| claude-opus-5-5 | $4.00 | $20.00 | $3.20 20% OFF | $16.00 |
| claude-sonnet-4-5-20250929 | $3.00 | $15.00 | $2.40 20% OFF | $12.00 |
| claude-sonnet-4-6 | $3.00 | $15.00 | $2.40 20% OFF | $12.00 |
| claude-sonnet-5 | $2.00 | $10.00 | $1.60 20% OFF | $8.00 |
| claude-sonnet-5-5 | $2.00 | $10.00 | $1.60 20% OFF | $8.00 |
Prompt caching
How do cache discounts reduce your Claude API bill?
Anthropic's prompt caching stores repeated prefixes and charges less when the cached version is reused. This matters for coding agents like Claude Code, which send the same system prompt and file context on every request.
Cache write (5 min TTL)
Writing a prefix to the 5-minute cache costs somewhat more than standard input. The cached prefix stays available for 5 minutes.
Cache write (1 hour TTL)
Writing to the 1-hour cache costs more than a 5-minute write. Useful for long coding sessions where context reuse is frequent.
Batch processing
Anthropic bills batch requests that can wait up to 24 hours at a lower rate than standard requests. See Anthropic's pricing page for the current batch rate.
Provider comparison
Is Claude API cheaper than OpenAI and Gemini?
Developers who hit their Claude limits often look at GPT-5 and Gemini 2.5 Pro as alternatives. Here is how the flagship models compare on actual per-million-token costs.
| Provider | Flagship model | Input /M | Output /M | RunAPI rate |
|---|---|---|---|---|
| Anthropic | claude-opus-4-7 | $5.00 | $25.00 | $4.00 / $20.00 |
| OpenAI | gpt-5.4 | $2.50 | $15.00 | $2.00 / $12.00 |
| gemini-3.1-pro-preview | $2.00 | $12.00 | $1.60 / $9.60 |
Subscription vs API
Is Claude API cheaper than a Claude Max subscription?
Claude Max is a fixed monthly subscription for heavy Claude Code usage. The API charges per token with no monthly commitment. One thing the subscription doesn't tell you: plans have both a short-window limit and a weekly cap, so if you use them hard every day, you can run out mid-week and wait days for a reset. The API has no such ceiling. To compare, multiply your monthly token usage by the rates in the pricing table and set the result against the subscription fee.
Claude Max
High usage limits for Sonnet and Opus in Claude Code. Fixed monthly cost. No API access for third-party tools.
Claude API via RunAPI
Pay per token with no monthly commitment, at the rates in the pricing table. You pay only for the tokens you use.
When Max wins
Heavy daily users whose monthly token usage, priced at API rates, would cost more than the subscription fee.
When API wins
Teams, CI pipelines, multi-model setups, and any tool that requires API access (OpenClaw, n8n, Cursor). No cap, no waitlist, no subscription lock-in. You can also route simpler tasks to Haiku, which costs far less per token than Sonnet.
Getting started
How to access Claude API through RunAPI
-
Create a RunAPI account
Sign up and generate an API key from the dashboard.
-
Copy your API key
Go to Dashboard → API Keys. Create a key and save it — you will use this as your OpenAI API key.
-
Point your SDK to RunAPI
Set the base URL to https://runapi.ai/v1 and use your RunAPI API key. Any OpenAI-compatible client works — Python, Node.js, Go, Ruby, or curl.
-
Start making requests
Use claude-sonnet-4-6, claude-opus-4-7, or any Claude model ID in the model parameter. RunAPI handles routing and bills at the rates listed on this page.
Frequently asked questions
Claude API Pricing FAQ
I asked one question and used a big share of my 5-hour usage. What's going on?
Large context windows — your system prompt, conversation history, attached files — dominate token cost. One question with a big context can use a large share of your 5-hour window. The API lets you control exactly what context you send on each request, so you stop paying for context you don't need.
Can I use a Claude subscription to power third-party tools?
Using third-party tools like OpenClaw, n8n, or Cursor with a personal Claude subscription can get your account banned. Anthropic's terms don't allow subscription plans to power external apps. The API is the only supported path — and RunAPI makes it pay-as-you-go with no monthly commitment.
Can I use RunAPI with Claude Code?
Yes. Set ANTHROPIC_BASE_URL to https://runapi.ai and your RunAPI key as the API key. Claude Code works without any other modification. You pay per token at the RunAPI rates in the pricing table — no subscription required.
What happens if Anthropic changes their pricing?
The pricing table reads from RunAPI's current price list, so the official and RunAPI rates on this page update when prices change.
Is there a free tier?
Creating an account and API key is free. API calls use prepaid, pay-as-you-go billing; add funds before making requests.
Does RunAPI support prompt caching?
Yes. Cache reads, 5-minute writes, and 1-hour writes are all supported and billed per token. If you send the same large system prompt on every request, cache reads cost much less than sending that prompt as standard input.
Can I use the OpenAI SDK to call Claude through RunAPI?
Yes. RunAPI is OpenAI-compatible. Point any OpenAI client at runapi.ai/v1 and use Claude model IDs. If you're already calling Claude from OpenRouter or a similar gateway, switching to RunAPI works the same way — you change one URL and one API key.
How does billing work?
Pay-as-you-go. You fund your account with a balance, and each API call deducts the token cost. No subscriptions, no invoices, no contracts. You can also set a hard spend limit in your RunAPI dashboard so you never get a surprise bill — unlike direct Anthropic billing, which has caught users off guard.
RELATED
Explore More
OpenAI API Pricing
GPT-5.5, GPT-5.4, and GPT-5.4-mini pricing with official and RunAPI rates.
Gemini API Pricing
Gemini 2.5 Pro and Flash pricing with official and RunAPI rates.
Claude Code Pricing
What Claude Code costs with API billing vs Max subscription.
All Model Pricing
Compare 250+ models across text, image, video, and audio.
Start using Claude with one API key.
Create a free RunAPI account, get your API key, and call Claude Opus, Sonnet, or Haiku at the rates listed on this page.
Building with a team?
We're here to help with enterprise setup, integrations, and technical questions.