DeepSeek-V3.1

deepseek· 2025-08-21· 128K ctx· mit

open weightstool call quant: unknown

spread (output)

2.5×

$0.700 – $1.72 · 20 providers

20 providers priced

Provider	Input	Output	Cache rd	Blended
NanoGPT relay router	$0.200	$0.700	$0.100	$0.182
TokenGo relay router	$0.190	$0.710	$0.060	$0.155
submodel relay router	$0.200	$0.800	—	$0.255^*
Vercel AI Gateway unknown	$0.250	$0.950	$0.130	$0.237
OpenRouter unknown	$0.250	$0.950	$0.130	$0.237
Deep Infra open weights host	$0.250	$0.950	$0.130	$0.237
Hugging Face relay router	$0.270	$1.00	—	$0.336^*
SiliconFlow relay router	$0.270	$1.00	—	$0.336^*
Jiekou.AI relay router	$0.270	$1.00	—	$0.336^*
Meganova relay router	$0.270	$1.00	—	$0.336^*
NovitaAI relay router	$0.270	$1.00	$0.135	$0.251
Baseten relay router	$0.500	$1.50	—	$0.591^*
Merge Gateway unknown	$0.500	$1.50	—	$0.591^*
CoreWeave relay router	$0.550	$1.65	$0.550	$0.650
Abacus relay router	$0.550	$1.66	—	$0.651^*
Pioneer relay router	$0.560	$1.68	$0.560	$0.708
Amazon Bedrock hyperscaler	$0.580	$1.68	—	$0.680^*
Vertex hyperscaler	$0.600	$1.70	$0.060	$0.356
Together AI open weights host	$0.600	$1.70	—	$0.700^*
Alibaba (China) relay router	$0.574	$1.72	—	$0.678^*

Cheapest (output)

NanoGPT

$0.700 /M

opencode.json

{
  "provider": {
    "nano-gpt": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://nano-gpt.com/api/v1"
      },
      "models": {
        "deepseek-ai/DeepSeek-V3.1": {}
      }
    }
  }
}

Set NANO_GPT_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.