LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

DeepSeek V4 Flash Vision Exp

deepseek·deepseek/deepseek-v4-flash-vision-exp·GA·Open weights·deepseek-flash series·NEW
Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·OpenCodeGateway
$0.14 / $0.28
Blended $0.18 · 3.1× spread
1 more $0 channels
Context
1,048,576
Output limit
384,000
Knowledge cutoff
—
Released / updated
2026-08-21 / 2026-09-01
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImage
License
MIT
Weights
Hugging Face

DeepSeek V4 Flash Vision Exp is offered by 16 providers on this page. Public prices are shown for 15 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is OpenCode at $0.14 / $0.28 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 3.1× across the providers that host it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,050,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice.

Available at 16 providers15 with public prices · 1 free

  • ProviderInput / Output
  • AMDCloud
    DeepSeek-V4-Flash-Vision-Exp
    Free
    Cache read $0Context 1,000,000 ⚠Output limit 384,000deprecated
  • OpenCodeGateway
    $0.14 / $0.28
    Cache read $0.028Context 1,000,000 ⚠Output limit 384,000deprecated
  • CommandCodeGateway
    $0.15 / $0.60
    Cache read $0.003Context 1,000,000 ⚠Output limit 384,000
  • Eden AIGateway
    $0.15 / $0.60
    Cache read $0.003Context 1,000,000 ⚠Output limit 384,000
  • AIHubMixGateway
    $0.16 / $0.62
    Cache read $0.0031Context 1,000,000 ⚠Output limit 384,000deprecated
  • NanoGPTGateway
    $0.22 / $0.65
    Cache read $0.0069Context 1,048,576Output limit 384,000
  • Vercel AI GatewayCloud
    $0.22 / $0.65
    Cache read $0.0068Context 1,048,576Output limit 1,048,576
  • OrcaRouterGateway
    $0.22 / $0.66
    Cache read $0.007Context 1,000,000 ⚠Output limit 384,000
  • LLM GatewayGateway
    $0.44 / $1.32
    Context 1,048,576Output limit 262,144
  • DevPass (LLM Gateway)Gateway
    $0.44 / $1.32
    Context 1,050,000 ⚠Output limit 384,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
AMD
DeepSeek-V4-Flash-Vision-Exp
CloudFree$0—1,000,000 ⚠384,000deprecated
OpenCodeGateway$0.14$0.28$0.028—1,000,000 ⚠384,000deprecated
CommandCodeGateway$0.15$0.60$0.003—1,000,000 ⚠384,000
Eden AIGateway$0.15$0.60$0.003—1,000,000 ⚠384,000
AIHubMixGateway$0.16$0.62$0.0031—1,000,000 ⚠384,000deprecated
NanoGPTGateway$0.22$0.65$0.0069—1,048,576384,000
Vercel AI GatewayCloud$0.22$0.65$0.0068—1,048,5761,048,576
OrcaRouterGateway$0.22$0.66$0.007—1,000,000 ⚠384,000
LLM GatewayGateway$0.44$1.32——1,048,576262,144
DevPass (LLM Gateway)Gateway$0.44$1.32——1,050,000 ⚠384,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = maxToggle (on / off)budget_tokens ≥ 128 ≤ 32,768

Interleaved thinking (reasoning between tool calls) is declared by 5 of 16 providers.

Your usage cost

Common scenarios
1OpenCode$28.56
2CommandCode$42.36
3Eden AI$42.36
4AIHubMix$43.77
5Vercel AI Gateway$50.40
6NanoGPT$50.41

1 more channels offer $0 (AMD); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.60$02026-08-222026-10-20
2026-10-20Input list —Output list —Min blended $0.18

Benchmark11 items

NameConditionsScoreMetricSource
Terminal-Benchharness: DeepSeek Harness minimal mode · variant: max effort · v2.183.9scoreSource ↗
NL2Repoharness: DeepSeek Harness minimal mode · variant: max effort57.7scoreSource ↗
CyberGymharness: DeepSeek Harness minimal mode · variant: max effort75.3scoreSource ↗
DeepSWEharness: DeepSeek Harness minimal mode · variant: max effort59.3scoreSource ↗
Toolathlon-Verifiedharness: DeepSeek Harness minimal mode · variant: max effort75.9scoreSource ↗
DSBench-Hardharness: DeepSeek Harness minimal mode · variant: max effort · dataset: internal63.6scoreSource ↗
AutomationBenchharness: DeepSeek Harness minimal mode · variant: max effort · dataset: public25.7scoreSource ↗
ApexBench—36.5pass@1Source ↗
Agents' Last Exam—27.3scoreSource ↗
Chartography—64.3scoreSource ↗
ZeroBench—35pass@5Source ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

DeepSeek V4.1 Flash 1017same series$0.15 / $0.60DeepSeek: DeepSeek Flash Latestsame series—DeepSeek V4.1 Flashsame series—DeepSeek V4 Flash Latestsame lab—DeepSeek V4 Prosame lab—
Data partly from models.dev (MIT)