tokenstat
tokenstat

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731 · rates as of · Benchmarks · Plans · Calculator

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Cheapest input
$0.09
$/MTok · OpenRouter
Cheapest output
$0.18
$/MTok
Context
1.0M
tokens
Offers
3
2 sources

Price changes

Cheapest list input/output only. Not a daily candle chart: rates move rarely, so this is an event log. Arrow down means cheaper.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ dropOutput $0.28 → $0.18
  • ↓ dropInput $0.14 → $0.09

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
OpenRoutercheapestdeepseek/deepseek-v4-flash-0731OpenRouter$0.09$0.18$0.0181.0M
models.devdeepseek/deepseek-v4-flash-0731Vercel AI Gateway$0.13$0.26$0.0281M
models.devdeepseek/deepseek-v4-flash-0731Kilo Gateway$0.14$0.28$0.0281.0M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-05Released: 2026-07-31Family: deepseek-flash

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash