DeepSeek V4 Flash Vision
Aug 2026
RetiredReplace withDeepSeek V4.1 Flash 1017Same lab, current
GPT-6.1 SolCheaper, as goodGPT-6 LunaBetter
MiMo v2.6 ProOpen weights
DeepSeek V4.1 Flash 1017Same lab, currentGPT-6.1 SolCheaper, as goodGPT-6 LunaBetterMiMo v2.6 ProOpen weightsDeepSeek V4 Flash VisionCompare inon
Benchmarks of DeepSeek V4 Flash Vision18
BenchmarkByScoreRank
Overall1
Knowledge3
Science3
Coding2
Agents5
Multimodal1
Documents2
Legacy · saturated or no longer reported1
No benchmark matches
$1.04per task?
API price not publicprice
215 tok/sfirst token in 1.4 s?
1Mcontext
Ranking?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGPT-6.1 Solmax+49%-30%$0.72Remove unsupported parameters+5BetterMiMo v2.6 FlashthinkingOpen+9%-94%$0.062Pass back reasoning_content+3OpenMiMo v2.6 Prothinking+33%-87%$0.13Pass back reasoning_content+3
CheaperClaude Sonnet 5.5high+34%-15%$0.88No forced tool use+5CheaperGPT-6 Astralow+31%-21%$0.82Monitoring can return HTTP 403+2ModelScoreCostPer taskWhat changes
GPT-6.1 Solmax+49%-30%$0.72Remove unsupported parameters+5Claude Sonnet 5.5high+34%-15%$0.88No forced tool use+5MiMo v2.6 ProthinkingOpen+33%-87%$0.13Pass back reasoning_content+3GPT-6 Astralow+31%-21%$0.82Monitoring can return HTTP 403+2DeepSeek V4.1 Flash 1017maxOpen+29%-75%$0.26Pass back reasoning_content · Chat Completions+4ModelScoreCostPer taskWhat changes
MiMo v2.6 FlashthinkingOpen+9%-94%$0.062Pass back reasoning_content+3GPT-6 Lunamax+9%-93%$0.068Function calling only with none · Chat Completions+3Claude Haiku 5.5high+9%-92%$0.079Remove sampling parameters+5GPT-6.1 Sollow+21%-87%$0.13Remove unsupported parameters+5MiMo v2.6 ProthinkingOpen+33%-87%$0.13Pass back reasoning_content+3ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen+33%-87%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen+29%-75%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen+29%+93%$2.01No image input+4
Step 5 PreviewthinkingOpen+26%same$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen+25%+93%$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
DeepSeek V4.1 Flash 1017maxOpen+29%-75%$0.26Pass back reasoning_content · Chat Completions+4DeepSeek V4 Pro 0813maxOpen+3%-35%$0.67No image input+5DeepSeek V3.2 SpecialethinkingOpen-59%——Context: 1M → 128K+1DeepSeek V3.1 Terminusnon-thinkingOpen-60%—$0.27 / $0.95Context: 1M → 128K+1DeepSeek V3.1non-thinkingOpen-61%—$0.25 / $0.95Context: 1M → 128K+1R1 0528thinkingOpen-62%—$0.39 / $1.63Context: 1M → 128K+1DeepSeek V3 0324non-thinkingOpen-72%-98%$0.021Context: 1M → 128K+1DeepSeek V3non-thinkingOpen-76%-98%$0.02Context: 1M → 128K+1All DeepSeek models →Benchmarks
all categoriesChat & Knowledge
AA Omniscience Index-17.6
CritPt (physics)10.9
GPQA Diamond91.3
Coding
SciCode49.7
Agents & Tool Use
AA-Briefcase 1.1 · Elo1,424.6
Vision & Documents
FAQ
How much does DeepSeek V4 Flash Vision cost?›
There is no per-unit API price: API price not public.
Is DeepSeek V4 Flash Vision free to use?›
There is no free API.
What is the context window of DeepSeek V4 Flash Vision?›
1M tokens.
When was DeepSeek V4 Flash Vision released? Is there a newer version?›
Released 2026-08-21. It is retired.
Is DeepSeek V4 Flash Vision open source?›
No, DeepSeek V4 Flash Vision is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can DeepSeek V4 Flash Vision read images?›
It accepts text and images as input.
What is DeepSeek V4 Flash Vision?›
DeepSeek V4 Flash Vision is a closed language model from DeepSeek, released Aug 2026.
What are the best alternatives to DeepSeek V4 Flash Vision?›
GPT-6.1 Sol (cheaper), MiMo v2.6 Flash (better), MiMo v2.6 Pro (open weights).