modelbenchmark.io

DeepSeek V4.1 Flash

DeepSeek · deepseek-v4-1-flash

Compare

DeepSeek V4.1 Flash model for reasoning and agentic coding

Specification

most-agreed values

Context
1M
Max output
384K
Released
2026-09-10
Knowledge cutoff
2025-05
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.2556
Output
$1.2778
Cache read
$0.0128
Cache write
$0.27

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Priority inputfireworks_ai$0.275
Priority outputfireworks_ai$0.825

Quality

1 benchmark · 1 source

Composite
94th
percentile of 334 scored models
Rank
21 / 334
±0.53 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
one configuration only
general91st1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
LiveBench81.4max · 23 runsLiveBench2026-06-25

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 36 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
alibaba-token-plan-cnfreefreefreefree1M384K
nano-gpt$0.10$0.40$0.0061M384K
nano-gpt · thinking$0.10$0.40$0.0061M384K
amd$0.14$0.28$0.00281M384K
cline-pass · cline-pass$0.15$0.60$0.0031M384K
edenai
$0.15
$0.20
$0.30
$0.60
$1.20
$0.015
$0.006
1M
1M
384K
llmgateway$0.15$0.60$0.0031.1M384K
merge-gateway$0.15$0.60$0.0031M384K
ollama-cloud$0.15$0.60$0.0031M384K
opencode-go$0.15$0.60$0.0031M384K
vercel$0.15$0.60$0.0151M384K
aihubmix$0.155$0.62$0.00311M384K
deepinfra · deepseek-ai$0.20$0.60$0.0061M384K
llmgateway-providers · consensusprotocol$0.20$0.60$0.0051M384K
fireworks_ai$0.22$0.66$0.0071M393K
fireworks-ai · accounts$0.22$0.66$0.0071M384K
melious$0.2318$1.1592$0.01161M384K
greenpt$0.2556$1.2778$0.01281M384K
crossmodel$0.27$1.08$0.0054$0.271M384K
baseten · deepseek-ai$0.30$1.20$0.031M33K
digitalocean$0.30$1.20$0.0061M1M
empiriolabs$0.30$1.20$0.301M393K
huggingface · deepseek-ai$0.30$1.201M384K
kilo$0.30$1.20$0.0061M384K
llmgateway-providers
$0.30
$0.20
$0.15
$0.22
$1.20
$0.60
$0.66
$0.03
$0.006
$0.003
$0.007
1M
1M
1.1M
393K
ofox$0.30$1.20$0.0061M384K
openrouter
$0.30
$0.15
$1.20
$0.60
$0.006
$0.003
1M384K
together_ai$0.30$1.20$0.006
togetherai · deepseek-ai$0.30$1.20$0.0061M384K
hyper$0.3266$1.3066$0.03271M13K
venice$0.375$1.50$0.00751M131K
cortecs$0.50$1.499$0.131M64K
edenai · tensorx$0.50$1.50$0.1251M384K
requesty$0.50$1.50$0.051M393K
nano-gpt · tee$0.65$1.45$0.131M384K
tinfoil$0.65$1.45$0.131M384K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-09nano-gptCache read$0.0312
2026-09-11nano-gptCache read$0.006
2026-09-12nano-gptCache read$0.003
2026-09-15nano-gptCache read$0.006
2026-09-09vercelCache read$0.007
2026-09-11vercelCache read$0.006
2026-09-15vercelCache read$0.015
2026-09-09nano-gptInput$0.1562
2026-09-11nano-gptInput$0.30
2026-09-12nano-gptInput$0.15
2026-09-15nano-gptInput$0.10
2026-09-09vercelInput$0.22
2026-09-11vercelInput$0.30
2026-09-15vercelInput$0.15
2026-09-09nano-gptOutput$0.3124
2026-09-11nano-gptOutput$1.20
2026-09-12nano-gptOutput$0.60
2026-09-15nano-gptOutput$0.40
2026-09-09vercelOutput$0.66
2026-09-11vercelOutput$1.20
2026-09-15vercelOutput$0.60
2026-09-10nano-gpt · thinkingCache read$0.0312
2026-09-11nano-gpt · thinkingCache read$0.006
2026-09-12nano-gpt · thinkingCache read$0.003
2026-09-15nano-gpt · thinkingCache read$0.006
2026-09-10nano-gpt · thinkingInput$0.1562
2026-09-11nano-gpt · thinkingInput$0.30
2026-09-12nano-gpt · thinkingInput$0.15
2026-09-15nano-gpt · thinkingInput$0.10
2026-09-10nano-gpt · thinkingOutput$0.3124
2026-09-11nano-gpt · thinkingOutput$1.20
2026-09-12nano-gpt · thinkingOutput$0.60
2026-09-15nano-gpt · thinkingOutput$0.40
2026-09-11edenaiCache read$0.006
2026-09-15edenaiCache read$0.015
2026-09-11hyperCache read$0.03
2026-09-15hyperCache read$0.0327
2026-09-11llmgateway-providersCache read$0.003
2026-09-14llmgateway-providersCache read$0.006
2026-09-15llmgateway-providersCache read$0.03
2026-09-11openrouterCache read$0.006
2026-09-12openrouterCache read$0.003
2026-09-13openrouterCache read$0.003
2026-09-14openrouterCache read$0.006
2026-09-11requestyCache read$0.006
2026-09-12requestyCache read$0.007
2026-09-14requestyCache read$0.05
2026-09-11edenaiInput$0.30
2026-09-12edenaiInput$0.20
2026-09-14edenaiInput$0.20
2026-09-15edenaiInput$0.15
2026-09-11hyperInput$0.30
2026-09-15hyperInput$0.3266
2026-09-11llmgateway-providersInput$0.15
2026-09-14llmgateway-providersInput$0.30
2026-09-11openrouterInput$0.30
2026-09-12openrouterInput$0.15
2026-09-13openrouterInput$0.15
2026-09-14openrouterInput$0.30
2026-09-11requestyInput$0.30
2026-09-12requestyInput$0.22
2026-09-14requestyInput$0.50
2026-09-11edenaiOutput$1.20
2026-09-12edenaiOutput$0.60
2026-09-14edenaiOutput$0.60
2026-09-11hyperOutput$1.20
2026-09-15hyperOutput$1.3066
2026-09-11llmgateway-providersOutput$0.60
2026-09-14llmgateway-providersOutput$1.20
2026-09-11openrouterOutput$1.20
2026-09-12openrouterOutput$0.60
2026-09-13openrouterOutput$0.60
2026-09-14openrouterOutput$1.20
2026-09-11requestyOutput$1.20
2026-09-12requestyOutput$0.66
2026-09-14requestyOutput$1.50
2026-09-14llmgateway-providers · consensusprotocolOutput$1.00
2026-09-15llmgateway-providers · consensusprotocolOutput$0.60

More from DeepSeek

most-hosted first