DeepSeek R1 0528 NVFP4

Open weights

DeepSeek R1 0528 NVFP4 is a language model from Deepseek with a 160K-token context window. Provider list price is $3 per million input tokens and $7 per million output; on Allocate you pay $3.21 and $7.49 with the 7% transaction fee. The weights are open under MIT, so you can fine-tune it and own the result.

Route DeepSeek R1 0528 NVFP4 Talk to sales

Pricing

Provider listOn Allocate

Input, per M tokens$3$3.21

Output, per M tokens$7$7.49

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

Price against its peers

Kimi K2.6 Fp4$1.20$4.50

GLM 5.1 FP4$1.40$4.40

GLM 5.2$1.40$4.40

Gemini 3.5 Flash$1.50$9

Qwen2.5-VL (72B) Instruct$1.95$8

Gemini 3.1 Pro$2$12

DeepSeek R1 0528 NVFP4$3$7

Meta Llama 3.1 405B Instruct$3.50$3.50

InputOutput

Provider list prices per M tokens, DeepSeek R1 0528 NVFP4 against its nearest language peers by price.

What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $3 + 350 × $7 = $6,050 a month. Billed on Allocate it is $6,474 with the 7% transaction fee.

DeepSeek R1 0528 NVFP4 is an open-weights model under the MIT license. Fine-tune it on your own data and the weights stay inside your boundary; they belong to you.

Example usage

Point a route at deepseek/deepseek-r1-0528 and the endpoint never changes; swap the model behind it whenever you want.

api.allocate.network

curl https://api.allocate.network/v1/chat/completions \
  -H "Authorization: Bearer $ALLOCATE_KEY" \
  -d '{
    "model": "deepseek/deepseek-r1-0528",
    "messages": [{"role": "user",
      "content": "Summarise the attached contract."}]
  }'

200 · deepseek/deepseek-r1-0528 · inside your boundary

Common questions

How much does DeepSeek R1 0528 NVFP4 cost per million tokens?

Provider list price is $3 per million input tokens and $7 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $3.21 in and $7.49 out.

What context window does DeepSeek R1 0528 NVFP4 have?

163,840 tokens (160K). At roughly 0.75 words per token, that is about 123k words of English text per request.

Can I fine-tune DeepSeek R1 0528 NVFP4?

Yes. DeepSeek R1 0528 NVFP4 is an open-weights model under the MIT license. The license is permissive, so the fine-tuned weights are yours to use commercially. On Allocate the trained weights stay inside your boundary and belong to you.

How do I call DeepSeek R1 0528 NVFP4 on Allocate?

Send deepseek/deepseek-r1-0528 in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.