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

Claude Sonnet 5 vs DeepSeek V4 Pro (0813)

vs

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

Both share a 1,000,000-token context window, so the split is about modality and cost: claude-sonnet-5 accepts image input alongside text and exposes a thinking mode you can switch off, while deepseek-v4-pro-0813 is text-only but roughly 1.5x cheaper on input ($1.32 vs $2 per million) and about 2.5x cheaper on output ($3.96 vs $10). Pick claude-sonnet-5 when the job involves images or you want explicit control over reasoning effort; pick deepseek-v4-pro-0813 for high-volume text work, or when you need single responses longer than 128000 tokens, since it allows up to 393216.

Pricing

Claude Sonnet 5 DeepSeek V4 Pro (0813) Δ
Input / 1M tokens $2 $1.32 1.5×
Output / 1M tokens $10 $3.96 2.5×
Cache read / 1M tokens $0.2 $0.132 1.5×
Cache write 1.25x (5m) / 2x (1h) 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)

Capabilities

Claude Sonnet 5 DeepSeek V4 Pro (0813)
Tool use yes yes
Thinking control configurable always on
Structured output yes yes
Prompt caching explicit (you mark the prefix) implicit (automatic)
Cache lifetime 5m default, 1h option no fixed TTL (evicted when unused)
Minimum cached prefix 1024 tokens not published

Specs

Claude Sonnet 5 DeepSeek V4 Pro (0813)
Input modalities text image text
Output modalities text text
Released 2026-06-30 2026-08-13
Knowledge cutoff 2026-01
Context window 1M 1M
Max output 128K 393K
Thinking parameter
  • thinking.type "adaptive"
  • output_config.effort
reasoning_effort
Accepted values
thinking.type
  • adaptive
  • disabled
effort
  • low
  • medium
  • high
  • xhigh
  • max

"enabled" returns 400

reasoning_effort
  • the model card documents low
  • high
  • max
Default

thinking on (adaptive)

effort
  • high

Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: Claude Sonnet 5 · DeepSeek V4 Pro (0813)

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

Claude Sonnet 5 passed · 3 sentences

Reasoning mode works by having the model generate extended internal "thinking" steps before producing its final answer, and since we're billed on total tokens, that hidden reasoning text adds significantly to what we pay for—even though you never see it in the output. This is different from simply getting longer visible responses; the model is essentially "showing its work" behind the scenes, and complex prompts can trigger thousands of extra reasoning tokens per request. The upside is improved accuracy on complex tasks, but if we want to control costs, we should selectively enable reasoning only for queries that truly need it, rather than applying it universally.

out 194 tok latency 4.3 s

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

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

Claude Sonnet 5 passed · 8/8 cases

## The Bug The function has two related off-by-one issues rooted in the same cause: `cur` and `best` are initialized to `0` instead of `1`, treating run lengths as the number of *matches* between adjacent elements rather than the number of *elements* in the run. This means a single-element input never enters the loop (since `range(1, 1)` is empty) and returns `0` instead of the correct answer of `1`. It also means that for any input, the run length is undercounted by exactly one — a run of 3 equal elements only produces 2 "match" increments, so `best` ends up as 2 instead of 3. The claim that it "misses runs that end at the last index" is actually a symptom of this same undercount: the logic does update `best` correctly on every iteration (including the last), but because it's counting matches instead of elements, the final reported value is always one less than the true longest run. […]

out 536 tok latency 7.1 s

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

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

Claude Sonnet 5 passed · 5/5 fields, guidance null

```json { "company": "Meridian Robotics", "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": 11.5, "guidance": null } ```

out 348 tok latency 5.3 s

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

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

Claude Sonnet 5 passed · 123 words, 0 banned, 1 question

## Introducing Cross-Provider Prompt Caching We're rolling out a new caching layer for our API gateway that works across every major LLM provider you connect through it. Instead of resending identical prompts and paying full price each time, the gateway recognizes repeated requests and serves cached responses in milliseconds—regardless of whether you're routing to OpenAI, Anthropic, or Google. What does this mean for your bill and your latency? Both drop, often significantly, especially for teams running high-volume, repetitive workloads like customer support bots or batch content generation. The cache is configurable per route, with adjustable TTLs and invalidation rules, so you stay in control of freshness versus cost. Available now for all Pro and Enterprise plans. Check your dashboard to enable it today.

out 259 tok latency 4.8 s

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

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="claude-sonnet-5",
    # model="deepseek-v4-pro-0813",  # 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, Claude Sonnet 5 or DeepSeek V4 Pro (0813)?

DeepSeek V4 Pro (0813) is cheaper on input / 1m tokens ($1.32 vs $2, 1.5× 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 Claude Sonnet 5 against DeepSeek V4 Pro (0813) 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 Claude Sonnet 5 and DeepSeek V4 Pro (0813) 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