Pricing
Cheap Claude API
Access Claude Sonnet and Opus through Tokely. Compare input, output and cached-token prices with Anthropic rates. Pay as you go. No subscription.
tokely.me/cheap-claude-api
Claude API pricing by model
Claude Haiku 5.5: $0.042353 input / $0.211764 output per 1M tokens. Up to 57.6% off selected models vs Anthropic prices. Pay as you go.
By TokelyReviewed Claude API pricing is per million tokens and depends on the exact model: input, output and cache-read tokens each have their own rate, and output costs several times more than input. The table below lists Anthropic's published rate and the Tokely rate for every enabled Claude version.
Claude API price comparison
| Model | Tokely input / output | Tokely example | model developer example | Discount vs model developer |
|---|---|---|---|---|
| Claude Haiku 5.5Anthropic | $0.042353 / $0.211764Cache read: $0.042353 | $0.095294 | $0.225$0.1 / $0.5 per 1M | 57.6% off |
| Claude Sonnet 5Anthropic | $1.5 / $7.5Cache read: $0.15 | $3.375 | $4.5$2 / $10 per 1M | 25.0% off |
| Claude Sonnet 5.5Anthropic | $1.5 / $7.5Cache read: $0.075 | $3.375 | $4.5$2 / $10 per 1M | 25.0% off |
| Claude Sonnet 4.6Anthropic | $2.25 / $11.25Cache read: $0.225 | $5.0625 | $6.75$3 / $15 per 1M | 25.0% off |
| Claude Opus 5.5Anthropic | $3 / $15Cache read: $0.15 | $6.75 | $9$4 / $20 per 1M | 25.0% off |
| Claude Opus 4.6Anthropic | $3.75 / $18.75Cache read: $0.375 | $8.4375 | $11.25$5 / $25 per 1M | 25.0% off |
| Claude Opus 4.7Anthropic | $3.75 / $18.75Cache read: $0.375 | $8.4375 | $11.25$5 / $25 per 1M | 25.0% off |
| Claude Opus 4.8Anthropic | $3.75 / $18.75Cache read: $0.375 | $8.4375 | $11.25$5 / $25 per 1M | 25.0% off |
| Claude Opus 5Anthropic | $3.75 / $18.75Cache read: $0.375 | $8.4375 | $11.25$5 / $25 per 1M | 25.0% off |
| Claude Opus 4.5Anthropic | $3.75 / $18.75Cache read: $0.375 | $8.4375 | $11.25$5 / $25 per 1M | 25.0% off |
| Claude Fable 5Anthropic | $7.5 / $37.5Cache read: $0.75 | $16.875 | $22.5$10 / $50 per 1M | 25.0% off |
| Claude Fable 5.1Anthropic | $7.5 / $37.5Cache read: $0.1875 | $16.875 | $22.5$10 / $50 per 1M | 25.0% off |
How a Claude API bill is calculated
Cost = uncached input tokens × input rate + cached input tokens × cache-read rate + output tokens × output rate, divided by one million. System prompts, conversation history and tool definitions count as input. Extended reasoning counts as output.
Opus, Sonnet, Haiku: pick the tier per task
Opus models cost the most and suit hard reasoning and long agentic work. Sonnet is the general-purpose default for coding and production apps. Haiku is the low-cost option for classification, extraction and high-volume routing. Price differences between tiers are larger than differences between gateways.
Claude API vs Claude subscription
Claude Pro and Max subscriptions cover the Claude apps with usage limits; API usage is billed separately per token. A subscription does not fund API calls, and API credit does not unlock app plans.
Prompt caching cuts repeated input
Reused prefixes, such as long system prompts or documents, can be billed at the lower cache-read rate when a cache hit is reported. The cached share is part of total input, not an extra count. A cache hit is not guaranteed for every request.
One key for every model
Every model on this page is available through one OpenAI-compatible endpoint and one balance, with routing modes, bounded fallback, spending limits and request logs.
LLM gateway: one API for every model ↗
A hosted LLM gateway with one OpenAI-compatible endpoint, account routing modes, bounded fallback, spending limits and request logs. Text, image, video and audio from one balance.
OpenAI-compatible API for Claude, Gemini, GPT and more ↗
Keep the OpenAI SDK and call Claude, Gemini, GPT, Kimi, GLM and other supported models. Change the base URL, key and model ID.
Questions before you switch
How much does the Claude API cost per million tokens?
It depends on the model version. See the table: each row lists input, output and cache-read prices per million tokens from Anthropic's published pricing and the Tokely rate for the same model.
Is there a free tier for the Claude API?
Anthropic's API is paid usage. Tokely also has no free tier; you fund a balance and pay the published per-token rate.
Can I estimate my Claude bill before switching?
Yes. Use the calculator with your real input, output and cached token counts. It runs locally and does not send a request.
START WITH YOUR OWN WORKLOADKnow the price.
Know the price.
Then make the call.
Check the model, compare the rate, and connect with a Tokely key.