星海词元星海词元
Ready to build?Get an API key — all models at 50% of the official price →
Home › Models › deepseek-flash

deepseek-flash API

Call deepseek-flash through a single OpenAI-compatible endpoint — one key, no separate vendor account, no multi-provider wiring.

DeepSeekChatVisionReasoningCoding工具调用Long context超大输出快速

Pricing

Input$0.15 / 1M tokens  (¥0.97)
Output$0.60 / 1M tokens  (¥3.90)
Output multiplier×4.00
Context window1M tokens

Prices are per 1M tokens in USD · ¥6.5 = $1 · Billed in CNY

DeepSeek

DeepSeek models are the default choice for high-volume workloads: strong reasoning, long context and a price point that makes them viable as an always-on backbone. On StarSeaAPI every DeepSeek variant is served through multiple independent upstream routes, so a single provider incident does not take the model offline.

When to use it

At $0.15 per 1M input tokens it sits below the catalogue median of $0.50 — a cost-first choice. Best for coding agents and repository-scale edits. Every model here is reachable with the same API key, so trialling it against a stronger sibling costs one line of code.

Code

from openai import OpenAI
client = OpenAI(
  base_url="https://starseaapi.com/v1",
  api_key="sk-your-key"
)
r = client.chat.completions.create(
  model="deepseek-flash",
  messages=[{"role": "user", "content": "Explain prefix caching in one paragraph"}]
)
print(r.choices[0].message.content)

Integrations · Quickstart

Other models from this provider

ModelsInput $/MOutput $/MIntelligence indexCoding index
deepseek-v4-flash$0.15$0.6034.369.1
deepseek-v4-flash-0731$0.15$0.6034.369.1
deepseek-v4.1-flash$0.15$0.6039.5—
deepseek-v4-pro$0.66$1.9836.068.8
deepseek-v4-pro-0813$0.66$1.9836.068.8

Capabilities