tokenstat
tokenstat

DeepSeek: V4 Flash Vision Exp

deepseek/deepseek-v4-flash-vision-exp · rates as of · How this catalog is built · Benchmarks

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

Cheapest input
$0.14
$/MTok · models.dev
Cheapest output
$0.28
$/MTok
Context
1.0M
tokens
Sources
3
21 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↑ higherOutput $0.2 → $0.28
  • ↑ higherInput $0.08 → $0.14
  • ↓ lowerOutput $0.28 → $0.2
  • ↓ lowerInput $0.14 → $0.08
  • ↓ lowerOutput $0.66 → $0.28
  • ↓ lowerInput $0.22 → $0.14

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (1 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
models.devcheapestdeepseek-v4-flash-vision-expOpenCode$0.14$0.28$0.0281M
models.devdeepseek/deepseek-v4-flash-vision-expCommandCode$0.15$0.6$0.0031M
models.devdeepseek-v4-flash-vision-expDeepSeek$0.15$0.6$0.0031.0M
models.devdeepseek/deepseek-v4-flash-vision-expEden AI$0.15$0.6$0.0031M
models.devdeepseek-v4-flash-vision-expAIHubMix$0.155$0.62$0.00311M
models.devdeepseek/deepseek-v4-flash-vision-expKilo Gateway$0.2156$0.6468$0.00691.0M
models.devdeepseek/deepseek-v4-flash-vision-expNanoGPT$0.2156$0.6468$0.00691.0M
OpenRouterdeepseek/deepseek-v4-flash-vision-expOpenRouter$0.2156$0.6468$0.00691.0M
models.devdeepseek/deepseek-v4-flash-vision-expVercel AI Gateway$0.2156$0.6468$0.00681.0M
models.devdeepseek/deepseek-v4-flash-vision-expOrcaRouter$0.22$0.66$0.0071M
LiteLLMaccounts/fireworks/models/deepseek-v4-flash-vision-expN/A$0.22$0.66$0.007N/A
LiteLLMfireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-expN/A$0.22$0.66$0.007N/A
models.devdeepseek/deepseek-v4-flash-vision-expCrossModel$0.3$1.20$0.0061M
LiteLLMdeepseek/deepseek-v4-flash-vision-expN/A$0.3$1.20$0.006N/A
LiteLLMdeepseek-v4-flash-vision-expN/A$0.3$1.20$0.006N/A
LiteLLMkyma/deepseek-v4-flash-vision-expN/A$0.3892$1.17$0.0389N/A
models.devdeepseek/deepseek-v4-flash-vision-expAI/ML API$0.44$1.32$0.0141.0M
models.devdeepseek-ai/DeepSeek-V4-Flash-Vision-ExpDeepInfra$0.44$1.32$0.0141.0M
models.devdeepseek-ai/DeepSeek-V4-Flash-Vision-ExpHugging Face$0.44$1.32$01.0M
models.devdeepseek-ai/DeepSeek-V4-Flash-Vision-ExpSiliconFlow$0.44$1.32$0.0281M
LiteLLMnovita/deepseek/deepseek-v4-flash-vision-expN/A$0.44$1.32$0.028N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • Out: text
Knowledge cutoff: 2025-05Released: 2026-08-21Output limit: 262K tokensFamily: deepseek-flash

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.