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

DeepSeek V4 Pro (0813) vs Gemini 3.8 Flash

vs

Which one, when

Both sit near a million tokens of context (1000000 for deepseek-v4-pro-0813, 1048576 for gemini-3.8-flash), so the real split is shape rather than size: gemini-3.8-flash takes text, image, audio and video in at $0.75 input and $3.75 output per million tokens, while deepseek-v4-pro-0813 is text-only at $1.32 and $3.96, roughly 1.76x the input and cache-read cost. Pick deepseek-v4-pro-0813 when you need long single-shot generations, since its 393216 max output is about 6x the 65536 of gemini-3.8-flash. Pick gemini-3.8-flash for cheaper prefill and any non-text input; both cover chat, code, reasoning and tools.

Benchmarks

Above averageNo peer higherDeepSeek V4 Pro (0813)13 / 211 / 21Gemini 3.8 Flash12 / 165 / 16
DeepSeek V4 Pro (0813) Gemini 3.8 Flash other models measured peer average no peer scored higher
DeepSWE 1.1
62.7%
73.7%
BioMysteryBench hard
N/A
no peer scored higher 56.5%
OSWorld 2.0 Partial score, batch tool enabled
N/A
59%
Cybergym
83.3%
N/A
HealthBench Professional
N/A
52.1%
Finance Agent v2
N/A
no peer scored higher 61.4%
Legal Agent Benchmark
N/A
10%
GPQA Diamond
92.4%
95.3%
Agents' Last Exam
25.7%
N/A
CharXiv (RQ) no tools
N/A
no peer scored higher 86.2%

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

Pricing

DeepSeek V4 Pro (0813) Gemini 3.8 Flash Δ
Input / 1M tokens $1.32 $0.75 1.8×
Output / 1M tokens $3.96 $3.75 1.1×
Cache read / 1M tokens $0.132 $0.075 1.8×
Cache write 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 71 chat models on this billing unit (log scale)

Capabilities

DeepSeek V4 Pro (0813) Gemini 3.8 Flash
Tool use yes yes
Thinking control always on yes - vendor dial not published
Structured output yes yes
Prompt caching implicit (automatic) implicit + explicit
Cache lifetime no fixed TTL (evicted when unused) not published
Minimum cached prefix not published 4096 tokens

Specs

DeepSeek V4 Pro (0813) Gemini 3.8 Flash
Input modalities text text image audio video
Output modalities text text
Released 2026-08-13 2026-09-02
Knowledge cutoff - 2026-03
Context window 1M 1M
Max output 393K 66K
Thinking parameter reasoning_effort -
Accepted values
reasoning_effort
  • the model card documents low
  • high
  • 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 Pro (0813) · Gemini 3.8 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 Pro (0813) passed · 3 sentences

Enabling reasoning causes the model to generate a hidden chain-of-thought with many additional tokens before producing the final answer, which sharply increases compute consumption per request. Those extra reasoning tokens are billed at the same or higher rates, so total usage doubled even though the volume of final outputs stayed similar. We can control this by adjusting reasoning effort, setting token limits, or routing only complex requests through reasoning mode.

out 308 tok (+226 thinking) latency 5.1 s

Gemini 3.8 Flash passed · 3 sentences

When we enabled reasoning, the model began generating hidden "thinking tokens" to work through logic step-by-step before producing a final answer. Because AI vendors bill for every single token processed—visible or not—this internal deliberation dramatically inflated our billable volume per query. In short, while our total number of user requests remained flat, the cost per transaction doubled to buy higher accuracy on complex tasks.

out 705 tok (+624 thinking) latency 6.4 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 Pro (0813) 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` was initialized to `0` and only counted adjacent matching pairs, so a run of length `n` produced `n - 1` (or `0` for a single element) instead of `n`. The code also reset to `0` on a change, when the new run should start at length `1`. Initializing `cur` and `best` to `1` fixes both the single-element case and runs ending at the last index.

out 1315 tok (+1130 thinking) latency 16.9 s

Gemini 3.8 Flash passed · 8/8 cases

Here is the corrected function: ```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 best = max(best, cur) else: cur = 1 return best ``` ### Explanation of the Bug The original function counted equal-neighbor transitions rather than the actual items making up each run. Because `cur` started at `0` (and was reset to `0` on mismatches), every run was undercounted by one: single-element lists returned `0` because the loop never executed, and any subsequent run—including those ending at the last index—recorded a count of $N - 1$ instead of $N$. The fix handles empty input upfront, initializes both `cur` and `best` to `1` (since any single element forms a run of length 1), and resets `cur` to `1` whenever a new run begins.

out 1393 tok (+1149 thinking) latency 10.1 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 Pro (0813) passed · 5/5 fields, guidance null

{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":11.0,"guidance":null}

out 2155 tok (+2121 thinking) latency 26.0 s

Gemini 3.8 Flash passed · 5/5 fields, guidance null

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": null, "guidance": null } ```

out 3989 tok (+3932 thinking) latency 30.4 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 Pro (0813) passed · 121 words, 0 banned, 1 question

Introducing cross-provider prompt caching in our API gateway. Send a prompt once, and the gateway stores its computed prefix across Anthropic, OpenAI, and other LLM providers. Subsequent requests with the same prompt hit the cache, cutting latency and token costs while keeping outputs consistent across routing decisions and provider failovers. Teams can route identical prompts between providers without reprocessing shared context or lengthy system instructions. How much could you save on repeated prompt prefixes? The cache respects provider-specific key formats, handles TTLs automatically, and works with streaming and batch requests. Enable it with one configuration flag—no changes to your application code. Available today on all plans. Monitor cache hit rates, token savings, and provider-specific performance metrics in the live dashboard.

out 2845 tok (+2694 thinking) latency 25.5 s

Gemini 3.8 Flash passed · 120 words, 0 banned, 1 question

Why pay multiple model providers for the exact same output? Introducing Universal Prompt Cache, our latest API gateway capability engineered to cut compute expenses and drop inference latency. When your application makes a call, the gateway inspects a central memory layer before routing traffic to external LLMs. If an identical query was previously processed by OpenAI, Anthropic, or Mistral, our gateway returns that response immediately. This shared cache eliminates duplicate token fees and insulates your production apps from vendor rate limits or unexpected downtime. Developers can easily customize expiration settings, enforce strict data privacy controls, and configure invalidation logic across every endpoint. Stop wasting your budget on repeated queries. Enable prompt caching in your dashboard to accelerate your pipeline today.

out 3833 tok (+3688 thinking) latency 21.8 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-pro-0813",
    # model="gemini-3.8-flash",  # uncomment this line, comment the one above
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

Get your API key →

FAQ

Which is cheaper, DeepSeek V4 Pro (0813) or Gemini 3.8 Flash?

Gemini 3.8 Flash is cheaper on input / 1m tokens ($0.75 vs $1.32, 1.8× 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 Pro (0813) against Gemini 3.8 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 Pro (0813) and Gemini 3.8 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