Moving to deepseek-flash-Abliterated on TopxAI

2026-10-24 · deepseek, models, api, topxai

Flash moves to a private deployment with a new ID and image inputs. Since November 10: $0.42 / $0.105 / $1.50 per million tokens, 131,072-token output.

Update, 2026-10-25: deepseek-v4-pro is retired. New requests for that ID return HTTP 403 permission_denied; the launch details below are historical.

Update, 2026-11-08: deepseek-flash-Abliterated moved to $0.28 input, $0.07 cache read and $1.00 output per million tokens, the prices until November 10; its maximum output is 131,072 tokens and the default reasoning effort is low. A costlier standby deployment can answer, rarely, when the main one fails; such a request is billed at the backup price ($1.20 / $0.15 / $2.40). deepseek-flash-fast, DeepSeek V4.1 Flash 1017 on standard weights, joins the same route. See the changelog.

Update, 2026-11-10: deepseek-flash-Abliterated now costs $0.42 input, $0.105 cache read and $1.50 output per million tokens. The backup price and the limits are unchanged. See the changelog.

Update, 2026-11-12: the backup price, charged only when the standby deployment answers because the main one failed, is now $1.30 input, $0.15 cache read and $2.60 output per million tokens. The main price does not change. See the changelog.

TopxAI now offers deepseek-flash-Abliterated in place of deepseek-flash. The replacement is a private deployment of a fine-tuned model, with text and image inputs, a 1,048,576-token context window and a maximum of 262,144 output tokens at launch (131,072 since November 8).

The route ID remains deepseek-official for existing keys. That name does not mean this Flash model calls DeepSeek's official API. deepseek-v4-pro continues on its official deployment and keeps its peak/off-peak prices.

Update the model ID and key

Use the exact ID deepseek-flash-Abliterated, including the capital A. The old deepseek-flash ID returns HTTP 403 and has no forwarding alias. Replace it in saved SDK settings and coding clients.

You can keep the same TopxAI base URL and an unrestricted DeepSeek or Auto-route key. If your key has an allowed-model list, edit the list to include the new ID; the upgrade does not broaden a restricted key's permissions. Check any saved output cap against the maximum, 131,072 tokens since November 8.

The model supports /v1/chat/completions, /v1/responses and /v1/messages. Responses supports stateless requests with the conversation context supplied by the client. The model guide includes a request example and explains the output-cap defaults.

Prices no longer change by time of day

Default USD prices per million tokens at launch were:

Input	Cache read	Output
$1.20	$0.15	$2.40

These were the replacement's fixed prices at launch, not the old official Flash tariff; the update above has the current ones. There is no peak/off-peak schedule or long-context premium. Tokens that the deployment reports as cache hits use the cache-read rate. Accepted requests keep the price captured when they were accepted, and historical charges are unchanged. The pricing page and usage log show the applicable rates and token counts.

Review reasoning settings

The model accepts none, low, high and max for reasoning_effort; the default is low since November 8 (high at launch). Set the effort explicitly when a client has a saved preference. A private fine-tune can behave differently from the official model, so check the answers and tool behavior your application depends on before switching its traffic.

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. TopxAI's Acceptable Use Policy applies to this private deployment as it does to GLM-5.3-Abliterated.

Models: deepseek-flash-Abliterated · Models & pricing

Other languages: 简体中文

Moving to deepseek-flash-Abliterated on TopxAI

Update the model ID and key

Prices no longer change by time of day

Review reasoning settings

Related