modelbenchmark.io

DeepSeek V4 Flash

DeepSeek · deepseek-v4-flash

Compare

DeepSeek V4.1 Flash model for reasoning and agentic coding

Specification

deepseek listing

Context
1M
Max output
384K
Released
2026-09-10
Knowledge cutoff
2025-05
Retires
2028-02-20
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · deepseek list price

Input
$0.15
Output
$0.60
Cache read
$0.003
Cache write
free

Batch and priority prices

US dollars per million tokens · per listing

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

Available from 113 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepseekvendor
$0.15
$0.30
$0.60
$1.20
$0.003
$0.006
free1M
384K
393K
alibaba-token-planfreefreefreefree1M384K
alibaba-token-plan-cnfreefreefreefree1M384K
inferxfreefree1M100K
kenarifreefree1M384K
kenari · freefreefree1M384K
nanfreefree1M384K
nvidia · deepseek-ai
free
$0.14
free
$0.28
$0.0028
1M
1M
384K
393K
pendrafreefree1M384K
scnet-token-planfreefreefree1M384K
sensenovafreefreefree1M66K
unorouter · freefreefree1M384K
volcengine-coding-planfreefreefree1M384K
kilo
$0.04
$0.44
$0.14
$0.10
$1.32
$0.28
$0.01
$0.028
1M
1M
393K
944K
384K
openrouter
$0.04
$0.06
$0.0886
$0.065
$0.0854
$0.10
$0.12
$0.1772
$0.18
$0.1708
$0.01
$0.012
$0.0177
$0.016
$0.0171
1.3M
1M
393K
944K
384K
llmgateway$0.05$0.10$0.011.1M384K
llmgateway-providers · consensusprotocol$0.05$0.10$0.011.1M393K
nano-gpt
$0.05
$0.14
$0.16
$0.28
$0.013
$0.0028
1M
1M
131K
384K
nano-gpt · thinking
$0.05
$0.14
$0.16
$0.28
$0.013
$0.0028
1M
1M
131K
384K
llmgateway-providers · gonka24$0.051$0.104$0.0097390K16K
unorouter$0.0625$0.1251M384K
edenai · flexai$0.065$0.18786K384K
llmgateway-providers · runware$0.076$0.153$0.0141M384K
vercel
$0.076
$0.13
$0.153
$0.26
$0.014
$0.028
1M384K
ambient
$0.08
$0.14
$0.18
$0.28
$0.016
$0.028
free1M1M
crof
$0.08
$0.12
$0.10
$0.21
$0.0031M131K
deepinfra
$0.08
$0.09
$0.18
$0.016
$0.018
1M
digitalocean$0.08$0.252$0.02521M1M
cortecs$0.09$0.17$0.0141M1M
deepinfra · deepseek-ai
$0.09
$0.06
$0.18
$0.018
$0.015
1M
16K
384K
tokengo$0.098$0.196$0.0281M384K
modelis$0.0983$0.19661M384K
bothub$0.10$0.281M384K
pinstripes · pinstripes$0.10$0.20164K164K
pioneer · deepseek-ai$0.10$0.20$0.0197$0.101M131K
gmicloud · deepseek-ai$0.112$0.224$0.0221M384K
routing-run$0.112$0.2241M64K
melious$0.1159$0.2898$0.02321M384K
baseten · deepseek-ai$0.13$0.26$0.0281M384K
inceptron · deepseek-ai$0.13$0.28$0.03free1M1M
perplexity$0.13$0.26$0.028
perplexity-agent$0.13$0.26$0.0281M384K
runinfra · deepseek-ai$0.13$0.27$0.011M33K
openreason · deepseek-ai$0.1371$0.27431M384K
merge-gateway
$0.139
$0.035
$0.278
$0.07
$0.007
131K
1M
33K
384K
abacus · deepseek-ai$0.14$0.28$0.031M33K
alibaba-cn$0.14$0.28$0.00281M384K
amd$0.14$0.28$0.00281M384K
arcee$0.14$0.28$0.0281M384K
auriko$0.14$0.28$0.00281M384K
cline-pass · cline-pass$0.14$0.28$0.00281M384K
databricks$0.14$0.28$0.028$0.141M393K
fireworks_ai
$0.14
$0.22
$0.28
$0.66
$0.028
$0.007
1M
384K
131K
hpc-ai$0.14$0.28$0.0281M128K
huggingface · deepseek-ai$0.14$0.281M384K
jalapeno$0.14$0.281M384K
llmgateway-providers · canopywave$0.14$0.28$0.031M393K
llmgateway-providers · ranoai$0.14$0.28$0.0281M393K
llmgateway-providers · tencent$0.14$0.28$0.00281M393K
nebius$0.14$0.28
1M
1M
1M
1M
nebius · deepseek-ai$0.14$0.28$0.141M1M
neuralwatt$0.14$0.28$0.0281M66K
novita-ai$0.14$0.28$0.0281M393K
opencode$0.14$0.28$0.0281M384K
siliconflow · deepseek-ai$0.14$0.28$0.0281M384K
siliconflow-cn · deepseek-ai$0.14$0.28$0.0031M384K
tencent · tencent$0.14$0.28$0.0028free1M384K
tensormesh · tensormesh$0.14$0.28free33K33K
together_ai$0.14$0.28$0.031M
togetherai · deepseek-ai$0.14$0.28$0.031M384K
wandb · deepseek-ai
$0.14
$0.13
$0.28$0.07
1M
262K
1M
262K
wandb · wandb
$0.14
$0.13
$0.28$0.07
1M
262K
zenmux$0.14$0.28$0.00281M384K
aihubmix$0.142$0.284$0.02841M384K
ebcloud$0.143$0.28571M384K
orcarouter$0.147$0.295$0.021M384K
aiand · deepseek-ai$0.15$0.25$0.081M384K
opencode-go$0.15$0.60$0.0031M384K
vivgrid$0.15$0.30$0.031M384K
greenpt$0.1596$0.399$0.04561M384K
above$0.165$0.66$0.00331M384K
venice
$0.175
$0.138
$0.35
$0.275
$0.035
$0.028
1M33K
azure$0.19$0.511M384K
azure_ai
$0.19
$0.44
$0.51
$1.32
$0.028
$0.014
1M
384K
128K
2028-02-20
2026-12-03
impossibl$0.19$0.51$0.0281M384K
ofox
$0.19
$0.44
$0.51
$1.32
$0.028
$0.014
1M384K
alibaba$0.20$0.40$0.041M384K
dashscope · dashscope$0.20$0.40$0.041M393K
llmgateway-providers
$0.20
$0.14
$0.08
$0.22
$0.40
$0.28
$0.18
$0.66
$0.04
$0.03
$0.028
$0.016
$0.007
1M
164K
1.1M
1M
393K
164K
nano-gpt · tee$0.20$0.40$0.041M393K
qwen_ai_platform · qwen-ai-platform$0.20$0.40$0.041M393K
qwencloud · qwencloud$0.20$0.40$0.041M393K
edenai
$0.22
$0.14
$0.44
$0.06
$0.66
$0.28
$1.32
$0.18
$0.022
$0.14
$0.014
$0.028
$0.015
$0.007
$0.03
$0.14
1M
1M
1.3M
1M
384K
fireworks-ai · accounts$0.22$0.66$0.0071M384K
ollama-cloud$0.22$0.66$0.0071M1M
edenai · tensorx$0.25$0.30$0.06251M384K
libertai · libertai$0.25$1.75200K200K
tensorx
$0.25
$0.15
$0.30
$0.06
$0.0375
$0.18751M384K
crossmodel$0.27$1.08$0.0054$0.271M384K
requesty$0.28$0.56$0.071M131K
tinfoil$0.30$0.70$0.061M384K
vultr · deepseek-ai$0.30$1.001M384K
scaleway · scaleway$0.40$0.80$0.08256K33K
empiriolabs
$0.424
$0.14
$1.272
$0.28
$0.424
$0.14
1M393K
cloudflare-workers-ai · cf$0.44$1.32$0.0141.3M1M
hyper
$0.44
$0.20
$1.32
$0.40
$0.044
$0.04
1M384K
llmgateway-providers · baidu$0.44$1.32$0.0441M131K
llmgateway-providers · bytedance$0.44$1.32$0.0141M393K
novita
$0.44
$0.14
$1.32
$0.28
$0.0281M393K
edenai · scaleway$0.462$0.9241256K384K
scaleway$0.468$0.936$0.0936256K16K
agentrouter1M384K
anyapi1M384K

Price history

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

DateHostField$/M
2026-09-02aboveCache read$0.0077
2026-09-12aboveCache read$0.0033
2026-09-02ambientCache read$0.028
2026-09-04ambientCache read$0.016
2026-09-02azure_aiCache read$0.028
2026-09-04azure_aiCache read$0.028
2026-09-02cortecsCache read$0.03
2026-09-12cortecsCache read$0.014
2026-09-02crossmodelCache read$0.0135
2026-09-11crossmodelCache read$0.0054
2026-09-02deepinfra · deepseek-aiCache read$0.016
2026-09-04deepinfra · deepseek-aiCache read$0.018
2026-09-07deepinfra · deepseek-aiCache read$0.018
2026-09-02deepseekCache read$0.0028
2026-09-11deepseekCache read$0.003
2026-09-13deepseekCache read$0.003
2026-09-02edenaiCache read$0.014
2026-09-04edenaiCache read$0.14
2026-09-07edenaiCache read$0.14
2026-09-15edenaiCache read$0.022
2026-09-02empiriolabsCache read$0.14
2026-09-04empiriolabsCache read$0.424
2026-09-02hyperCache read$0.04
2026-09-04hyperCache read$0.044
2026-09-02kiloCache read$0.028
2026-09-04kiloCache read$0.013
2026-09-05kiloCache read$0.01
2026-09-07kiloCache read$0.009
2026-09-08kiloCache read$0.013
2026-09-13kiloCache read$0.005
2026-09-14kiloCache read$0.0011
2026-09-15kiloCache read$0.01
2026-09-02llmgatewayCache read$0.0097
2026-09-06llmgatewayCache read$0.01
2026-09-02llmgateway-providersCache read$0.007
2026-09-04llmgateway-providersCache read$0.04
2026-09-11llmgateway-providersCache read$0.04
2026-09-02llmgateway-providers · consensusprotocolCache read$0.02
2026-09-06llmgateway-providers · consensusprotocolCache read$0.01
2026-09-02nano-gptCache read$0.0028
2026-09-04nano-gptCache read$0.014
2026-09-11nano-gptCache read$0.013
2026-09-02nano-gpt · thinkingCache read$0.0028
2026-09-04nano-gpt · thinkingCache read$0.014
2026-09-11nano-gpt · thinkingCache read$0.013
2026-09-02ofoxCache read$0.014
2026-09-12ofoxCache read$0.028
2026-09-02opencode-goCache read$0.007
2026-09-11opencode-goCache read$0.003
2026-09-02openrouterCache read$0.014
2026-09-02openrouterCache read$0.0177
2026-09-02openrouterCache read$0.0171
2026-09-03openrouterCache read$0.0177
2026-09-04openrouterCache read$0.013
2026-09-05openrouterCache read$0.01
2026-09-06openrouterCache read$0.01
2026-09-07openrouterCache read$0.009
2026-09-08openrouterCache read$0.013
2026-09-09openrouterCache read$0.013
2026-09-12openrouterCache read$0.013
2026-09-13openrouterCache read$0.005
2026-09-14openrouterCache read$0.0011
2026-09-15openrouterCache read$0.01
2026-09-02requestyCache read$0.014
2026-09-03requestyCache read$0.07
2026-09-02tensorxCache read$0.0375
2026-09-04tensorxCache read$0.06
2026-09-02tinfoilCache read$0.06
2026-09-12tinfoilCache read$0.13
2026-09-13tinfoilCache read$0.06
2026-09-02veniceCache read$0.028
2026-09-04veniceCache read$0.035
2026-09-02vercelCache read$0.028
2026-09-04vercelCache read$0.014
2026-09-02crossmodelCache write$0.405
2026-09-11crossmodelCache write$0.27
2026-09-02aboveInput$0.242
2026-09-12aboveInput$0.165
2026-09-02ambientInput$0.14
2026-09-04ambientInput$0.08
2026-09-02azure_aiInput$0.19
2026-09-04azure_aiInput$0.19
2026-09-02cortecsInput$0.13
2026-09-12cortecsInput$0.09
2026-09-02crofInput$0.12
2026-09-04crofInput$0.08
2026-09-02crossmodelInput$0.405
2026-09-11crossmodelInput$0.27
2026-09-02deepinfra · deepseek-aiInput$0.08
2026-09-04deepinfra · deepseek-aiInput$0.09
2026-09-07deepinfra · deepseek-aiInput$0.09
2026-09-02deepseekInput$0.14
2026-09-11deepseekInput$0.15
2026-09-13deepseekInput$0.15
2026-09-02edenaiInput$0.44
2026-09-04edenaiInput$0.176
2026-09-07edenaiInput$0.176
2026-09-15edenaiInput$0.22
2026-09-02edenai · flexaiInput$0.03
2026-09-09edenai · flexaiInput$0.065
2026-09-02edenai · scalewayInput$0.4636
2026-09-02edenai · scalewayInput$0.4631
2026-09-04edenai · scalewayInput$0.4646
2026-09-05edenai · scalewayInput$0.4649
2026-09-09edenai · scalewayInput$0.4646
2026-09-10edenai · scalewayInput$0.4661
2026-09-11edenai · scalewayInput$0.4646
2026-09-12edenai · scalewayInput$0.4637
2026-09-15edenai · scalewayInput$0.462
2026-09-02empiriolabsInput$0.14
2026-09-04empiriolabsInput$0.424
2026-09-02hyperInput$0.20
2026-09-04hyperInput$0.44
2026-09-02kiloInput$0.14
2026-09-04kiloInput$0.05
2026-09-07kiloInput$0.045
2026-09-08kiloInput$0.05
2026-09-13kiloInput$0.03
2026-09-14kiloInput$0.0352
2026-09-15kiloInput$0.04
2026-09-02llmgatewayInput$0.051
2026-09-06llmgatewayInput$0.05
2026-09-02llmgateway-providersInput$0.22
2026-09-04llmgateway-providersInput$0.20
2026-09-02llmgateway-providers · consensusprotocolInput$0.13
2026-09-05llmgateway-providers · consensusprotocolInput$0.08
2026-09-06llmgateway-providers · consensusprotocolInput$0.05
2026-09-02merge-gatewayInput$0.22
2026-09-11merge-gatewayInput$0.139
2026-09-12merge-gatewayInput$0.139
2026-09-02nano-gptInput$0.14
2026-09-11nano-gptInput$0.05
2026-09-02nano-gpt · thinkingInput$0.14
2026-09-11nano-gpt · thinkingInput$0.05
2026-09-02nvidia · deepseek-aiInput$0.14
2026-09-04nvidia · deepseek-aiInputfree
2026-09-02ofoxInput$0.44
2026-09-12ofoxInput$0.19
2026-09-02opencode-goInput$0.22
2026-09-11opencode-goInput$0.15
2026-09-02openrouterInput$0.0701
2026-09-02openrouterInput$0.0886
2026-09-02openrouterInput$0.0855
2026-09-03openrouterInput$0.0886
2026-09-04openrouterInput$0.05
2026-09-05openrouterInput$0.05
2026-09-06openrouterInput$0.05
2026-09-07openrouterInput$0.045
2026-09-08openrouterInput$0.05
2026-09-09openrouterInput$0.05
2026-09-12openrouterInput$0.05
2026-09-13openrouterInput$0.03
2026-09-14openrouterInput$0.0352
2026-09-15openrouterInput$0.04
2026-09-02requestyInput$0.44
2026-09-03requestyInput$0.14
2026-09-09requestyInput$0.28
2026-09-02tensorxInput$0.15
2026-09-04tensorxInput$0.25
2026-09-02tinfoilInput$0.30
2026-09-12tinfoilInput$0.65
2026-09-13tinfoilInput$0.30
2026-09-02veniceInput$0.138
2026-09-04veniceInput$0.175
2026-09-02vercelInput$0.13
2026-09-04vercelInput$0.076
2026-09-02wandb · deepseek-aiInput$0.13
2026-09-04wandb · deepseek-aiInput$0.14
2026-09-02aboveOutput$0.726
2026-09-12aboveOutput$0.66
2026-09-02ambientOutput$0.28
2026-09-04ambientOutput$0.18
2026-09-02azure_aiOutput$0.51
2026-09-04azure_aiOutput$0.51
2026-09-02cortecsOutput$0.28
2026-09-12cortecsOutput$0.17
2026-09-02crofOutput$0.21
2026-09-04crofOutput$0.10
2026-09-02crossmodelOutput$1.215
2026-09-11crossmodelOutput$1.08
2026-09-02deepseekOutput$0.28
2026-09-11deepseekOutput$0.60
2026-09-13deepseekOutput$0.60
2026-09-02edenaiOutput$1.32
2026-09-04edenaiOutput$0.528
2026-09-15edenaiOutput$0.66
2026-09-02edenai · flexaiOutput$0.10
2026-09-09edenai · flexaiOutput$0.18
2026-09-02edenai · scalewayOutput$0.9272
2026-09-02edenai · scalewayOutput$0.9262
2026-09-04edenai · scalewayOutput$0.9292
2026-09-05edenai · scalewayOutput$0.9298
2026-09-09edenai · scalewayOutput$0.9291
2026-09-10edenai · scalewayOutput$0.9322
2026-09-11edenai · scalewayOutput$0.9293
2026-09-12edenai · scalewayOutput$0.9274
2026-09-15edenai · scalewayOutput$0.9241
2026-09-02empiriolabsOutput$0.28
2026-09-04empiriolabsOutput$1.272
2026-09-02hyperOutput$0.40
2026-09-04hyperOutput$1.32
2026-09-02kiloOutput$0.28
2026-09-04kiloOutput$0.16
2026-09-05kiloOutput$0.10
2026-09-07kiloOutput$0.09
2026-09-08kiloOutput$0.16
2026-09-13kiloOutput$0.07
2026-09-14kiloOutput$0.1056
2026-09-15kiloOutput$0.10
2026-09-02llmgatewayOutput$0.104
2026-09-06llmgatewayOutput$0.10
2026-09-02llmgateway-providersOutput$0.66
2026-09-04llmgateway-providersOutput$0.40
2026-09-02llmgateway-providers · consensusprotocolOutput$0.27
2026-09-05llmgateway-providers · consensusprotocolOutput$0.16
2026-09-06llmgateway-providers · consensusprotocolOutput$0.10
2026-09-02merge-gatewayOutput$0.66
2026-09-11merge-gatewayOutput$0.278
2026-09-12merge-gatewayOutput$0.278
2026-09-02nano-gptOutput$0.28
2026-09-11nano-gptOutput$0.16
2026-09-02nano-gpt · thinkingOutput$0.28
2026-09-11nano-gpt · thinkingOutput$0.16
2026-09-02nvidia · deepseek-aiOutput$0.28
2026-09-04nvidia · deepseek-aiOutputfree
2026-09-02ofoxOutput$1.32
2026-09-12ofoxOutput$0.51
2026-09-02opencode-goOutput$0.66
2026-09-11opencode-goOutput$0.60
2026-09-02openrouterOutput$0.1403
2026-09-02openrouterOutput$0.1772
2026-09-02openrouterOutput$0.1711
2026-09-03openrouterOutput$0.1772
2026-09-04openrouterOutput$0.16
2026-09-05openrouterOutput$0.10
2026-09-06openrouterOutput$0.10
2026-09-07openrouterOutput$0.09
2026-09-08openrouterOutput$0.16
2026-09-09openrouterOutput$0.16
2026-09-12openrouterOutput$0.16
2026-09-13openrouterOutput$0.07
2026-09-14openrouterOutput$0.1056
2026-09-15openrouterOutput$0.10
2026-09-02requestyOutput$1.32
2026-09-03requestyOutput$0.28
2026-09-09requestyOutput$0.56
2026-09-02tinfoilOutput$0.70
2026-09-12tinfoilOutput$1.45
2026-09-13tinfoilOutput$0.70
2026-09-02veniceOutput$0.275
2026-09-04veniceOutput$0.35
2026-09-02vercelOutput$0.26
2026-09-04vercelOutput$0.153

Other listings of this model

same model, different key

More from DeepSeek

most-hosted first