Docs · Comparisons
TopxAI vs the providers' own APIs: price, retention and what stays direct
What changes when Claude, GPT, Grok or Kimi go through TopxAI: the price per token, one key and one balance, zero retention, and what stays with the provider.
Calling a provider directly is the baseline every relay is measured against. This page lists what changes when the same request goes through TopxAI, including what you give up.
What changes
| Direct | Through TopxAI | |
|---|---|---|
| Price per token | The provider's list price | Shared pool 50% of list, official line 90%; Kimi K3.1 Pro 120%; Jev 107%; GLM and deepseek-flash-Abliterated use separate private-deployment prices |
| Accounts and keys | One account, one key, one invoice per provider | One account, one Auto-route key for every model, one prepaid USD balance |
| Payment | The provider's billing: card, monthly invoice, prepaid, in the provider's currency and terms | Prepaid USD by card on topxea.com, crypto invoice or gift card; every top-up earns a 3–12% bonus |
| Request path | Client → provider | Client → TopxAI → provider; the extra hop adds the round trip between TopxAI and the provider |
| Prompts and completions | The provider's retention policy | Relayed in memory, never stored; the usage log keeps token counts, model, route and identifiers |
| Rate limits | The provider's per-account limits | Per-key request limits and the shared pool's capacity; the official line calls the provider under TopxAI's own account |
| Usage records | The provider's dashboard | One usage-log row per request with the route and the charge, filterable by key, model and route |
| Model versions | Every model and snapshot the provider offers | The models in TopxAI's catalogue; new releases arrive when they are added |
What stays with the provider
TopxAI serves Chat Completions, Responses, Messages, image generation and edits, video generation, /v1/systemone and /v1/models. Anything else stays on the provider's own key:
- Batch APIs and their discounts
- Fine-tuning, files, assistants, vector stores
- Realtime and audio endpoints
- Embeddings (no embedding model in the catalogue)
- Provider-side features that need account-level settings, such as organisation-wide data controls
The same either way
TopxAI preserves the provider's request and response format where the selected endpoint uses that format, with the adjustments below. Cross-format requests are converted. Tool calling, structured output, streaming, vision and reasoning support depend on the model and endpoint; use the compatibility table and model guides to check the limits. Prompt caching is charged from reported cache usage at the selected route's rates. TopxAI sets upstream authentication headers for the selected route and supplies anthropic-version: 2023-06-01 when a Claude request omits the version. It adds a system prompt in two cases. Claude has no JSON mode, so a Chat Completions request to Claude with response_format set to json_object gets one sentence in the system prompt asking for a single JSON object. A GPT request without a system prompt that reaches the provider's Responses API (GPT-6.1 Sol and GPT-6.1 Terra on every endpoint, GPT-6 Astra through /v1/responses) is sent the one-line instruction "You are a helpful assistant.", so that the provider does not add its own longer prompt (next paragraph); a request with its own system prompt or instructions is forwarded unchanged. Native Claude requests retain the Messages structure, including cache breakpoints. The relay validates tool choice and reasoning settings against the model's capabilities; incompatible sampling controls may be removed. Common field adjustments include: a missing max_tokens is set to the model's output limit, service_tier, inference_geo and speed are not passed on, and the deprecated output_format, which the upstream ignores, is sent as output_config.format. GLM-5.3-Abliterated has one change of its own: its deployment decodes some string formats badly, so the uri, email, date and date-time formats of a json_schema move into the field description before forwarding, as its page explains.
For deepseek-flash-Abliterated, an omitted output cap on Chat Completions or converted Messages is filled from the model's output limit, bounded by the context remaining after the estimated prompt. Flash also applies this rule to max_output_tokens on its native Responses endpoint, with a 262,144-token maximum. It supports stateless Responses requests with full conversation context in input; server-side conversation persistence is not promised for this deployment.
Some upstream capacity puts a system prompt of its own in front of the request. The upstream counts those tokens as input, so they are billed with the rest of the input. The GPT provider adds about 4,300 tokens of instructions to a Responses request that has no instructions: on 2026-10-16 a short GPT-6.1 Sol request counted 4,353 input tokens without them and 107 with them. TopxAI's one line keeps that prompt out. On /v1/responses, a system prompt sent only as a system or developer item of input leaves instructions empty and TopxAI adds nothing, so such a request can still carry the provider's prompt; send the system prompt in instructions to avoid it. Some Claude requests can carry several thousand such tokens, reported mostly as cache writes and cache reads. On /v1/responses the upstream also returns the instructions it ran with and members of its own: TopxAI sets instructions, metadata, safety_identifier and prompt_cache_key back to what your request sent, so TopxAI's line never shows in an answer, and removes the members of its own that it is known to add, in the body and in every stream event. Some capacity also adds a provider_specific_fields member to Chat Completions answers, and TopxAI removes it too. The usage log lists the input and cache counts each request was billed for.
Deciding
Go direct when you need an endpoint TopxAI does not serve, the provider's own billing terms, or a model outside the catalogue. Go through TopxAI when the models you use are in the catalogue, the price per token matters, and one key with one balance is simpler than several accounts. The two are not exclusive: most tools take a base URL per model, so the catalogue models can run through TopxAI while the rest stay direct.
Related
- Every model's price
- TopxAI vs OpenRouter: what is the same and what differs
- Shared pool, official line and auto route
- Connect your SDK
Previous: TopxAI vs OpenRouter: what is the same and what differs · Next: TopxAI vs Vercel AI Gateway: list price with no markup, or half of it
Other languages: 简体中文