THE CLAUDE MODEL FAMILY
Claude API models & pricing
Looking for a cheap Claude API? Compare the Claude models in AELDER's catalog, see input and output rates against official prices, and connect through one OpenAI-compatible key without a subscription.
- Models in this catalog
- 12
- Input from / 1M tokens
- $0.035
- Lower token rates, up to
- 80%
Savings compare input/output unit rates with the stated official tier. Actual cost depends on your selected model and token usage.
Compare API token prices
Calculate your savingsPrices per 1M tokens. Cached tokens cost 10% of the input price. Very small requests are charged a minimum of $0.00002. Struck-through prices are official list prices. Official cached-input prices are shown only when confirmed.
Compare Claude versions, not just family names.
Sonnet, Opus, Fable and Haiku are separate model lines. Choose an exact version, then compare its input/output rates, published specifications and available benchmark results on its model page.
Claude Sonnet
Compare the Sonnet releases side by side. A matching price does not mean two versions have identical specifications or evaluation results.
Claude Opus
Review the individual Opus releases and the separately listed 1M entry. Check the exact model configuration before treating variants as interchangeable.
Claude Fable
Explore the listed Fable versions. External evaluation configurations are labelled on each model page and are separate from API connection settings.
Claude Haiku
Check the available Haiku entry and its token rates. Compare it with other Claude models using published information rather than the family label alone.
Claude API pricing: how token costs work.
This is AELDER's Claude API catalog. The crossed-out prices use official base input/output rates for the listed models. Long-context tiers, cache writes and optional services can change official charges; they are not included in the unit-rate saving. Our cached-input rate is shown separately.
Input is the text and context you send; output is what the model generates. Cached input is a separate unit rate, not a promise that every request will hit the cache.
Compare the model and the service.
For a provider comparison, read AELDER vs OpenRouter API pricing. That page uses its own dated OpenRouter reference; the crossed-out prices here are official model rates.
Estimate a token mix with the API cost calculator, or browse all model families and API prices.
Connect to the Claude API through AELDER.
Set your AELDER API key, the service Base URL and an exact model ID from your account's model list. A catalog name is not a guarantee of every optional API feature.
Use the Python and JavaScript OpenAI SDK guide for an OpenAI-compatible Chat Completions connection.
Connect OpenCode to the API →
For a coding-tool connection, use a model that supports the features your tool requires and check the exact request ID in your account.
Need another tool? Browse the integration guides. Confirm model and protocol support before relying on tools, images or structured output.
Claude API questions
What does Claude API access cost on AELDER?
Input prices start at $0.035 per million tokens across the 12 Claude models in this catalog. Output and cached input have separate rates. The table shows each model's prices; there is no mandatory monthly subscription.
Does a Claude subscription pay for this API?
No. A Claude web or app subscription does not provide an AELDER API balance or key. This catalog describes pay-per-token API access with a separate account and balance.
Do I need a separate API key for each Claude model?
One AELDER key can access the models enabled for your account. To change Claude versions, select the exact model ID in your request or tool configuration. An Anthropic key is a different credential and does not authenticate this service.