New Sign up free, 10 calls on us. Up to $1, no card needed.

DeepSeek V4 Flash vs DeepSeek V4.1 Flash

vs

Which one, when

Both share a 1,000,000-token context and 393,216-token max output with tools and reasoning, so the upgrade question is inputs against price: deepseek-v4.1-flash adds image input and costs $0.3 input (about 2.2x) and $1.2 output (about 4.4x) against $0.138 and $0.275 for the text-only deepseek-v4-flash, with cache reads at $0.03 against $0.0028 (roughly 10.7x). Stay on deepseek-v4-flash for high-volume text chat and code where the lower rates and the option to turn thinking off matter; move to deepseek-v4.1-flash when you need to send images.

Benchmarks

Above averageNo peer higherDeepSeek V4 Flashonly 2 comparableDeepSeek V4.1 Flash16 / 194 / 19
DeepSeek V4 Flash DeepSeek V4.1 Flash other models measured peer average no peer scored higher
NL2Repo
N/A
64%
Cybergym
N/A
no peer scored higher 88.1%
GPQA Diamond
N/A
90.9%
Agents' Last Exam
N/A
31.8%
BabyVision with tools
N/A
89.6%

Vendor-published: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai

Pricing

DeepSeek V4 Flash DeepSeek V4.1 Flash Δ
Input / 1M tokens $0.138 $0.3 0.46×
Output / 1M tokens $0.275 $1.2 0.23×
Cache read / 1M tokens $0.0028 $0.03 0.093×
Cache write no separate charge no separate charge -

Rates from the live catalog at build time; each model page carries the current card.

Where they sit - input price per 1M tokens across all 69 chat models on this billing unit (log scale)

Capabilities

DeepSeek V4 Flash DeepSeek V4.1 Flash
Tool use yes yes
Thinking control configurable yes - vendor dial not published
Structured output yes -
Prompt caching implicit (automatic) implicit (automatic)
Cache lifetime no fixed TTL (evicted when unused) no fixed TTL (evicted when unused)
Minimum cached prefix not published not published

Specs

DeepSeek V4 Flash DeepSeek V4.1 Flash
Input modalities text text image
Output modalities text text
Released 2026-04-24 2026-09-10
Context window 1M 1M
Max output 393K 393K
Thinking parameter
  • thinking.type
  • reasoning_effort
-
Accepted values
thinking.type
  • enabled
  • disabled
reasoning_effort
  • high
  • max (low and medium map to high, xhigh maps to max)
-
Default

enabled, with reasoning_effort high

some complex agent requests are automatically set to max

-

Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: DeepSeek V4 Flash · DeepSeek V4.1 Flash

One prompt, both models - measured through the gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. CHECK exactly 3 sentences

DeepSeek V4 Flash passed · 3 sentences

When reasoning is enabled, the model generates additional "chain-of-thought" tokens internally before producing the final answer, effectively doubling the total token count per request. Since our billing is based on tokens processed, this directly doubled your usage. Additionally, reasoning often requires more expensive model tiers or higher compute resources, further amplifying the cost increase.

out 154 tok (+85 thinking) latency 3.1 s

DeepSeek V4.1 Flash passed · 3 sentences

Enabling reasoning changed the unit economics: the model now spends extra billable tokens internally to “think” before producing the answer, and those reasoning tokens are charged like output tokens even though users never see them. That added token generation—plus longer contexts and occasional retries on harder prompts—roughly doubled our cost per request. We can control this by capping reasoning depth, routing only complex queries to reasoning models, and caching common prompts to bring the bill back down.

out 423 tok (+327 thinking) latency 14.6 s

Instruction following (exactly three sentences - countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. CHECK fix passes tests

DeepSeek V4 Flash passed · 8/8 cases

The bug is that the function counts the number of consecutive equal **pairs** (i.e., `cur` increments for each `i` where `xs[i] == xs[i-1]`), but it should return the **length** of the longest run. For a run of length `L`, the number of pairs is `L-1`, so the result is always one less than the correct value. This causes the function to return 0 for a single‑element list (expected 1) and to undercount runs that end at the last index (e.g., `[1,1]` returns 1 instead of 2). Additionally, runs of length 1 that are not part of any pair (such as a single element at the end of a list) are never considered because `best` is only updated when a pair is found. […]

out 2494 tok (+2227 thinking) latency 19.4 s

DeepSeek V4.1 Flash passed · 8/8 cases

```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 best = max(best, cur) return best ``` The bug is that `cur` is counting equal adjacent pairs, not elements in the current run: every time `xs[i] == xs[i - 1]`, the run length increases by one element, but the first element of the run was never counted, so all runs are undercounted by one. Also, `best` starts at `0`, so single-element inputs return `0` instead of `1`, and a one-element run ending at the last index is missed entirely.

out 918 tok (+733 thinking) latency 11.4 s

Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. CHECK valid JSON, schema exact

DeepSeek V4 Flash passed · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": null, "guidance": null }

out 1101 tok (+1054 thinking) latency 10.2 s

DeepSeek V4.1 Flash passed · 5/5 fields, guidance "withheld pending the Q4 close"

{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":11.0,"guidance":"withheld pending the Q4 close"}

out 1707 tok (+1667 thinking) latency 15.1 s

Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. CHECK 120 words, 0 banned words

DeepSeek V4 Flash passed · 119 words, 0 banned, 1 question

We're thrilled to introduce Prompt Cache, a new feature for our API Gateway that stores prompt responses from any provider. When a user submits a prompt you've already processed, the system returns the cached result instantly—eliminating redundant API calls and reducing latency. This works across OpenAI, Anthropic, Google, and more, with automatic cache invalidation based on your rules. What does this mean for your budget? Fewer API calls directly lower your monthly spend. Additionally, response times drop by up to 80% for cached prompts, improving user experience. Developers can configure cache duration per provider, set TTLs, and bypass cache when needed. The feature is available now in your gateway dashboard. Start saving time and money with Prompt Cache.

out 2039 tok (+1887 thinking) latency 15.6 s

DeepSeek V4.1 Flash passed · 116 words, 0 banned, 1 question

Today we're launching Cross-Provider Prompt Cache for our API gateway. It stores identical prompt requests and their responses across supported model providers, then serves cached results when a match is found. Teams can cut duplicate inference costs, reduce latency, and keep behavior consistent during provider failover. The cache works with configurable TTLs, per-route rules, and cache-key controls, so you decide what is reusable and what must stay fresh. Does your application send the same prompts to multiple providers? Now your gateway can answer many of those calls without another upstream request. Existing observability dashboards show hit rates, saved tokens, and estimated spend reduction. Enable it in the gateway console, set your policy, and start caching today.

out 917 tok (+770 thinking) latency 9.0 s

Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.

Switch between them with one line

Both ids are in every tab below - the highlighted pair of lines is the only edit. Same endpoint, same key, same request shape.

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="deepseek-v4-flash",
    # model="deepseek-v4.1-flash",  # uncomment this line, comment the one above
    messages=[{"role": "user", "content": "Summarize this diff"}],
)
print(resp.choices[0].message.content)

Get your API key →

FAQ

Which is cheaper, DeepSeek V4 Flash or DeepSeek V4.1 Flash?

DeepSeek V4 Flash is cheaper on input / 1m tokens ($0.138 vs $0.3, 2.2× apart). Other rows may point the other way - the table above carries the full card, and real cost depends on your mix.

Can I A/B test DeepSeek V4 Flash against DeepSeek V4.1 Flash without two integrations?

Yes. Both are served through the same OpenAI-compatible endpoint with one API key - switching is a one-line model-string change, so you can route a fraction of traffic to each and compare bills directly.

Do DeepSeek V4 Flash and DeepSeek V4.1 Flash support prompt caching?

Yes - both bill cached reads below their input rate, so warm-prefix workloads cost less than the list rates suggest. The exact cache-read rows are in the pricing table above.

Related comparisons

From our measured studies