SylphxModels

DeepSeek

Flash family · v4.1

DeepSeek V4.1 Flash

NewMost used · 7dNewest in catalog
deepseek/deepseek-v4.1-flash

DeepSeek: DeepSeek V4.1 Flash on Sylphx Models · 1.0M of context. One Responses contract, with list prices published per million tokens.

Released
Sep 10, 2026 · 11 days old
Provider
DeepSeek
Context
1,000,000 tokens
Open in the playgroundSee a request sampleRead the docs
Input $0.4725 / MOutput $1.89 / MCached input $0.0504 / MFull rate sheet
Context window1,000,000tokens per request
Max output65,536tokens per response
Input$0.4725 / Mper million tokens
Output$1.89 / Mper million tokens
Requests · 7d484.9Kmetered on Responses
Avg TPM · 7d12.2M123.3B tokens

Pricing

USD per million tokens
Input
$0.4725
Output
$1.89
Cached input
$0.0504

$0.83 for 750,000 input and 250,000 output tokens.

Assumption: one batch of 750,000 input plus 250,000 output tokens at the published list prices — recompute for your own mix. Blended $0.8269 per million at a 3:1 mix.

Chat replies · 3:1 input:output
$0.8269 / M
Long documents · 9:1 input:output
$0.6142 / M
Heavy output · 1:1 input:output
$1.181 / M
Cache write
Not published
Currency and unit
USD / million tokens

Cached input reads cost 89% less than fresh input tokens.

Full rate sheet and billing rules.

Specification

Context window
1,000,000 tokens
Max output
65,536 tokens
Input modalities
Not published
Output modalities
Not published
Family
Flash
Version
v4.1
Provider
DeepSeek
Released
Sep 10, 2026 · 11 days old
Model id
deepseek/deepseek-v4.1-flash

Data posture

Consent-trained

The provider may train on data sent to this model, and Zero Data Retention is not available. Keep regulated or confidential material on a standard-posture model.

Training on what you send
Yes
Zero Data Retention
Not available

Traffic

Daily traffic the platform metered on Responses for this exact model id. Totals are the window they name; a day with no traffic is zero, not missing.

Requests · last 7 days
484,865
Tokens · last 7 days
123.3B
Average TPM · last 7 days
12.2M
Series total · 14d
800,713 req · 192.4B tok

14-day total 800,713 · peak 132,051 on Sep 16

Sep 8Sep 21
Daily numbers for the last 14 days
Daily requests and tokens metered for deepseek/deepseek-v4.1-flash
DayRequestsTokens
2026-09-0800
2026-09-0900
2026-09-1061,78611,877,743,390
2026-09-1191,00121,790,090,398
2026-09-1261,79613,178,471,897
2026-09-1390,63519,710,364,180
2026-09-1466,10415,494,953,815
2026-09-15113,29423,278,526,215
2026-09-16132,05132,149,131,714
2026-09-1772,09821,494,166,166
2026-09-1856,04814,091,162,374
2026-09-1918,3535,857,859,576
2026-09-2036,17112,863,008,583
2026-09-211,376598,079,876
curl https://api.models.sylphx.ai/v1/responses \
  -H "Authorization: Bearer $SYLPHX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4.1-flash",
    "input": "Summarise this incident report in three bullets.",
    "stream": false
  }'

How to call it

Send the official Responses document to the base URL above with your organization key and this exact model id. Streaming arrives as ordered events with one terminal event.

  • Retries: send an Idempotency-Key and a retry replays the original response instead of billing twice.
  • Errors: typed envelopes tell you whether to retry, wait, or fix the request.
  • Keys: mint and revoke organization keys from the console.
QuickstartResponses APIErrors and retries

Related models

Derived from this catalog: same provider first, then the same family, then the nearest neighbours by input price and context window.

More from DeepSeek

Same provider

Similar price and context

Nearest by input price and context window

Independent evaluation

We do not publish benchmark scores for this model — we have not verified any. These external leaderboards run their own tests, so check them against your own workload.

Not our numbers
484,865 requests metered on deepseek/deepseek-v4.1-flash over the last seven daysEvery DeepSeek model →
DeepSeek V4.1 Flash — pricing, context, and usage · Sylphx Models