DeepSeek

DeepSeek V3 (0324)

164K ctxText Tools

Released Mar 24, 2025 · 66B tokens this week · 4 providers

Overview

A mid-2025 refresh of DeepSeek V3 with better coding and front-end generation. A solid, inexpensive general model with fully open weights. Still widely served because so many providers have it warm.

programmingtranslationroleplay

Providers

Reference data — not yet measured from live traffic

PROVIDER		MAX OUT		OUTPUT /M				QUANT
DeepInfraCheapest	164K	16K	$0.25	$0.88	620ms	92	98.80%	fp8
Novita AI	164K	16K	$0.27	$0.94	680ms	80	98.50%	fp8
Hyperbolic	131K	16K	$0.28	$0.97	760ms	60	97.80%	fp8
Together AI	164K	16K	$0.28	$1.00	195ms	118	99.40%	Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

Grok 4 Fast$0.42

DeepSeek V3 (0324)$0.72

Gemini 3 Flash$1.95

GPT-5.2$10.94

Claude Sonnet 4.5$12.00

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v3-0324",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'