Why this makes Capriole more useful
One USD 9 Premium membership covers unlimited browser chat across the supported Premium model set, 5 million monthly charged API tokens, and 10 documented coding-agent paths. Applications keep the protocol they already use, while the user keeps one Capriole account, key, balance, and billing page. This is the practical advantage over assembling provider accounts separately. The dated cost comparison uses the USD 9 personal Premium subscription, which includes 5M monthly API tokens. On the same 5 million-token workload, direct paid Standard pricing ranges from USD 6.75 to USD 90, while OpenRouter ranges from USD 7.55 to USD 94.95 after its published credit-purchase fee. For the current flagship models, Claude API pricing, OpenAI API pricing, and Gemini API pricing show how official rates compare with the personal Premium top-up price of USD 8 per 5M tokens.The public paths
Successful routed responses and streamed events remain in the protocol the client requested. A Responses payload is not converted into Chat Completions on the way back. An Anthropic Messages stream is not repackaged as OpenAI output.
This preserves the protocol-specific behavior that Responses, Messages, and Chat Completions clients expect.
The shared layer handles access and accounting. Each public route keeps the request and response contract its client expects. The model groups are route-specific compatibility sets, not a hierarchy; a model may appear on more than one supported route when it implements each contract.
Why one endpoint is not enough
Model families disagree about more than field names. OpenAI Responses represents output as typed events and items. Anthropic Messages uses its own content blocks and streaming events. Chat Completions has another request and response shape. Reasoning controls, tool calls, usage data, errors, and token-counting behavior also differ. A shallow adapter can make a simple text prompt work. Coding agents and production clients expose the missing details quickly. They depend on streaming order, tool-result turns, usage metadata, and model-specific controls. Capriole therefore owns multiple protocol-preserving routes behind one authentication and billing layer.One key, explicit model selection
All public generation routes use the same Capriole API key and account balance. The requested model still has to belong to the selected protocol. For example, the Responses path accepts the maintained OpenAI alias and supported Responses-compatible OpenAI models, plus Grok models sent with thexai/ prefix. The Messages path accepts the maintained Claude alias and supported Claude Messages model IDs. Compatible chat paths can expose a broader set of public chat models.
Each route validates the requested model ID before dispatch. An invalid ID returns a validation error, so clients can correct the model or endpoint before retrying.
Latest aliases and reproducible IDs
Capriole exposes maintained aliases such asopenai-latest, claude-latest, and google-latest on the public paths that support them.
Aliases are resolved before upstream dispatch. Usage, quota, and fallback records are attached to the resolved canonical model rather than an ambiguous “latest” bucket.
Use an alias when you want Capriole’s maintained default to move with supported releases. Use a concrete model ID when the exact version is part of the result and must remain reproducible.
The List models endpoint is the current public inventory.
Fallback happens before the response begins
For supported routes, Capriole can attempt another configured source when the first source fails before response bytes have been sent. The source stays fixed once streaming begins. The requested model key is preserved through a supported source fallback. Capriole changes the delivery source, not the user’s stated model choice. Browser chat can separately offer optional model auto-switching and manual model changes inside a conversation. Those are workspace behaviors, not the raw API fallback contract.Usage remains visible
Programmatic workloads are metered. Capriole records usage from the metadata supplied by the matching protocol, including completed streamed responses when usage is available. Premium currently includes 5 million charged API tokens per month. Capriole counts uncached input and output at 100% and cached input at 10% for this balance. Additional token packs are available as top-ups. The charged-token article gives the exact formula, rounding rule, and reproducible examples. Browser chat and automated API workloads use separate allowances. A coding agent processing millions of tokens draws from the visible charged-token balance.What the unified layer actually provides
The useful common layer is not one response schema. It is the surrounding product contract:- one Capriole account and API key;
- one visible API balance;
- maintained model aliases;
- validation against the selected protocol;
- supported source fallback before output begins;
- usage accounting against the resolved model;
- documented setup for applications and coding agents.
How we test compatibility
Capriole documents a route as supported after its protocol contract and a representative real client flow both pass. A successful text prompt is an initial check. Streaming, tool-result turns, alias resolution, usage accounting, and negative protocol tests provide the rest of the evidence. The focused public-route and file-conversion suites completed 68 automated tests against controlled upstream responses, not production live calls. Separate local upstream and coding-agent runs check behavior that a mocked endpoint cannot prove.
Stream checks consume the full response and require each protocol’s own terminal event. Responses ends with its completion event, Chat Completions reaches
[DONE], and Messages reaches message_stop. Tool tests send the tool result back and require the final assistant turn.
Validation tests check that each endpoint accepts its own model aliases. Use google-latest with Chat Completions and openai-latest with Responses or Chat Completions.
For Browser Chat uploads, see supported files and upload steps.

