DeepSeek V4 Pro pricing.
Prices checked
DeepSeek V4 Pro costs $0.66 in and $1.98 out per million tokens from DeepSeek; the cheapest price is $0.28 at TrustedRouter, checked .
DeepSeek's own price
DeepSeek
$0.66 in · $1.98 out
12% above the typical price of the 392 text models we track.
Cheapest price
TrustedRouter
$0.16 in · $0.63 out
72% less than DeepSeek, and the provider says why.
Every provider selling DeepSeek V4 Pro
- 1
$0.16 in · $0.63 out
$0.28/M tokens - 2
routing.run
Runs it themselves$0.35 in · $0.70 out
$0.43/M tokens - 3

EBCloud
Runs it themselves$0.43 in · $0.86 out
$0.54/M tokens - 4

Sail Research
Lower precision (fp4)$0.45 in · $0.80 out
price from , a change is being checked$0.54/M tokens - 5

TokenGo
Runs it themselves$0.43 in · $0.87 out
$0.54/M tokens - 6

Modelis
Runs it themselves$0.43 in · $0.87 out
$0.54/M tokens - 7

RunInfra
Resells$0.60 in · $1.90 out
$0.92/M tokens - 8

StreamLake
Costs more$0.79 in · $1.58 out
$0.99/M tokens - 9
$0.66 in · $1.98 out
$0.99/M tokens - 10
$0.66 in · $1.98 out · 1.1M context here
$0.99/M tokens - 11Same as maker
$0.66 in · $1.98 out
$0.99/M tokens - 12
$0.66 in · $1.98 out
$0.99/M tokens - 13
$0.66 in · $1.98 out
$0.99/M tokens - 14

OpenCode Go
Same as maker$0.66 in · $1.98 out
$0.99/M tokens - 15

ClinePass
Same as maker$0.66 in · $1.98 out
$0.99/M tokens - 16
Ollama Cloud
Same as maker$0.66 in · $1.98 out
$0.99/M tokens - 17
Ollama Cloud
Same as maker$0.66 in · $1.98 out
$0.99/M tokens - 18Same as maker
$0.66 in · $1.98 out
$0.99/M tokens - 19
$0.66 in · $1.98 out
$0.99/M tokens - 20
$0.66 in · $1.98 out
$0.99/M tokens - 21

StreamLake
Same as maker$0.66 in · $1.98 out
$0.99/M tokens - 22
$0.66 in · $1.98 out
$0.99/M tokens - 23
$0.67 in · $2 out
$1.00/M tokens - 24$1.00/M tokens
- 25$1.00/M tokens
- 26

Ionstream
Runs it themselves$0.37 in · $2.93 out
$1.01/M tokens - 27
$0.69 in · $2.08 out
$1.04/M tokens - 28
above.dev
Costs more$0.73 in · $2.18 out
$1.09/M tokens - 29

UnoRouter
Costs more$0.90 in · $1.80 out
$1.12/M tokens - 30

IteraCompute
Costs more$0.79 in · $2.38 out
$1.19/M tokens - 31

Wafer
Lower precision (mxfp4)$0.28 in · $4.30 out
price from , a change is being checked$1.29/M tokens - 32
Boundless
Costs more$1.04 in · $2.08 out
$1.30/M tokens - 33
$0.99 in · $2.97 out
$1.48/M tokens - 34
$1.06 in · $3.17 out
$1.58/M tokens - 35

DekaLLM
Costs more$0.88 in · $3.80 out
$1.61/M tokens - 36
$1.30 in · $2.60 out
$1.63/M tokens - 37
$1.30 in · $2.60 out
$1.63/M tokens - 38
$1.30 in · $2.60 out
$1.63/M tokens - 39
$1.30 in · $2.60 out
$1.63/M tokens - 40
$1.31 in · $2.61 out
$1.63/M tokens - 41
Standard Compute
Costs more$1.12 in · $3.37 out
price from , a change is being checked$1.68/M tokens - 42
$1.39 in · $2.78 out
$1.74/M tokens - 43
$1.42 in · $2.83 out
$1.77/M tokens - 44

CoreWeave
Costs more$1.31 in · $3.96 out
$1.97/M tokens - 45

CoreWeave
Costs more$1.31 in · $3.96 out
$1.97/M tokens - 46
$1.32 in · $3.96 out · 979k context here
$1.98/M tokens - 47
$1.32 in · $3.96 out
$1.98/M tokens - 48
$1.32 in · $3.96 out
$1.98/M tokens - 49

FrogBot
Costs more$1.32 in · $3.96 out · 128k context here
$1.98/M tokens - 50
$1.32 in · $3.96 out
$1.98/M tokens - 51
$1.32 in · $3.96 out
$1.98/M tokens - 52
$1.32 in · $3.96 out
$1.98/M tokens - 53
$1.32 in · $3.96 out
$1.98/M tokens - 54
$1.32 in · $3.96 out
$1.98/M tokens - 55

Auriko
Costs more$1.32 in · $3.96 out
$1.98/M tokens - 56
$1.32 in · $3.96 out
$1.98/M tokens - 57
Arcee AI
Costs more$1.32 in · $3.96 out · 512k context here
price from , a change is being checked$1.98/M tokens - 58
$1.32 in · $3.96 out
$1.98/M tokens - 59
$1.32 in · $3.96 out
$1.98/M tokens - 60$1.98/M tokens
- 61
$1.32 in · $3.96 out
$1.98/M tokens - 62

Baidu
Costs more$1.32 in · $3.96 out
price from , a change is being checked$1.98/M tokens - 63
$1.32 in · $3.96 out
$1.98/M tokens - 64
$1.32 in · $3.96 out
$1.98/M tokens - 65
$1.32 in · $3.96 out
$1.98/M tokens - 66
$1.32 in · $3.96 out
$1.98/M tokens - 67
$1.32 in · $3.96 out
$1.98/M tokens - 68
$1.32 in · $3.96 out
$1.98/M tokens - 69
$1.35 in · $4.05 out
$2.03/M tokens - 70

Jalapeno Cloud
Costs more$1.60 in · $3.38 out
$2.05/M tokens - 71
$1.65 in · $3.30 out
$2.06/M tokens - 72
$1.65 in · $3.30 out
$2.06/M tokens - 73
$1.65 in · $3.30 out
$2.06/M tokens - 74

Relace
Lower precision (fp4)$0.12 in · $8 out
price from , a change is being checked$2.09/M tokens - 75$2.09/M tokens
- 76
$1.68 in · $3.38 out
$2.11/M tokens - 77
$1.68 in · $3.38 out
$2.11/M tokens - 78
$1.70 in · $3.40 out
$2.13/M tokens - 79

Charm Hyper
Costs more$1.44 in · $4.31 out
$2.16/M tokens - 80

Vivgrid
Costs more$1.74 in · $3.48 out
$2.18/M tokens - 81
$1.74 in · $3.48 out
$2.18/M tokens - 82
$1.74 in · $3.48 out
$2.18/M tokens - 83
$1.74 in · $3.48 out
$2.18/M tokens - 84
$1.74 in · $3.48 out
$2.18/M tokens - 85
$1.74 in · $3.48 out
$2.18/M tokens - 86
$1.74 in · $3.48 out
$2.18/M tokens - 87
$1.74 in · $3.48 out
$2.18/M tokens - 88

HPC-AI
Costs more$1.74 in · $3.48 out
$2.18/M tokens - 89
$1.74 in · $3.48 out · 131k context here
$2.18/M tokens - 90
$1.74 in · $3.48 out
$2.18/M tokens - 91
$1.45 in · $4.36 out
$2.18/M tokens - 92$2.19/M tokens
- 93
TensorX
Costs more$1.75 in · $3.50 out
$2.19/M tokens - 94
$1.79 in · $3.58 out
$2.24/M tokens - 95
$1.79 in · $3.59 out
$2.24/M tokens - 96

Moark
Costs more$1.80 in · $3.60 out
$2.25/M tokens - 97$2.30/M tokens
- 98
Wally
Costs more$1.91 in · $3.83 out
$2.39/M tokens - 99Costs more
$1.91 in · $3.83 out
$2.39/M tokens - 100
$2.01 in · $4.01 out
$2.51/M tokens - 101
$2.10 in · $4.20 out
$2.63/M tokens - 102

Bothub
Costs more$1.77 in · $5.30 out
$2.65/M tokens - 103
$2.40 in · $4.80 out
$3/M tokens - 104
$2.40 in · $4.80 out
$3/M tokens - 105
$2.40 in · $4.80 out
$3/M tokens - 106
$8.50 in · $17 out
$10.63/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
free
Volcengine Ark Coding Plan
Free tiergiven away with limits
freeSCNet Token Plan
Free tiergiven away with limits
free
Alibaba Token Plan (China)
Free tiergiven away with limits
free
SenseNova (China)
Free tiergiven away with limits
free$1 in · $2 out
$1.25/M tokens$1 in · $2.50 out
$1.38/M tokens$1.60 in · $3.20 out · 262k context here
$2/M tokens
What it costs for your work
A month at DeepSeek's own price
A month at TrustedRouter, 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.
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.
- Resells
- The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- 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.
- Costs more
- Sold by someone else for more than the maker charges.
- 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.
- Credits
- Priced in credits or points that convert to dollars, so the rate moves when the conversion does.
- 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 Pro does, cheapest first. Each percentage is against DeepSeek V4 Pro's cheapest price, $0.28 per M tokens.
Frequently asked
- Who sells DeepSeek V4 Pro cheapest?
- TrustedRouter, at $0.16 in and $0.63 out per million tokens, checked 31 Oct 2026. The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Is DeepSeek V4 Pro open weights?
- Yes. DeepSeek publishes the weights, so anyone may host DeepSeek V4 Pro, which is why 94 providers sell it and why their prices differ so much.
- How much context does DeepSeek V4 Pro hold?
- 1,048,576 tokens in one call, which is about 1M, and it can call your own functions.
- How does DeepSeek V4 Pro compare with the rest of the market?
- At $0.99 per million tokens, DeepSeek's own price is 12% above the typical $0.88 across the 392 text models we track.
More from DeepSeek