← Model list

DeepSeek-V3.1

deepseek·deepseek/deepseek-v3.1·Deprecated·Open weights·deepseek series

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

At a glance
Reference price$0.60 / $1.70 per 1M
Cache read · Together AI
Lowest paid$0.20 / $0.70
NanoGPT Gateway · 3× spread
Context131,072
⚠ Providers report 75,000–164,000; the table below is authoritative
Output limit131,072
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextPDF
Knowledge cutoff2025-03-31
Released / updated2025-08-21 / 2025-08-21

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Non-reasoning

Intelligence21.4
Value66
Coding
Agentic
Output speed
TTFT
Value formulaIQ 21.4 ÷ min blended $0.325 = 66
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
ReasoningIQ 21
Non-reasoningIQ 21.4

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 19 providers18 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPT
deepseek-ai/DeepSeek-V3.1
Gateway$0.20$0.70$0.10128,00065,536
submodel
deepseek-ai/DeepSeek-V3.1
Gateway$0.20$0.8075,000163,840
Deep Infra
deepseek-ai/DeepSeek-V3.1
Cloud$0.25$0.95$0.13163,8408,192
OpenRouter
deepseek/deepseek-chat-v3.1
Gateway$0.25$0.95$0.13163,84032,768
Vercel AI GatewayCloud$0.25$0.95$0.13163,840128,000
Meganova
deepseek-ai/DeepSeek-V3.1
Gateway$0.27$1.00164,000164,000
Hugging Face
deepseek-ai/DeepSeek-V3.1
Cloud$0.27$1.00131,0728,192
Jiekou.AIGateway$0.27$1.00163,84032,768
NovitaAIGateway$0.27$1.00$0.135131,07232,768
Merge GatewayGateway$0.50$1.50164,00041,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1NanoGPT$63.00
2submodel$80.00
3Deep Infra$83.10
4OpenRouter$83.10
5Vercel AI Gateway$83.10
6NovitaAI$87.80
The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

Toggle (on / off)budget_tokens ≥ 1,024 ≤ 32,767effort = loweffort = mediumeffort = higheffort = xhigh

8 / 19 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.70$02026-08-052026-08-132026-08-05 · Input list $0.602026-08-06 · Input list $0.602026-08-07 · Input list $0.602026-08-08 · Input list $0.602026-08-09 · Input list $0.602026-08-10 · Input list $0.602026-08-11 · Input list $0.602026-08-12 · Input list $0.602026-08-13 · Input list $0.602026-08-05 · Output list $1.702026-08-06 · Output list $1.702026-08-07 · Output list $1.702026-08-08 · Output list $1.702026-08-09 · Output list $1.702026-08-10 · Output list $1.702026-08-11 · Output list $1.702026-08-12 · Output list $1.702026-08-13 · Output list $1.702026-08-05 · Min blended $0.3252026-08-06 · Min blended $0.3252026-08-07 · Min blended $0.3252026-08-08 · Min blended $0.3252026-08-09 · Min blended $0.3252026-08-10 · Min blended $0.3252026-08-11 · Min blended $0.3252026-08-12 · Min blended $0.3252026-08-13 · Min blended $0.325