DeepInfra model pricing.
Prices checked
DeepInfra sells 198 prices on 126 models, from $0.02 per million tokens, checked .
Every model DeepInfra sells
- 1Runs it themselves
$0.02 in · $0.02 out
$0.02/M tokens - 2Runs it themselves
$0.02 in · $0.04 out
$0.03/M tokens - 3Lower precision (fp8)
$0.02 in · $0.04 out
$0.03/M tokens - 4Same as maker
$0.03 in · $0.03 out
$0.03/M tokens - 5Runs it themselves
$0.03 in · $0.05 out
$0.04/M tokens - 6Same as maker
$0.04 in · $0.05 out
$0.04/M tokens - 7Same as maker
$0.05 in · $0.05 out
$0.05/M tokens - 8Runs it themselves
$0.04 in · $0.10 out
$0.06/M tokens - 9Costs more
$0.03 in · $0.14 out
$0.06/M tokens - 10Costs more
$0.03 in · $0.14 out
$0.06/M tokens - 11Costs more
$0.03 in · $0.14 out
$0.06/M tokens - 12Same as maker
$0.05 in · $0.08 out
$0.06/M tokens - 13Same as maker
$0.05 in · $0.08 out
$0.06/M tokens - 14Runs it themselves
$0.04 in · $0.12 out
$0.06/M tokens - 15Same as maker
$0.05 in · $0.10 out
$0.06/M tokens - 16Same as maker
$0.05 in · $0.10 out
$0.06/M tokens - 17Same as maker
$0.05 in · $0.10 out
$0.06/M tokens - 18Runs it themselves
$0.04 in · $0.16 out
$0.07/M tokens - 19Runs it themselves
$0.06 in · $0.11 out
$0.07/M tokens - 20Runs it themselves
$0.04 in · $0.17 out
$0.07/M tokens - 21Runs it themselves
$0.04 in · $0.17 out
$0.07/M tokens - 22Runs it themselves
$0.04 in · $0.17 out
$0.07/M tokens - 23Same as maker
$0.05 in · $0.15 out
$0.08/M tokens - 24Same as maker
$0.05 in · $0.15 out
$0.08/M tokens - 25Runs it themselves
$0.06 in · $0.16 out
$0.08/M tokens
- 26Runs it themselves
$0.05 in · $0.20 out
$0.09/M tokens - 27Same as maker
$0.07 in · $0.14 out
$0.09/M tokens - 28Same as maker
$0.07 in · $0.14 out
$0.09/M tokens - 29Lower precision (fp8)
$0.06 in · $0.18 out
$0.09/M tokens - 30Costs more
$0.06 in · $0.18 out
$0.09/M tokens - 31Costs more
$0.06 in · $0.18 out
$0.09/M tokens - 32Same as maker
$0.06 in · $0.18 out
$0.09/M tokens - 33Same as maker
$0.06 in · $0.18 out
$0.09/M tokens - 34Same as maker
$0.08 in · $0.16 out
$0.10/M tokens - 35Same as maker
$0.08 in · $0.16 out
$0.10/M tokens - 36Runs it themselves
$0.07 in · $0.20 out
$0.11/M tokens - 37Lower precision (fp8)
$0.07 in · $0.20 out
$0.11/M tokens - 38Same as maker
$0.06 in · $0.25 out
$0.11/M tokens - 39Same as maker
$0.06 in · $0.25 out
$0.11/M tokens - 40Runs it themselves
$0.09 in · $0.18 out
$0.11/M tokens - 41Costs more
$0.10 in · $0.15 out
$0.11/M tokens - 42Costs more
$0.10 in · $0.15 out
$0.11/M tokens - 43Costs more
$0.10 in · $0.15 out
$0.11/M tokens - 44Runs it themselves
$0.08 in · $0.28 out
$0.13/M tokens - 45Lower precision (fp8)
$0.08 in · $0.28 out
$0.13/M tokens - 46Runs it themselves
$0.07 in · $0.34 out
$0.14/M tokens - 47Lower precision (fp8)
$0.07 in · $0.34 out
$0.14/M tokens - 48Runs it themselves
$0.14 in · $0.14 out
$0.14/M tokens - 49Same as maker
$0.06 in · $0.40 out
$0.15/M tokens - 50Runs it themselves
$0.12 in · $0.24 out
$0.15/M tokens - 51Lower precision (fp8)
$0.12 in · $0.24 out
$0.15/M tokens - 52Same as maker
$0.10 in · $0.30 out
$0.15/M tokens - 53Same as maker
$0.10 in · $0.30 out
$0.15/M tokens - 54Resells
$0.10 in · $0.30 out
$0.15/M tokens - 55Runs it themselves
$0.09 in · $0.34 out
$0.15/M tokens - 56Lower precision (fp4)
$0.09 in · $0.34 out
$0.15/M tokens - 57Same as maker
$0.10 in · $0.32 out
$0.16/M tokens - 58Same as maker
$0.10 in · $0.32 out
$0.16/M tokens - 59Runs it themselves
$0.09 in · $0.40 out
$0.16/M tokens - 60Runs it themselves
$0.09 in · $0.40 out
$0.16/M tokens - 61Runs it themselves
$0.09 in · $0.40 out
$0.16/M tokens - 62Same as maker
$0.14 in · $0.28 out
$0.18/M tokens - 63Same as maker
$0.14 in · $0.28 out
$0.18/M tokens - 64Same as maker
$0.14 in · $0.28 out
$0.18/M tokens - 65Same as maker
$0.10 in · $0.40 out
$0.18/M tokens - 66Same as maker
$0.18 in · $0.18 out
$0.18/M tokens - 67Same as maker
$0.18 in · $0.18 out
$0.18/M tokens - 68Same as maker
$0.20 in · $0.20 out
$0.20/M tokens - 69Runs it themselves
$0.09 in · $0.55 out
$0.21/M tokens - 70Lower precision (fp8)
$0.09 in · $0.55 out
$0.21/M tokens - 71Runs it themselves
$0.15 in · $0.40 out
$0.21/M tokens - 72Costs more
$0.12 in · $0.50 out
$0.21/M tokens - 73Costs more
$0.12 in · $0.50 out
$0.21/M tokens - 74Same as maker
$0.13 in · $0.53 out
$0.23/M tokens - 75Same as maker
$0.15 in · $0.50 out
$0.24/M tokens - 76Same as maker
$0.15 in · $0.50 out
$0.24/M tokens - 77Same as maker
$0.15 in · $0.50 out
$0.24/M tokens - 78Same as maker
$0.20 in · $0.40 out
$0.25/M tokens - 79Same as maker
$0.20 in · $0.40 out
$0.25/M tokens - 80Same as maker
$0.15 in · $0.60 out
$0.26/M tokens - 81Runs it themselves
$0.15 in · $0.60 out
$0.26/M tokens - 82Lower precision (fp8)
$0.15 in · $0.60 out
$0.26/M tokens - 83Runs it themselves
$0.27 in · $0.27 out
$0.27/M tokens - 84Costs more
$0.23 in · $0.40 out
$0.27/M tokens - 85Resells
$0.26 in · $0.38 out
$0.29/M tokens - 86Resells
$0.26 in · $0.38 out
$0.29/M tokens - 87Costs more
$0.20 in · $0.60 out
$0.30/M tokens - 88Costs more
$0.20 in · $0.60 out
$0.30/M tokens - 89Runs it themselves
$0.10 in · $0.95 out
$0.31/M tokens - 90Lower precision (fp8)
$0.10 in · $0.95 out
$0.31/M tokens - 91Runs it themselves
$0.09 in · $1.10 out
$0.34/M tokens - 92Lower precision (fp8)
$0.09 in · $1.10 out
$0.34/M tokens - 93Costs more
$0.20 in · $0.80 out
$0.35/M tokens - 94
Nemotron 3 Nano Omni 30B A3B Reasoning
Costs more$0.20 in · $0.80 out
$0.35/M tokens - 95Runs it themselves
$0.14 in · $1 out
$0.35/M tokens - 96Lower precision (fp8)
$0.14 in · $1 out
$0.35/M tokens - 97Same as maker
$0.36 in · $0.40 out
$0.37/M tokens - 98Same as maker
$0.36 in · $0.40 out
$0.37/M tokens - 99Runs it themselves
$0.20 in · $0.88 out
$0.37/M tokens - 100Lower precision (fp8)
$0.20 in · $0.88 out
$0.37/M tokens - 101Costs more
$0.20 in · $0.95 out
$0.39/M tokens - 102Runs it themselves
$0.15 in · $1.15 out
$0.40/M tokens - 103Same as maker
$0.40 in · $0.40 out
$0.40/M tokens - 104Same as maker
$0.40 in · $0.40 out
$0.40/M tokens - 105Same as maker
$0.40 in · $0.40 out
$0.40/M tokens - 106Costs more
$0.40 in · $0.40 out
$0.40/M tokens - 107Runs it themselves
$0.24 in · $0.90 out
$0.41/M tokens - 108Same as maker
$0.25 in · $0.95 out
$0.42/M tokens - 109Same as maker
$0.25 in · $0.95 out
$0.42/M tokens - 110Runs it themselves
$0.25 in · $1 out
$0.44/M tokens - 111Same as maker
$0.20 in · $1.15 out
$0.44/M tokens - 112Costs more
$0.30 in · $0.90 out
$0.45/M tokens - 113Same as maker
$0.27 in · $1 out
$0.45/M tokens - 114Runs it themselves
$0.14 in · $1.40 out
$0.45/M tokens - 115Costs more
$0.32 in · $0.89 out
$0.46/M tokens - 116Runs it themselves
$0.30 in · $1 out
$0.47/M tokens - 117Lower precision (fp4)
$0.30 in · $1 out
$0.47/M tokens - 118Resells
$0.28 in · $1.10 out
$0.49/M tokens - 119Resells
$0.28 in · $1.10 out
$0.49/M tokens - 120Same as maker
$0.30 in · $1.20 out
$0.52/M tokens - 121Same as maker
$0.30 in · $1.20 out
$0.52/M tokens - 122Same as maker
$0.43 in · $0.87 out
$0.54/M tokens - 123Same as maker
$0.43 in · $0.87 out
$0.54/M tokens - 124Same as maker
$0.25 in · $1.50 out
$0.56/M tokens - 125Runs it themselves
$0.15 in · $1.88 out
$0.58/M tokens - 126Runs it themselves
$0.45 in · $1.20 out
$0.64/M tokens - 127Lower precision (fp8)
$0.45 in · $1.20 out
$0.64/M tokens - 128Costs more
$0.44 in · $1.32 out
$0.66/M tokens - 129Costs more
$0.44 in · $1.32 out
$0.66/M tokens - 130Same as maker
$0.70 in · $0.70 out
$0.70/M tokens - 131Same as maker
$0.70 in · $0.70 out
$0.70/M tokens - 132Runs it themselves
$0.40 in · $1.60 out
$0.70/M tokens - 133Runs it themselves
$0.40 in · $1.60 out
$0.70/M tokens - 134Costs more
$0.38 in · $1.70 out
$0.71/M tokens - 135Runs it themselves
$0.40 in · $1.75 out
$0.74/M tokens - 136Lower precision (fp4)
$0.40 in · $1.75 out
$0.74/M tokens - 137Runs it themselves
$0.20 in · $2.50 out
$0.78/M tokens - 138Runs it themselves
$0.29 in · $2.40 out
$0.82/M tokens - 139Runs it themselves
$0.26 in · $2.60 out
$0.84/M tokens - 140Lower precision (fp8)
$0.26 in · $2.60 out
$0.84/M tokens - 141Same as maker
$0.30 in · $2.50 out
$0.85/M tokens - 142Same as maker
$0.85 in · $0.85 out
$0.85/M tokens - 143Runs it themselves
$0.50 in · $2 out
$0.88/M tokens - 144Lower precision (fp4)
$0.50 in · $2 out
$0.88/M tokens - 145Runs it themselves
$0.50 in · $2 out
$0.88/M tokens - 146Runs it themselves
$0.45 in · $2.25 out
$0.90/M tokens - 147Resells
$0.50 in · $2.15 out
$0.91/M tokens - 148Resells
$0.50 in · $2.15 out
$0.91/M tokens - 149Runs it themselves
$0.50 in · $2.20 out
$0.93/M tokens - 150Lower precision (fp4)
$0.50 in · $2.20 out
$0.93/M tokens - 151Runs it themselves
$0.30 in · $2.90 out
$0.95/M tokens - 152Same as maker
$1 in · $1 out
$1/M tokens - 153Same as maker
$1 in · $1 out
$1/M tokens - 154Runs it themselves
$0.32 in · $3.20 out
$1.04/M tokens - 155Lower precision (fp8)
$0.32 in · $3.20 out
$1.04/M tokens - 156Runs it themselves
$0.45 in · $3 out
$1.09/M tokens - 157Lower precision (fp8)
$0.45 in · $3 out
$1.09/M tokens - 158Same as maker
$0.50 in · $3 out
$1.13/M tokens - 159Runs it themselves
$0.75 in · $2.40 out
$1.16/M tokens - 160Lower precision (fp4)
$0.75 in · $2.40 out
$1.16/M tokens - 161Same as maker
$0.83 in · $2.50 out
$1.25/M tokens - 162Same as maker
$0.83 in · $2.50 out
$1.25/M tokens - 163Runs it themselves
$0.68 in · $3.40 out
$1.36/M tokens - 164Resells
$1 in · $2.70 out
$1.43/M tokens - 165Runs it themselves
$0.75 in · $3.50 out
$1.44/M tokens - 166Lower precision (fp4)
$0.75 in · $3.50 out
$1.44/M tokens - 167Costs more
$1 in · $3 out
$1.50/M tokens - 168Same as maker
$0.75 in · $3.75 out
$1.50/M tokens - 169Costs more
$1 in · $3 out
$1.50/M tokens - 170Costs more
$1.30 in · $2.60 out
$1.63/M tokens - 171Costs more
$1.30 in · $2.60 out
$1.63/M tokens - 172Runs it themselves
$1.05 in · $3.50 out
$1.66/M tokens - 173Runs it themselves
$0.90 in · $4 out
$1.68/M tokens - 174Lower precision (fp4)
$0.90 in · $4 out
$1.68/M tokens - 175Runs it themselves
$0.95 in · $4.05 out
$1.72/M tokens - 176Same as maker
$1 in · $5 out
$2/M tokens - 177Costs more
$1 in · $5 out
$2/M tokens - 178Same as maker
$1.20 in · $6 out
$2.40/M tokens - 179Same as maker
$2 in · $6 out
$3/M tokens - 180Same as maker
$1.50 in · $9 out
$3.38/M tokens - 181Same as maker
$1.25 in · $10 out
$3.44/M tokens - 182Same as maker
$2.50 in · $7.50 out
$3.75/M tokens - 183Same as maker
$2 in · $10 out
$4/M tokens - 184Same as maker
$2 in · $12 out
$4.50/M tokens - 185Resells
$2.85 in · $14.25 out
$5.70/M tokens - 186Resells
$2.85 in · $14.25 out
$5.70/M tokens - 187Same as maker
$3 in · $15 out
$6/M tokens - 188Costs more
$3 in · $15 out
$6/M tokens - 189Same as maker
$4 in · $20 out
$8/M tokens - 190Same as maker
$5 in · $25 out
$10/M tokens - 191Same as maker
$5 in · $25 out
$10/M tokens - 192Same as maker
$5 in · $25 out
$10/M tokens - 193Same as maker
$10 in · $50 out
$20/M tokens
Not ranked
Below the maker's own price with nothing published to account for it, or from a catalog we could not read reliably. Why
- Not ranked
$0.02 in · $0.03 out
$0.02/M tokens - Not ranked
$0.06 in · $0.06 out
$0.06/M tokens - Not ranked
$0.11 in · $0.38 out
$0.18/M tokens - Not ranked
$0.60 in · $2.08 out
$0.97/M tokens - Not ranked
$1.65 in · $4.95 out
$2.48/M tokens
Where to start
Cheapest
Llama 3.2 3B Instruct
131k context · structured output · open weights
DeepInfra
The least you pay per million tokens at DeepInfra.
Biggest saving
Qwen3 32B
131k context · tool calling · reasoning
DeepInfra
89% less than you pay Alibaba Cloud for it.
Most widely sold
GLM-5.3-Flash
1M context · tool calling · reads images
DeepInfra
105 providers sell it, so you can hold this price against theirs.
Kind
Host
based in US
Free tier
No
every price is paid
Where DeepInfra ranks
What DeepInfra charges per million tokens embedded
Priced on input alone, since an embedding model writes no output, so never held beside a chat model's blended price. Every embedding model
Embedding models, per 1M input tokens
- 1No maker price
Beijing Academy of Artificial Intelligence
0.5¢/M tokens - 2Runs it themselves
Beijing Academy of Artificial Intelligence
$0.01/M tokens - 3Runs it themselves
intfloat
$0.01/M tokens - 4
E5 Multi-Lingual Large Embeddings 0.6B
No maker priceintfloat
$0.01/M tokens - 5
E5 Multi-Lingual Large Embeddings 0.6B
No maker priceintfloat
$0.01/M tokens - 6Runs it themselves
Alibaba Cloud
$0.01/M tokens - 7No maker price
Alibaba Cloud
$0.01/M tokens - 8No maker price
Alibaba Cloud
$0.02/M tokens
What DeepInfra charges per image, clip or recording
Priced by the job, so never held beside a price per million tokens. Every image model
Images, per image
- 1
Sdxl Turbo
No maker priceStability AI
0.02¢per image - 2No maker price
Black Forest Labs
0.05¢per image - 3No maker price
Black Forest Labs
0.9¢per image - 4
FLUX.2 [dev]
No maker priceBlack Forest Labs
1¢per image - 5No maker price
Black Forest Labs
1.4¢per image - 6No maker price
Black Forest Labs
1.5¢per image - 7No maker price
Black Forest Labs
1.5¢per image - 8
Wan 2.6 Image
No maker priceAlibaba Cloud
3¢per image
- 9
Wan 2.7 Image
No maker priceAlibaba Cloud
3¢per image - 10
Fibo
No maker priceBria
4¢per image - 11
Fibo 2.0
No maker priceBria
4¢per image - 12
Fibo Edit 1.5
No maker priceBria
4¢per image - 13No maker price
Black Forest Labs
4¢per image - 14No maker price
ByteDance
4¢per image - 15No maker price
ByteDance
4¢per image - 16
Qwen Image Edit Max
No maker priceAlibaba Cloud
7.5¢per image - 17
Qwen Image Max
No maker priceAlibaba Cloud
7.5¢per image - 18No maker price
ByteDance
9.9¢per image - 19No maker price
Black Forest Labs
$0.10per image - 20
Flux
No maker priceBlack Forest Labs
$0.20per image
Video, per 5-second clip
- 1
Pixverse 6
No maker pricePixVerse
$0.23per 5-second clip - 2
Wan 2.2 T 2v A 14b
No maker priceAlibaba Cloud
$0.38per 5-second clip - 3No maker price
Alibaba Cloud
$0.50per 5-second clip - 4No maker price
Alibaba Cloud
$0.50per 5-second clip - 5Costs more
Google
$0.75per 5-second clip - 6No maker price
Alibaba Cloud
$1per 5-second clip - 7Same as maker
Google
$2per 5-second clip
Speech, per 1M characters
- 1
Kokoro 82M
No maker pricehexgrad
$0.99per 1M characters - 2
Csm 1b
No maker priceSesame
$7per 1M characters - 3
Orpheus 3b 0.1 Ft
No maker priceCanopy Labs
$7per 1M characters
Frequently asked
- What is DeepInfra?
- Serves open-weight models on its own GPUs, often at fp8 or fp4, and publishes the precision per model. It sells 126 of the models we track, and trades as Deep Infra, Inc., based in US.
- Is DeepInfra cheaper than buying from the maker?
- 103 of its 198 prices are below the maker's own price, and 90 of those come with a published reason, so they can lead a ranking. 5 are listed and not ranked, because nothing accounts for the gap.
- Does DeepInfra train on what you send it?
- DeepInfra does not say whether it trains on what you send it. It does not say how long it keeps requests.
- How current are these DeepInfra prices?
- They come from its own public catalog, read every 3 days; the reading on this page is from 31 Oct 2026. Prices exclude tax.
Where to go next