DeepSeek V4.1 Flash 1017 pricing.
Prices checked
DeepSeek V4.1 Flash 1017 costs $0.15 in and $0.60 out per million tokens from DeepSeek; the cheapest price is $0.05 at Engy, checked .
DeepSeek's own price
DeepSeek
$0.15 in · $0.60 out
70% below the typical price of the 392 text models we track.
Cheapest price
Engy
$0.03 in · $0.12 out
80% less than DeepSeek, and the provider says why.
Every provider selling DeepSeek V4.1 Flash 1017
- 1
Engy
Runs it themselves$0.03 in · $0.12 out
$0.05/M tokens - 2
Sail Research
Lower precision (fp4)$0.10 in · $0.15 out
$0.11/M tokens - 3$0.13/M tokens
- 4
$0.07 in · $0.30 out
$0.13/M tokens - 5
$0.10 in · $0.29 out
$0.15/M tokens - 6
$0.10 in · $0.29 out
$0.15/M tokens - 7
Relace
Lower precision (fp4)$0.04 in · $0.50 out
$0.15/M tokens - 8
Reka
Runs it themselves$0.04 in · $0.50 out
price from , a change is being checked$0.15/M tokens - 9
Wafer
Lower precision (mxfp4)$0.07 in · $0.50 out
price from , a change is being checked$0.18/M tokens - 10
$0.08 in · $0.55 out
$0.20/M tokens - 11
Morph
Lower precision (fp8)$0.05 in · $0.69 out
price from , a change is being checked$0.21/M tokens - 12
StreamLake
Lower precision (fp8)$0.12 in · $0.48 out
$0.21/M tokens - 13
Standard Compute
Resells$0.14 in · $0.42 out
$0.21/M tokens - 14
$0.12 in · $0.49 out
$0.22/M tokens - 15
$0.15 in · $0.44 out
$0.22/M tokens - 16
$0.13 in · $0.51 out
$0.22/M tokens - 17$0.23/M tokens
- 18$0.23/M tokens
- 19$0.24/M tokens
- 20
CoreWeave
Runs it themselves$0.13 in · $0.65 out
$0.26/M tokens - 21
CoreWeave
Lower precision (fp8)$0.13 in · $0.65 out
$0.26/M tokens - 22
$0.15 in · $0.60 out
$0.26/M tokens - 23Same as maker
$0.15 in · $0.60 out
$0.26/M tokens - 24
$0.15 in · $0.60 out
$0.26/M tokens - 25
OpenCode Go
Same as maker$0.15 in · $0.60 out
$0.26/M tokens
- 26
$0.15 in · $0.60 out
$0.26/M tokens - 27
ClinePass
Same as maker$0.15 in · $0.60 out
$0.26/M tokens - 28
Ollama Cloud
Same as maker$0.15 in · $0.60 out
$0.26/M tokens - 29
Ollama Cloud
Same as maker$0.15 in · $0.60 out
$0.26/M tokens - 30
$0.15 in · $0.60 out
$0.26/M tokens - 31
$0.15 in · $0.60 out
$0.26/M tokens - 32Costs more
$0.16 in · $0.58 out
$0.27/M tokens - 33
$0.15 in · $0.62 out
$0.27/M tokens - 34
Hopper
Runs it themselves$0.09 in · $0.85 out
$0.28/M tokens - 35
above.dev
Costs more$0.17 in · $0.66 out
$0.29/M tokens - 36
$0.20 in · $0.60 out
$0.30/M tokens - 37
$0.20 in · $0.60 out
$0.30/M tokens - 38
$0.20 in · $0.60 out
$0.30/M tokens - 39
$0.20 in · $0.60 out
$0.30/M tokens - 40
IteraCompute
Costs more$0.17 in · $0.70 out
$0.30/M tokens - 41
$0.20 in · $0.61 out
$0.31/M tokens - 42
$0.18 in · $0.72 out
$0.32/M tokens - 43
Ionstream
Costs more$0.22 in · $0.60 out
price from , a change is being checked$0.32/M tokens - 44
$0.20 in · $0.78 out
$0.34/M tokens - 45
$0.20 in · $0.78 out
$0.34/M tokens - 46
Boundless
Costs more$0.20 in · $1 out
$0.40/M tokens - 47
Makora
Same as maker$0.15 in · $1.20 out
$0.41/M tokens - 48
Vancine
Costs more$0.24 in · $0.96 out
$0.42/M tokens - 49
Modular
Costs more$0.17 in · $1.20 out
$0.43/M tokens - 50
Particle AI
Costs more$0.25 in · $1 out
price from , a change is being checked$0.44/M tokens - 51
Munito AI
Costs more$0.27 in · $1 out
$0.45/M tokens - 52$0.46/M tokens
- 53
$0.30 in · $1 out
$0.47/M tokens - 54
CoralBricks
Costs more$0.25 in · $1.20 out
$0.49/M tokens - 55
Baidu
Costs more$0.28 in · $1.13 out
price from , a change is being checked$0.49/M tokens - 56
GreenPT
Costs more$0.26 in · $1.28 out
$0.51/M tokens - 57
$0.29 in · $1.20 out
$0.52/M tokens - 58
$0.30 in · $1.19 out
$0.52/M tokens - 59
$0.30 in · $1.20 out
$0.52/M tokens - 60
$0.30 in · $1.20 out
$0.52/M tokens - 61
Wally
Costs more$0.30 in · $1.20 out
$0.52/M tokens - 62
$0.30 in · $1.20 out
$0.52/M tokens - 63Costs more
$0.30 in · $1.20 out
$0.52/M tokens - 64
$0.30 in · $1.20 out
$0.52/M tokens - 65
Modal
Costs more$0.30 in · $1.20 out
$0.52/M tokens - 66
$0.30 in · $1.20 out
$0.52/M tokens - 67
$0.30 in · $1.20 out
$0.52/M tokens - 68
$0.30 in · $1.20 out
$0.52/M tokens - 69Costs more
$0.30 in · $1.20 out
$0.52/M tokens - 70
$0.30 in · $1.20 out
$0.52/M tokens - 71
$0.30 in · $1.20 out
$0.52/M tokens - 72
$0.30 in · $1.20 out
$0.52/M tokens - 73
$0.30 in · $1.20 out
$0.52/M tokens - 74
$0.30 in · $1.20 out
$0.52/M tokens - 75
$0.30 in · $1.20 out
$0.52/M tokens - 76
$0.30 in · $1.20 out
$0.52/M tokens - 77
$0.30 in · $1.20 out
$0.52/M tokens - 78
Arcee AI
Costs more$0.30 in · $1.20 out
$0.52/M tokens - 79
$0.30 in · $1.20 out
$0.52/M tokens - 80
$0.30 in · $1.20 out
$0.52/M tokens - 81
$0.30 in · $1.20 out
$0.52/M tokens - 82
$0.30 in · $1.20 out
$0.52/M tokens - 83$0.52/M tokens
- 84
$0.30 in · $1.20 out
$0.52/M tokens - 85$0.52/M tokens
- 86
Near AI
Costs more$0.30 in · $1.20 out
$0.52/M tokens - 87
$0.30 in · $1.20 out
$0.52/M tokens - 88
$0.30 in · $1.20 out
$0.52/M tokens - 89
$0.30 in · $1.20 out
$0.52/M tokens - 90
$0.30 in · $1.20 out
$0.52/M tokens - 91
PrimeIntellect
Costs more$0.30 in · $1.20 out
$0.52/M tokens - 92
$0.30 in · $1.20 out
$0.52/M tokens - 93
$0.30 in · $1.20 out
$0.52/M tokens - 94
$0.30 in · $1.20 out
$0.52/M tokens - 95
$0.30 in · $1.20 out
$0.52/M tokens - 96
$0.30 in · $1.20 out
$0.52/M tokens - 97
$0.30 in · $1.21 out
$0.53/M tokens - 98
Vivgrid
Costs more$0.31 in · $1.23 out
$0.54/M tokens - 99
$0.36 in · $1.09 out
$0.54/M tokens - 100
Charm Hyper
Costs more$0.33 in · $1.31 out
$0.57/M tokens - 101
$0.33 in · $1.32 out
$0.58/M tokens - 102
Melious
Costs more$0.33 in · $1.34 out
$0.59/M tokens - 103
TensorX
Costs more$0.50 in · $1.50 out
$0.75/M tokens - 104
Synthetic
Costs more$0.60 in · $1.20 out · 524k context here
$0.75/M tokens - 105
$0.67 in · $2.02 out · 256k context here
$1.01/M tokens - 106
$0.60 in · $2.40 out
$1.05/M tokens - 107
Wally
Costs more$0.60 in · $2.40 out
$1.05/M tokens - 108
$0.60 in · $2.40 out
$1.05/M tokens - 109
Inco
Costs more$0.60 in · $2.40 out
$1.05/M tokens - 110
$0.63 in · $2.53 out
$1.11/M tokens
Not ranked
Below the maker's own price with nothing published to account for it, from a catalog we could not read reliably, or a free tier, which is a limit rather than a price. Why
Alibaba Token Plan
Free tiergiven away with limits
freeSCNet Token Plan
Free tiergiven away with limits
freegiven away with limits
free
AMD
Free tiergiven away with limits
free
Alibaba Token Plan (China)
Free tiergiven away with limits
free
SenseNova (China)
Free tiergiven away with limits
free$0.01 in · $0.13 out
$0.04/M tokens
Neuralwatt
Not ranked$0.15 in · $0.60 out
$0.26/M tokens
OpenInference
Not ranked$0.02 in · $1 out
price from , a change is being checked$0.27/M tokens$0.28 in · $0.55 out
$0.34/M tokens$0.30 in · $0.60 out
$0.38/M tokens$0.20 in · $1 out
$0.40/M tokens$0.30 in · $1.20 out · 262k context here
$0.52/M tokens$0.65 in · $1.45 out
$0.85/M tokens
What it costs for your work
A month at DeepSeek's own price
A month at Engy, the cheapest
What you save
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
Evidence
LiveBench · deepseek-v4.1-flash-max · max effort. Published 15 Oct 2026, read 31 Oct 2026.
How it is calculatedEach is a measurement of the stated version and configuration. Two benchmarks are not the same test, and a score is not the chance your own work succeeds.
How we count
Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below DeepSeek's own is listed as cheapest only when the provider says why.
- Runs it themselves
- The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Lower precision
- The open weights, served at a lower precision than the maker's, so not quite the same product.
- Resells
- The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Same as maker
- Sold by someone else at the price the maker charges.
- Maker's price
- What the lab that trained the model charges on its own API. Every other row is measured against it.
- Costs more
- Sold by someone else for more than the maker charges.
- Free tier
- Given away inside a quota. A limit is not a price, so it is never called cheapest.
- Not ranked
- Below the maker's price on a closed model with nothing to account for it, or from a catalog we could not read reliably. Listed, and never a pick.
Similar models
Models from other labs that do what DeepSeek V4.1 Flash 1017 does, cheapest first. Each percentage is against DeepSeek V4.1 Flash 1017's cheapest price, $0.05 per M tokens.
Frequently asked
- Who sells DeepSeek V4.1 Flash 1017 cheapest?
- Engy, at $0.03 in and $0.12 out per million tokens, checked 31 Oct 2026. The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Is DeepSeek V4.1 Flash 1017 open weights?
- Yes. DeepSeek publishes the weights, so anyone may host DeepSeek V4.1 Flash 1017, which is why 102 providers sell it and why their prices differ so much.
- How much context does DeepSeek V4.1 Flash 1017 hold?
- 1,048,576 tokens in one call, which is about 1M, and it can call your own functions.
- How does DeepSeek V4.1 Flash 1017 compare with the rest of the market?
- At $0.26 per million tokens, DeepSeek's own price is 70% below the typical $0.88 across the 392 text models we track.
More from DeepSeek
Ranked in