providers/DeepSeek
DeepSeek · Hangzhou, China

DeepSeek models on AIgateway — pricing, context, capabilities

DeepSeek ships 6 models on AIgateway spanning reasoning, text. Call any of them via the OpenAI-compatible endpoint at api.aigateway.sh/v1 with one key. Pass-through inference pricing, no seat fees, no minimum.

Get your key →See pricingVisit DeepSeek →
models · 6modalities · reasoning, textlocation · Hangzhou, China
reasoning

DeepSeek reasoning models

1 reasoning model from DeepSeek.

Deepseek-R1-Distill-Qwen-32b
deepseek/deepseek-r1-distill-qwen-32b
DeepSeek-R1-Distill-Qwen-32B is a model distilled from DeepSeek-R1 based on Qwen2.5. It outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
$0.500 in · $4.88 out / 1M80,000 ctx
text

DeepSeek text models

5 text models from DeepSeek.

Deepseek-V4-Pro-0813
deepseek/deepseek-v4-pro-0813
DeepSeek V4 Pro is a high-capability reasoning model from DeepSeek with a one million token context window, built for long-horizon agentic workflows and complex, multi-step problem-solving
$1.32 in · $3.96 out / 1M1,048,576 ctx
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
DeepSeek V4 Pro is a high-capability reasoning model from DeepSeek, served via Fireworks infrastructure for production-grade inference.
$2.40 in · $4.80 out / 1M131,072 ctx
DeepSeek V4 Flash
deepseek/deepseek-v4-flash
$0.200 in · $0.400 out / 1M
Deepseek-V4-Flash-0731
deepseek/deepseek-v4-flash-0731
DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities.
$0.440 in · $1.32 out / 1M1,310,720 ctx
DeepSeek V3.2
deepseek/deepseek-v3.2
$0.570 in · $1.71 out / 1M
About DeepSeek

Who they are, what they focus on

DeepSeek builds open-weight frontier reasoning models. DeepSeek R1 and the R1-distilled variants brought step-by-step reasoning to open weights at a fraction of closed-model cost. Strong on math, code, and structured planning.

Headquartered in Hangzhou, China. Homepage: deepseek.com.

FAQ

Common questions about DeepSeek on AIgateway

Which DeepSeek models does AIgateway support?
AIgateway routes 6 DeepSeek models including Deepseek-V4-Pro-0813. Full catalog with pricing and context windows is in the sections above.
How do I call a DeepSeek model from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to the DeepSeek slug (e.g. "deepseek/deepseek-v4-pro-0813"). Request and response shapes are identical to OpenAI.
How much do DeepSeek models cost on AIgateway?
Pass-through DeepSeek pricing. No seat fees, no minimum beyond the $5 top-up floor.
Can I bring my own DeepSeek API key (BYOK)?
Yes. Attach your DeepSeek key in the AIgateway dashboard. Calls to DeepSeek models flip to pass-through and AIgateway adds no platform fee on those calls.
Where is DeepSeek based?
DeepSeek is headquartered in Hangzhou, China.
Is there free credit?
A payment method is required to call the API — adding a card is free and never charges you, and grants $1 in credit across a curated trial catalog led by GLM-5.3 Flash. The $1 expires 30 days after you add the card. Paid DeepSeek models require a $5 minimum credit top-up.
Other providers

Browse other labs

Anthropic →OpenAI →Google →xAI →Moonshot →Meta →Mistral →Alibaba →Deepgram →Black Forest Labs →BAAI →All providers →