DeepSeek V4.1 Flash 1017
DeepSeek logo

DeepSeek V4.1 Flash 1017

deepseek-v4.1-flash-1017llms.txt
DeepSeek
The official latest version of DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. API usage and pricing remain unchanged—you can still access the latest model using deepseek-flash.

Pricing

  • Input Tokens: $0.155 /M tokens
  • Output Tokens: $0.62 /M tokens
  • Cache Read: $0.0031 /M tokens

Input Modalities

  • Text
  • Vision

Output Modalities

  • Text

Context length

  • 1M tokens

Max output

  • 393K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Structured outputs
  • Structured decision
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Providers

Bytedance doubao-deepseek-v4.1-flash-1017
50% off·Oct 29 07:00 – Nov 26 07:00 GMT+0
Off-peak04:00–06:00, 10:00–01:00 UTC
Pricing$0.1408$0.0704$0.5632$0.2816
Cache Storage$0.0024/h/M tokens
Cache Read$0.0028/M tokens$0.0014/M tokens
Web Search$0.0031/request
Peak01:00–04:00, 06:00–10:00 UTC
Pricing$0.2816$0.1408$1.1264$0.5632
Cache Storage$0.0024/h/M tokens
Cache Read$0.0056/M tokens$0.0028/M tokens
Web Search$0.0031/request
PrecisionⓘNot Disclosed
Latency4.8S
Throughput64.1TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today
Overall
66.37
Response quality
50.83
Feature support
62.24
Response speed
76.57
Service reliability
88.50
Baidu baidu-deepseek-v4.1-flash-1017
50% off·Oct 29 07:00 – Nov 26 07:00 GMT+0
Off-peak14:00–00:00 UTC
Pricing$0.1408$0.0704$0.5632$0.2816
Cache Read$0.0028/M tokens$0.0014/M tokens
Peak00:00–14:00 UTC
Pricing$0.2816$0.1408$1.1264$0.5632
Cache Read$0.0056/M tokens$0.0028/M tokens
PrecisionⓘNot Disclosed
Latency3.2S
Throughput79.1TPS
Uptime
99.89% uptime 2 days ago
99.96% uptime yesterday
99.99% uptime today
Overall
56.48
Response quality
36.70
Feature support
75.71
Response speed
36.55
Service reliability
87.00
Pareto pareto-deepseek-v4.1-flash-1017
Off-peak04:00–06:00, 10:00–01:00 UTC
Pricing$0.155$0.62
Cache Read$0.0031/M tokens
Web Search$0.00077/request
Peak01:00–04:00, 06:00–10:00 UTC
Pricing$0.3098$1.2392
Cache Read$0.0062/M tokens
Web Search$0.00077/request
PrecisionⓘFP8
Latency3.1S
Throughput56.2TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today
Overall
68.72
Response quality
53.97
Feature support
85.33
Response speed
52.50
Service reliability
90.00
Alibaba Cloud alicloud-deepseek-v4.1-flash-1017
Off-peak14:00–00:00 UTC
Pricing$0.1408$0.5632
Cache Read$0.0141/M tokens
Web Search$0.00062/request
Peak00:00–14:00 UTC
Pricing$0.2816$1.1264
Cache Read$0.0282/M tokens
Web Search$0.00062/request
PrecisionⓘNot Disclosed
Latency7.5S
Throughput63.7TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
99.95% uptime today
Overall
73.38
Response quality
52.13
Feature support
80.54
Response speed
85.01
Service reliability
90.00
DeepSeek deepseek-flash
Off-peak04:00–06:00, 10:00–01:00 UTC
Pricing$0.155$0.62
Cache Read$0.0031/M tokens
Web Search$0.00077/request
Peak01:00–04:00, 06:00–10:00 UTC
Pricing$0.3098$1.2392
Cache Read$0.0062/M tokens
Web Search$0.00077/request
PrecisionⓘNot Disclosed
Latency1.7S
Throughput123.7TPS
Uptime
99.99% uptime 2 days ago
99.98% uptime yesterday
99.97% uptime today
Overall
73.76
Response quality
52.59
Feature support
84.60
Response speed
80.99
Service reliability
90.00
Fireworks fireworks-deepseek-v4.1-flash-1017
Pricing$0.33$1.32
Cache$0.0066
PrecisionⓘNot Disclosed
Latency0.6S
Throughput23.9TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today
Overall
64.10
Response quality
50.42
Feature support
60.16
Response speed
68.55
Service reliability
88.50
Tencent tencent-deepseek-v4.1-flash-1017
Off-peak04:00–06:00, 10:00–01:00 UTC
Pricing$0.1618$0.6472
Cache Read$0.0032/M tokens
Peak01:00–04:00, 06:00–10:00 UTC
Pricing$0.3234$1.2936
Cache Read$0.0065/M tokens
PrecisionⓘNot Disclosed
Latency-
Throughput-
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today

Dimension scores are D-layer composites (0.65 A + 0.20 B + 0.15 C); raw A-layer values are in each APB Profile.

Scoring methodology

Response quality quantifies task-level correctness under the specified adjudication protocol; feature support assesses conformance to API, tool-invocation and usage-reporting contracts; response speed characterizes latency under the evaluated load conditions; service reliability measures first-attempt completion within the observed request cohort.

Each dimension is a 0–100 composite of absolute performance, deviation from the reference route and evidence sufficiency. The overall score weights them 35%, 25%, 20% and 20%. These results are provisional and conditional on the sampled workload and observation protocol; they do not establish statistical superiority, a production ranking or a long-term SLA.

Performance for deepseek-v4.1-flash-1017

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4.1-flash-1017",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is DeepSeek V4.1 Flash 1017?

The official latest version of DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. API usage and pricing remain unchanged—you can still access the latest model using deepseek-flash.