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

DeepSeek V4 Pro vs Kimi K2.7 Code

vs

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

Pick deepseek-v4-pro for long-context, high-volume text: a 1000000-token window, up to 393216 output tokens, cache reads at $0.0134 per million versus $0.19 (about 14x cheaper) and output at $3.216 versus $4. Pick kimi-k2.7-code when you need image or video input or cheaper ingestion, since its $0.95 input undercuts the $1.608 by roughly 1.7x, accepting 256000 context, a 32768-token output cap and reasoning that cannot be disabled. Both cover chat, code, reasoning and tools, so the real split is modality and context, not features.

Pricing

DeepSeek V4 Pro Kimi K2.7 Code Δ
Input / 1M tokens $1.608 $0.95 1.7×
Output / 1M tokens $3.216 $4 0.8×
Cache read / 1M tokens $0.0134 $0.19 0.071×
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 K2.7 Code · $0.95
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

Capabilities

DeepSeek V4 Pro Kimi K2.7 Code
Tool use yes yes
Thinking control configurable always on
Structured output 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 K2.7 Code
Input modalities text text image video
Output modalities text text
Released 2026-04-24 2026-06
Context window 1M 256K
Max output 393K 33K
Thinking parameter
  • thinking.type
  • reasoning_effort
  • thinking.type
  • thinking.keep
Accepted values
thinking.type
  • enabled
  • disabled
reasoning_effort
  • high
  • max (low and medium map to high, xhigh maps to max)
type
  • accepts only enabled
keep
  • accepts only all
Default

enabled, with reasoning_effort high

some complex agent requests are automatically set to max

thinking on with Preserved Thinking on

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 K2.7 Code

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 K2.7 Code passed · 3 sentences

Enabling reasoning mode causes the model to generate an internal chain-of-thought before producing each answer, and that hidden reasoning text is billed like any other output. Those extra reasoning tokens typically add up to much more than the final response itself, so every API call now costs significantly more than before. Because our overall usage volume did not change, the doubled bill reflects that each query consumes roughly twice as many billable tokens.

out 259 tok (+174 thinking) latency 5.4 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 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 K2.7 Code 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 that the function counts *transitions* between equal neighbors instead of counting the items themselves, so a single-element list never enters the loop and returns `0` instead of `1`. Likewise, resetting `cur` to `0` on a mismatch forgets the current item that starts a new run, which causes runs that end at the last index to be undercounted. Initializing both `best` and `cur` to `1` and resetting `cur` to `1` fixes both issues.

out 410 tok (+222 thinking) latency 9.4 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 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 K2.7 Code passed · 5/5 fields, guidance "withheld pending the Q4 close"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "withheld pending the Q4 close" } ```

out 721 tok (+663 thinking) latency 13.2 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 K2.7 Code passed · 120 words, 0 banned, 1 question

We're introducing Prompt Cache for our API Gateway, a new capability that stores prompt responses across multiple AI providers. By caching replies, you reduce redundant calls, lower latency, and cut costs without changing how you build. Teams using several model providers can now reuse identical prompt results instantly, keeping traffic consistent and budgets predictable. Responses are keyed by provider, model, and exact prompt, so you always get the right result. Configure TTL, hit thresholds, and eviction rules from a single dashboard. It fits into your existing routing and requires no code changes. Setup takes minutes and works with your current endpoints. Want to see how much latency and spend you can trim? Check the docs to enable Prompt Cache today.

out 2375 tok (+2235 thinking) latency 38.6 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-k2.7-code",  # 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 K2.7 Code?

Kimi K2.7 Code is cheaper on input / 1m tokens ($0.95 vs $1.608, 1.7× 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 K2.7 Code 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 K2.7 Code 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