DeepSeek V4 Flash Vision (Exp)

deepseek/deepseek-v4-flash-vision-exp
New
VisionToolsJSONReasoning
by DeepSeek · 2026-08-21

Experimental vision-enabled variant of DeepSeek V4 Flash: text + image in, text out, 1M context, 384K max output, thinking and non-thinking modes. Pure-text capability on par with V4 Flash; multimodal agent capability approaching Opus 4.8.

Endpoints:/v1/chat/completions
ctx1M tokens
Max output384K
Inputtext + image
Outputtext
p50 TTFT384 ms
INPUT$0.15/ 1M tokens
OUTPUT$0.29/ 1M tokens
p50 TTFT384 ms7d
p95 TTFT441 ms7d
TRAFFIC65.7Ktokens / 7d
Get the DeepSeek V4 Flash Vision (Exp) API →▶ Try in playground</> Use via API

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash-vision-exp",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • logprobs
  • max_tokens
  • reasoning
  • response_format
  • stop
  • stream
  • stream_options
  • temperature
  • thinking
  • tool_choice
  • tools
  • top_logprobs
  • top_p
  • user_id

Pricing

Input / 1M tokens · Off-peak$0.147
Output / 1M tokens · Off-peak$0.295
Cache read / 1M · Off-peak$0.020
Peak hours01:00–04:00, 06:00–10:00 ×2 (UTC)
Input / 1M tokens · ×2$0.294
Output / 1M tokens · ×2$0.590
Cache read / 1M · ×2$0.040
CurrencyUSD

Estimates below use the off-peak rate; peak windows multiply token prices as shown above.

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $1.91 · With prompt caching $1.47

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000150

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

last 7 days
p50 TTFT
384 ms
Output speed
103 tok/s
p95 TTFT
441 ms
Error rate
0%

Public benchmarks

Last evaluated 2026-08-21
Agents' Last Exam
27.3
ApexBench (Pass@1)
36.5
AutomationBench (Public)
25.7
Chartography
64.3
DeepSWE
59.3
DSBench-Hard
63.6
NL2Repo
57.7
Terminal-Bench 2.1
83.9
ZeroBench (Pass@5)
35.0
Source: api-docs.deepseek.com

Community buzz

What developers are saying this week

Hacker News2 mentions · 7dup 1 vs the previous week

How it compares

DeepSeek V4 Flash Vision (Exp)DeepSeek V4 ProDeepSeek V4 FlashDeepSeek V4 Pro 0813
Input $/M$0.15$0.44$0.15$0.44
Output $/M$0.29$0.88$0.29$0.88
Context1.0M1.0M1.0M1.0M
Quality7/108/107/107/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

Browse AI model comparisons →

More from DeepSeek

See all models from deepseek →
DeepSeek V4 Flash 0731New
deepseek/deepseek-v4-flash-0731
$0.15 in · $0.29 out / 1M
1M ctx· quality 6/10
 Compare side-by-side
DeepSeek V3
deepseek/deepseek-chat
$0.15 in · $0.29 out / 1M
1M ctx· quality 5/10
 Compare side-by-side
deepseek/deepseek-reasoner
deepseek/deepseek-reasoner
$0.15 in · $0.29 out / 1M
1M ctx· quality 5/10
 Compare side-by-side

FAQ

How much does DeepSeek: DeepSeek V4 Flash Vision (Exp) cost on OrcaRouter?
DeepSeek: DeepSeek V4 Flash Vision (Exp) is priced at $0.15 per 1M input tokens and $0.29 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
What is DeepSeek: DeepSeek V4 Flash Vision (Exp)'s context window?
DeepSeek: DeepSeek V4 Flash Vision (Exp) supports a context window of 1M tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call DeepSeek: DeepSeek V4 Flash Vision (Exp) via the OpenAI SDK?
Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="deepseek/deepseek-v4-flash-vision-exp" in the chat.completions.create call.
Does OrcaRouter rate-limit DeepSeek: DeepSeek V4 Flash Vision (Exp)?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.

Embed this badge

Paste into your blog post
DeepSeek: DeepSeek V4 Flash Vision (Exp)•$0.15/M in•384ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/deepseek/deepseek-v4-flash-vision-exp" target="_blank"> <img src="https://www.orcarouter.ai/embed/deepseek/deepseek-v4-flash-vision-exp.svg" alt="DeepSeek: DeepSeek V4 Flash Vision (Exp) on OrcaRouter" /> </a>
Markdown [![DeepSeek: DeepSeek V4 Flash Vision (Exp)](https://www.orcarouter.ai/embed/deepseek/deepseek-v4-flash-vision-exp.svg)](https://www.orcarouter.ai/models/deepseek/deepseek-v4-flash-vision-exp)

Model card as data

GET /api/public/models/deepseek/deepseek-v4-flash-vision-expOpen
Machine-readable:/llms.txt/llms-full.txt