Docs · Models
deepseek-flash-Abliterated
Private deployment with text and image inputs, 1,048,576-token context, 262,144-token output, four reasoning settings and fixed token prices.
deepseek-flash-Abliterated is a private deployment of a fine-tuned model. It accepts text and images. Send the model ID exactly as shown, including the capital A in Abliterated.
Route and limits
The model is served on the existing deepseek-official route. That route ID remains for API keys, but this model uses a private deployment and does not call DeepSeek's official API. An Auto-route key can also reach it. deepseek-v4-pro stays on the same logical route with its separate official deployment and peak/off-peak tariff.
| Setting | Value |
|---|---|
| Input | Text and images |
| Context window | 1,048,576 tokens |
| Maximum output | 262,144 tokens |
| Endpoints | /v1/chat/completions, /v1/responses, /v1/messages |
| Reasoning effort | none, low, high, max |
| Default reasoning effort | high |
Input and output must fit within the context window. The output limit is 262,144 tokens even when more space remains in the context. If you omit the output cap, TopxAI fills it from that limit, reduced to the space remaining after the estimated prompt. This applies to max_tokens / max_completion_tokens on Chat Completions, converted Messages requests, and max_output_tokens on Responses.
Make a request
Use the existing TopxAI base URL and key:
curl https://ai.topxea.com/v1/chat/completions \
-H "Authorization: Bearer $TOPXAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-flash-Abliterated","max_tokens":4096,"reasoning_effort":"high","messages":[{"role":"user","content":"Explain how a database transaction works."}]}'Responses requests go to /v1/responses; Messages requests are converted to Chat Completions. Responses supports stateless requests: clients can send the full conversation context in input. TopxAI does not promise server-side conversation persistence for this deployment. Endpoint support alone does not establish that every Codex workflow has been tested.
Set stream: true for streaming. For an image request, put text and image_url content blocks in the user message as in the OpenAI Chat Completions format. The API reference describes the Messages conversion and how images in tool results are handled.
Fixed prices
Default prices in USD per million tokens:
| Input | Cache read | Output |
|---|---|---|
| $1.20 | $0.15 | $2.40 |
The same prices apply throughout the day and across the context window. There is no peak/off-peak tariff or long-context premium. Cache-read pricing applies to tokens reported as cache hits. See the pricing page for current prices and the usage log for the token categories charged on a request. Accepted requests and historical charges keep their captured prices.
Replacing the old model
deepseek-flash is retired. Requests to the old ID receive HTTP 403; there is no forwarding alias. Update the model ID in saved clients and integrations. If your key has an allowed-model list, add deepseek-flash-Abliterated separately. Existing restricted keys are not automatically granted access to the replacement.
Check saved output limits too: the replacement's maximum is 262,144 tokens. A request copied from the old Flash configuration may exceed it. The private deployment also has its own reasoning settings; do not assume that every setting from the official model transfers.
Because fine-tuning may affect safety alignment, the model may produce biased, offensive or locally unlawful content. Users bear full responsibility for compliance and legal consequences. The Acceptable Use Policy applies to this private deployment, as it does to GLM-5.3-Abliterated and the rest of the catalogue.
Models: deepseek-flash-Abliterated · Models & pricing
Related
- deepseek-flash-Abliterated API pricing
- Moving to deepseek-flash-Abliterated on TopxAI
- Create an API key and choose a route
- How requests are billed
- Acceptable use and abuse reports
Previous: Video generation · Next: Top up with a card
Other languages: 简体中文