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

DeepSeek V4 Pro vs Kimi K3

vs

Which one, when — curated verdict, not a benchmark table

Both are text-in reasoning models with chat, code and tools, but deepseek-v4-pro is the cheaper text-only path at $1.608 input and $3.216 output per million versus $3 and $15 for kimi-k3 — roughly 1.9x on input, 4.7x on output — and its $0.0134 cache reads are about 22x cheaper than kimi-k3's $0.3. Pick kimi-k3 when you need image or video input, a 1048576-token context, or up to 1048576 output tokens in one response; pick deepseek-v4-pro for high-volume text work, 1000000 tokens of context up to 393216 out, and the option to turn thinking off, which kimi-k3 does not allow.

Pricing

DeepSeek V4 Pro Kimi K3 Δ
Input / 1M tokens $1.608 $3 0.54×
Output / 1M tokens $3.216 $15 0.21×
Cache read / 1M tokens $0.0134 $0.3 0.045×
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 63 chat models on this billing unit (log scale)

DeepSeek V4 Pro · $1.608 Kimi K3 · $3
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

Capabilities

DeepSeek V4 Pro Kimi K3
Tool use yes yes
Thinking control configurable always on
Structured output yes yes
Prompt caching implicit (automatic) implicit (automatic)
Cache lifetime no fixed TTL (evicted when unused) not published
Minimum cached prefix not published not published

Specs

DeepSeek V4 Pro Kimi K3
Input modalities text text image video
Output modalities text text
Released 2026-04-24
Context window 1M 1M
Max output 393K 1M
Thinking parameter
  • thinking.type
  • reasoning_effort
reasoning_effort (top-level; the thinking object is not accepted)
Accepted values
thinking.type
  • enabled
  • disabled
reasoning_effort
  • high
  • max (low and medium map to high, xhigh maps to max)
reasoning_effort
  • low
  • high
  • max
Default

enabled, with reasoning_effort high

some complex agent requests are automatically set to max

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 · Kimi K3

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 passed · 3 sentences

Enabling reasoning causes the model to generate a lengthy internal chain‑of‑thought before it delivers a visible answer, and we are billed for every one of those hidden reasoning tokens just as we are for the final output. In most interactions, the volume of these unseen tokens at least equals the visible response, effectively doubling the total tokens consumed per query. That doubled token consumption translates directly into a doubled per‑query cost, which is why our overall LLM bill doubled.

out 641 tok (+545 thinking) latency 11.5 s

Kimi K3 passed · 3 sentences

Reasoning models don't just answer questions—they "think" first, generating long internal chains of step-by-step logic before producing a response. Those hidden thinking steps are billed as output tokens (the most expensive kind, typically 3–5x the price of input tokens), and a single query can generate thousands of them even when the visible answer is only a paragraph long. So you're paying for dramatically more compute per request: the bill doubled because the model does far more work behind the scenes, not because usage increased.

out 755 tok (+637 thinking) latency 20.8 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 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 best = max(best, cur) else: cur = 1 return best ``` **Explanation:** The bug stems from initializing `cur = 0` and only incrementing it when two adjacent elements match, which counts the number of *additional* equal elements rather than the actual run length (which is `cur + 1`). As a result, the returned `best` is always one less than the true longest run—most obviously returning 0 for a single-element list instead of 1. […]

out 2418 tok (+2131 thinking) latency 35.6 s

Kimi K3 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 best = max(best, cur) else: cur = 1 return best ``` The bug is a fencepost error: `cur` counts *matching adjacent pairs* rather than *items in the run*, because it starts at 0 and only increments when `xs[i] == xs[i - 1]`. A run of length L contains L−1 equal pairs, so every run was undercounted by exactly one. For a single-element list (a run of length 1) the loop never runs and the function returns 0 instead of 1; likewise any run ending at the last index — e.g. the two `2`s in `[1, 2, 2]` — reported 1 instead of 2, making it look like no run existed at all. […]

out 1837 tok (+1547 thinking) latency 47.2 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 passed · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": "eleven and change", "guidance": null }

out 1204 tok (+1153 thinking) latency 19.9 s

Kimi K3 passed · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }

out 924 tok (+863 thinking) latency 25.9 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 no answer to grade · no answer text within 16,384 tokens (all of it went to thinking)

The model returned no answer text — the whole token budget went to hidden thinking.

out 8193 tok (+8192 thinking) latency 106.2 s

Kimi K3 passed · 120 words, 0 banned, 1 question

Meet Prompt Cache, a new API gateway capability that stores prompt responses and serves them across OpenAI, Anthropic, Google, and Azure endpoints. It matches requests by model, prompt hash, tools, temperature, and tenant policy, so repeated work returns fast while sensitive contexts stay isolated. Teams set TTLs, stale rules, encryption scopes, and bypass flags per route. Analytics show hit rate, latency saved, token spend avoided, and drift risk by provider. What changes for developers? Keep one integration, add cache headers, and watch fallback logic respect consent, residency, and audit needs. During rollout, canary keys compare fresh answers with cached copies before promotion. Prompt Cache cuts vendor calls, steadies p95 latency, and gives platform owners controls for cost, quality, and compliance.

out 1527 tok (+1354 thinking) latency 37.9 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",
    # model="kimi-k3",  # uncomment this line, comment the one above
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

Get an API key →

FAQ

Which is cheaper, DeepSeek V4 Pro or Kimi K3?

DeepSeek V4 Pro is cheaper on input / 1m tokens ($1.608 vs $3, 1.9× 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 against Kimi K3 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 and Kimi K3 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