DeepSeek Chat

DeepSeek · DeepSeek V3.2 · budget · Current model version: DeepSeek-V3.2 · deprecated Jul 24, 2026 · deepseek-chat

DeepSeek V3.2 family:DeepSeek Chat·DeepSeek Reasoner

DeepSeek's non-thinking lane with extremely low pricing and basic tool and JSON support.

Pricing

Input$0.028 / 1M cache hit, $0.28 / 1M cache miss

Cached input$0.028 / 1M

Output$0.42 / 1M

Pricing page lists both cache-hit and cache-miss token rates.

Cost bandUltra-budget

Free tierPaid API; pricing is among the lowest publicly listed.

Context window128k checked Jul 19, 2026

Max output8k

Knowledge cutoffNot surfaced in pricing page

DeploymentDeepSeek API

OpenAI-compatible APIYes

ModalitiesText

Best forLow-cost chat, extraction, and automation where price dominates the shortlist.

Business fitA budget disruptor, but teams should weigh policy, governance, and deployment constraints carefully.

JSON outputTool callsPrefix completionFIM completion

Composite84 / 100

Coding87 / 100 (SWE-bench Verified)

Reasoning83 / 100 (GPQA Diamond)

Long context78 / 100 (RULER 64K)

Vision68 / 100

Instruction following87 / 100 (IFEval)

Editorial aggregate of published benchmark results as of Oct 1, 2025. These are not independent measurements run by this site.

Jul 19, 2026DeprecatedDeepSeek Chat API name retires Jul 24, 2026 DeepSeek retires the deepseek-chat model name on 2026-07-24 15:59 UTC; requests fold into deepseek-v4-flash (thinking and non-thinking modes). DeepSeek API docs

Last checkedJul 19, 2026

Cross-checked againstopenrouter.ai/deepseek/deepseek-chat

Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.