DeepSeek V3.2 API model profile

Evidence snapshot: 2026-08-12

DeepSeek V3.2 is a DeepSeek model profile with a 163,840-token context window. The dated catalog snapshot records text modalities and interfaces for coding, prompt caching, reasoning, reasoning controls, structured output.

DeepSeek V3.2 is available under the Kendr alias kc-deepseek-v3.2. Current account availability and customer credit quotes come from Kendr's live public model API and applicable account policy.

DeepSeek V3.2 accepts text and returns text. The snapshot records coding, prompt caching, reasoning, reasoning controls, structured output, text generation, tool calling, tools, and web search as capabilities or interfaces.

The dated reference snapshot lists $0.269 input and $0.4 output per million tokens. Cached input is $0.1345 per million tokens. The separately published provider-route reference is $0.62 / $1.85.

DeepSeek V3.2 ranked #28 in the cited trailing-7-day third-party catalog usage dataset as of 2026-08-12. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.

Profile data was reviewed for the 2026-08-12 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.

Profile facts

Profile type: Kendr API model
Kendr API alias: kc-deepseek-v3.2
Model developer: DeepSeek
Kendr route provider: DeepSeek
Context window: 164K
Snapshot date: 2026-08-12
Reference catalog ID: deepseek/deepseek-v3.2

Context, modalities, and identity

Model developer: DeepSeek
Kendr route provider: DeepSeek
Context window: 164K
Maximum output: 65,536 tokens
Input modalities: text
Output modalities: text
Knowledge cutoff: Not disclosed

Capabilities and supported controls

Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.

Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

coding
prompt caching
reasoning
reasoning controls
structured output
text generation
tool calling
tools
web search

Dated pricing snapshot

The dated reference snapshot lists $0.269 input and $0.4 output per million tokens. Cached input is $0.1345 per million tokens. The separately published provider-route reference is $0.62 / $1.85.

Reference figures are dated 2026-08-12; the live Kendr quote can differ by selected provider route, context tier, caching, tools, region, and current rate card.

Price date: 2026-08-12
Input: $0.269 per 1M tokens
Cached input: $0.1345 per 1M tokens
Output: $0.4 per 1M tokens

Benchmark evidence and limitations

Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Coding Index: 44.2

Design Arena category	Elo	Win rate	Rank
3d	1187	49.5%	#52
asciiart	1120	40.5%	#50
codecategories	1190	49.3%	#60
dataviz	1184	48.1%	#58
gamedev	1172	46.6%	#61
svg	1078	40.8%	#59
uicomponent	1182	46.8%	#59
website	1195	50.2%	#58

Popularity and market context

Third-party catalog rank: #28
Global market share: Not inferred
Observation date: 2026-08-12

OpenAI-compatible API example

This example applies to the published Kendr alias on this hosted profile. Check the live public catalog before use.

curl https://api.kendr.org/v1/chat/completions \
  -H "Authorization: Bearer $KENDR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kc-deepseek-v3.2","messages":[{"role":"user","content":"Hello"}]}'

Frequently asked questions

What is DeepSeek V3.2?

What context window does DeepSeek V3.2 have?

The dated profile lists 164K of context and up to 65,536 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.

What benchmark evidence is available for DeepSeek V3.2?

The 2026-08-12 snapshot includes 1 Artificial Analysis index and 8 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

What is the Kendr API alias for DeepSeek V3.2?

Use kc-deepseek-v3.2 as the model value. The live public model API and signed-in catalog remain authoritative for route availability and customer credit quotes.

How is DeepSeek V3.2 priced on Kendr?

The dated reference snapshot lists $0.269 input and $0.4 output per million tokens. Cached input is $0.1345 per million tokens. The separately published provider-route reference is $0.62 / $1.85. Kendr applies one 5% markup to configured provider model cost; the live quote and settled routing receipt are authoritative for a request.

Sources and evidence dates

DeepSeek V3.2 third-party catalog record (catalog, checked 2026-08-12)
Third-party model catalog methodology (methodology, checked 2026-08-12)
DeepSeek official model documentation (primary, checked 2026-08-12)
Artificial Analysis capability indices methodology (benchmark, checked 2026-08-12)
Design Arena leaderboard and methodology (benchmark, checked 2026-08-12)
DeepSeek V3.2 provider or route reference (primary, checked 2026-08-12)