DeepInfra models on OneInfer

One key for every DeepInfra model.

Browse the DeepInfra models available through OneInfer's unified API. Compare current pricing, supported modalities, context limits, and model capabilities from a single provider catalog.

171 models and 282 price rows; the lowest listed price is $0.00022 / 1024x1024 image for Stability AI: SDXL Turbo.

Use DeepInfra models in 4 steps

Step 1 of 4

Create a key in the Console. The same key works for DeepInfra and every other provider in the catalog.

Categories

  • Text models51
  • Image models36
  • Embedding models31
  • Video models20
  • Audio models13
  • Transcription models8
  • Decision models5
  • Rerank models5
  • Image classification models2

Modalities

text, audio, embeddings, video, image, decisions, rerank, classification

API access

Use the same OneInfer API key and model ID format to route requests across available DeepInfra models.

DeepInfra model catalog

Dynamic data from model pricing and model metadata APIs.

All models
ModelPricing

ACE-Step: ACE-Step 1.5 XL

107fc88cbfe14884ba922f80db0b4778
$0.0011 / sec

Alibaba: GTE Base

3a91ef8bdaaf46a2b09130513a83d623
$0.0055 / 1M input tokens

Alibaba: GTE Large

6b894b0712b4498daa8ec916cc8eaec4
$0.011 / 1M input tokens

Alibaba: Wan 2.6 T2V

b0eb82519919498a9a9a54fa674fd73a
$0.1000 / sec

Alibaba: Wan 3.0 Video

4192b9bc9fc64aaf9b7a9cc75560cbe5
$0.0550 / sec

Alibaba: Wan2.2 T2V A14B

7c247ef8a70d46f9956e84f72119d0e0
$0.412 / video

Audio8: TTS Preview 0.6B

f7690400c56043fe99790c7daedfa21b
$5.500 / 1M chars

BAAI: BGE Base EN v1.5

0bcc60c4af53454a958ee32ea4b196e3
$0.0055 / 1M input tokens

BAAI: BGE EN ICL

c91e88cc664b45d3a3109b15082659fd
$0.011 / 1M input tokens

BAAI: BGE Large EN v1.5

4c3354ebf26b41f2a9b108ef2bb48da7
$0.011 / 1M input tokens

BAAI: BGE M3

77a4bd443a87486587d359c4aecccb87
$0.011 / 1M input tokens

BAAI: BGE M3 Multi

18b3ca32751148f19f77b55a13a7bef4
$0.011 / 1M input tokens

BAAI: BGE M3 Multi 8K

0b223105db36421981ef9cb742f47df9
$0.011 / 1M input tokens

Black Forest Labs: FLUX.1 [dev]

32a03b70695746848aa5655b86caef24
$0.0099 / 1024x1024 image

Black Forest Labs: FLUX.1 [schnell]

56af9a05eab94c3da9d214bf230243a5
$0.00055 / 1024x1024 image

Black Forest Labs: FLUX.2 [dev]

d90a6f59f6ee40679d496cb303906238
$0.011 / 1024x1024 image

Black Forest Labs: FLUX.2 Klein 4B

395baef5cc8f48d8a1297d17fb4d9c0a
$0.015 / 1024x1024 image

Black Forest Labs: FLUX.2 Klein 9B

054f5fa71768438f8f00e36449c0f728
$0.017 / 1024x1024 image

Black Forest Labs: FLUX.2 Max

c41e50c0d42b43128d96d80577400b96
from $0.070 / image

Black Forest Labs: FLUX.2 Pro

ee9cbfc48e4047159e81fdb1da472b86
from $0.030 / image

Black Forest Labs: FLUX1.1 [pro]

4fbc0f764f7b4312a994d4617af07ad3
$0.044 / image

Boson AI: Higgs Audio V2.5

9cc616e58d9a45b193765e9214f0727c
$22.000 / 1M chars

Bria: Blur Background

21669ce9deb4405fb26b1207083f7a01
$0.044 / image

Bria: Bria 3.2

94655ba2966f4e719c05f379e1f46866
$0.044 / image

Bria: Bria 3.2 Vector

46707cfc0c4748b5b30f8192f6f0d76d
$0.044 / image

Bria: Enhance

c4f614969fad459cbf3cbdbbeb4e27ad
$0.044 / image

Bria: Erase Foreground

2b81468df54f4bf1bebff8f1897e9e72
$0.044 / image

Bria: Eraser

da3db23a435f4a8c91c174d861c24eb0
$0.044 / image

Bria: Expand

1c11c29628dc4d5a92d2750821515050
$0.044 / image

Bria: FIBO 2.0

8f2190e4750b4aa9969429b400d47af7
$0.044 / image

Bria: FIBO Edit

81e481c692e4424da47c7c961d304e89
$0.044 / image

Bria: FIBO Edit 1.5

5586e2a570a44b3fadd689595c6e8f3e
$0.044 / image

Bria: GenFill

7c54feb6c97d4ed895d15373691133c7
$0.044 / image

Bria: Remove Background

d0864b19531c45cba25d290830d59852
$0.020 / image

Bria: Remove Background (Guided)

cac1b406a3d448a48ad5ec7293260402
$0.033 / image

Bria: Replace Background

990e0f4715194dae8b38a07e178ffc8c
$0.044 / image

Bria: Video Eraser

e062a223063449dc9654cb658d6eb8cb
$0.0550 / sec

Bria: Video Foreground Mask

1000c140e34b46779ba2cde15120bba5
$0.1540 / sec

Bria: Video Mask by Prompt

e1aa71df78284302b75fa2fe6fca3819
$0.1540 / sec

Bria: Video Remove Background

9b6b3381fd4b456790fefceca00ec9fa
$0.0550 / sec

Bria: Video Upscale

bbe94177c92e42afbc58763f0f50333e
$0.0550 / sec

Canopy Labs: Orpheus 3B

09050064598a4fe3b52fa22e61de85cf
$7.700 / 1M chars

Clarity AI: Creative Upscaler

ba22867c0fc5457a94c9d213609671c7
$0.055 / image

Clarity AI: Crystal Upscaler

107ecc7b6afe487a8bfb1ba0f30b4d56
$0.055 / image

Clarity AI: Flux Upscaler

b143525e061b4b05a83b838dc8fae0cd
$0.220 / image

Cloudflare: Clef

17449402327541b48bdaddec0b29c7e6
$0.264 / 1M input tokens

Cloudflare: Clef Flash

cd90b28f66c74e8e9ffeec873780c172
$0.042 / 1M input tokens

DeepSeek: DeepSeek R1 0528

8cba63fb141a49a6a161e86029304dff
$0.550 in / $2.365 out

DeepSeek: DeepSeek V3

25e99e21a6584f7b818696756e805e6b
$0.352 in / $0.979 out

DeepSeek: DeepSeek V3.1

546eee12b8694b94b96d9f3e6fa31dda
$0.270 in / $1.000 out

DeepSeek: DeepSeek V3.2

2c7c25b34d1947ed99ce971e176be983
$0.269 in / $0.400 out

DeepSeek: DeepSeek V4 Flash Vision (Exp)

9af4827188894454a8e382a2ffc7b9a4
$0.484 in / $1.452 out

DeepSeek: DeepSeek V4.1 Flash

716599fa426843b1be46ee720ed4d0f6
$0.300 in / $1.200 out

FastVideo: FastWan 1.3B

7e4d38d412d64053ad63125449189c2d
$0.014 / video

FastVideo: FastWan 2.2 5B

68bd71c75c964176bab1b92506d042a8
$0.025 / video

Google: EmbeddingGemma 2

af2f51b86c27463594c25b36df5ad855
$0.022 / 1M input tokens

Google: EmbeddingGemma 300M

59e2c4a101c1443caa5aa49b83b90865
$0.0022 / 1M input tokens

Google: Gemini 3 Pro Image

09f8cb8433cb4499bfeb0efe126816fc
$0.160 / image

Google: Gemini 3.1 Flash Image

81bb05eb8b7c4f9089812e4a61debeab
$0.075 / image

Google: Gemma 3 27B

a401ebb6958840c99c09a8a2a44fc476
$0.088 in / $0.176 out

Google: Gemma 3 4B

d9160b26bf994eafb1e202c7d8ef6717
$0.055 in / $0.110 out

Google: Gemma 4 26B A4b

64ddc56799ba4c8b88fdcea066e92e22
$0.130 in / $0.400 out

Google: Nano Banana 2 Lite

3569a88200494a60ba10a412f4a9cba5
$0.037 / image

Google: Veo 3.1

f974b79bdc8941ee827098a0a565d170
$3.520 / video

Google: Veo 3.1 Fast

d5ce69c847fb4ee7aa29cb00e35d47d3
$1.320 / video

hexgrad: Kokoro 82M

02351d1b78c44a12ba365987c1048a64
$1.089 / 1M chars

IBM: Granite 4.2 8B

6b66b05627f64037a30de6f6cd916a23
$0.066 in / $0.275 out

InclusionAI: Ling 3.0 Flash

02e9f537e1d24a3197ad326072341b22
$0.060 in / $0.180 out

InclusionAI: Ling 3.0 Flash VL

f561d9cae2f948a8ac63f61ba66a1c04
$0.075 in / $0.220 out

InclusionAI: Ling 3.1 Flash

cc50062e9eb64aa88974ec0e1f00911c
$0.300 in / $0.900 out

inclusionAI: Ming-Image 0.1 Design

375df18a85654aca9172bc41bd8fa75b
$0.047 / image

inclusionAI: Ming-Image 0.1 Design Layer

149d668235c748ffbb0a970de586242c
$0.011 / image

intfloat: E5 Base v2

92964be08529474aaffaf4cc4a97e42e
$0.0055 / 1M input tokens

intfloat: E5 Large v2

8fced9868f2e40978c3fd5179477d7ef
$0.011 / 1M input tokens

intfloat: Multilingual E5 Large

d6dba05b725d4bc1aa30ec22630a08ab
$0.011 / 1M input tokens

intfloat: Multilingual E5 Large Instruct

1722712f090f416899ca81e7f005d052
$0.011 / 1M input tokens

Inworld: Realtime TTS 1.5 Max

b6b8501a67c8470c8e945efc253a405c
$55.000 / 1M chars

Inworld: Realtime TTS 1.5 Mini

611bda6c428c486e87b6e0972fd9c1e6
$27.500 / 1M chars

Inworld: Realtime TTS 2

0e756a50b7254dfbb9bca014a530f5bf
$38.500 / 1M chars

Meta: Llama 3.1 8B Instruct

f68ca662890240f88f7281d9874e8f98
$0.022 in / $0.044 out

Meta: Llama 3.3 70B Instruct

41d777609f63458e8deb0e32f634d21d
$0.135 in / $0.400 out

Meta: Llama 4 Scout 17B 16E

391d894439b94fbfb5c6876361d02f25
$0.110 in / $0.330 out

Meta: Llama Guard 4 12B

96d243f0d7e04dd8a9a3c8652debb523
$0.198 in / $0.198 out

Meta: Muse Glimmer 30B

e059ca29986448038c397070d82af892
$0.350 in / $1.500 out

Microsoft: Phi-4

8b1dead1ac29425d88c4de3376d9d9f4
$0.077 in / $0.154 out

Mistral AI: Mistral Nemo Instruct 2407

27814cfe104a48f3a1fb02859d9f9be9
$0.040 in / $0.170 out

Mistral AI: Mistral Small 3 24B

140e416056c644e3bd4e805398c6de22
$0.055 in / $0.088 out

Mistral AI: Mistral Small 3.2 24B

c014c1ed88064fa583eb4f3b32c0ef37
$0.083 in / $0.220 out

Mistral: Voxtral Mini 3B

fb273139153043459e8ca0201b1371f1
$0.066 / audio hour

Mistral: Voxtral Small 24B

a93338d9de1a457fae4247338d0ce6ec
$0.198 / audio hour

Moonshot AI: Kimi K3

0d44936e86a64972a90aaf873f907bc8
$3.000 in / $15.000 out

Moonshot AI: Kimi K3.1 Pro

af60ff55be7143b689ec09d95fb655ad
$2.000 in / $10.000 out

Nace.AI: Drex Max

c897783f07df45028b32faf582268a56
$0.132 / 1M input tokens

Nace.AI: Drex v1.5

f3a78b6df9f0433ea75b239e19e691a7
$0.044 / 1M input tokens

Nace.AI: Drex v2.0

71f3e6f07b4f4512a4e7c995ffe759bc
$0.066 / 1M input tokens

NVIDIA: Llama Nemotron Embed VL 1B v2

52d9a4fcc498470ba9a39461624681c3
$0.011 / 1M input tokens

NVIDIA: Llama Nemotron Rerank VL 1B v2

702683947cbc4f279bd08e93dca3420d
$0.011 / 1M input tokens

NVIDIA: Nemotron 3 Embed 1B

9c1ef4c201d144ed83fb98ff2373a816
$0.017 / 1M input tokens

NVIDIA: Nemotron 3 Embed 1B NVFP4

ce72229ea90f4d41945d855c90ca84d1
$0.011 / 1M input tokens

NVIDIA: Nemotron 3 Embed 8B

cde81feda959445fa38b462769f585bd
$0.038 / 1M input tokens

NVIDIA: Nemotron 3 Super 120B A12B

30bb2553524d49f087c0b29d40a92dc3
$0.093 in / $0.440 out

NVIDIA: Nemotron 3.5 ASR Multilingual 0.6B

543ab0ffcd5e4f20bc5bfb22630e1e1a
$0.013 / audio hour

NVIDIA: Nemotron 3.5 Embed 1B

dea9eb0616544f8f97fdb6d73ff884d6
$0.017 / 1M input tokens

NVIDIA: Nemotron 3.5 Embed 8B

d8e0ed1824dd4bc5bdf144cda9c375d5
$0.038 / 1M input tokens

NVIDIA: Nemotron 3.5 Lightning

a30aaad7f96c4e718552f2dccc64f4ba
$0.066 in / $0.176 out

NVIDIA: Nemotron 3.5 Rerank 8B

c5ee9fe9b2554da9b309c83d420f18d9
$0.055 / 1M input tokens

NVIDIA: Nemotron 3.5 Transcribe 30B

b81b7640b69b410aaf5b022bc566898a
$0.132 / audio hour

NVIDIA: Nemotron Content Safety 3.5

e657836f7ebd43b79679f7b29610cc04
$0.220 in / $0.220 out

NVIDIA: Nemotron-3 Ultra 550B A55B

cc71cb88b4d54a07a1efc693d77ec72c
$0.600 in / $3.600 out

NVIDIA: Nemotron-3.5 Super VL 120B A12B

d8bf37a6fd6f4866a5d5ffc628132eec
$0.150 in / $0.500 out

OpenAI: CLIP ViT-B/32

ca4022d2501a4de797e4f3d057fdf366
$0.00055 / sec

OpenAI: CLIP ViT-L/14 336px

e4412b7e81cf4599ba58159880fb15ec
$0.00055 / sec

OpenAI: GPT Oss 120B

edf00af1ab9143e4977c7c1e3cd15e89
$0.037 in / $0.187 out

OpenAI: Whisper Large v3

768d1abbbf54482ca634d621b8c360d4
$0.030 / audio hour

OpenAI: Whisper Large v3 Turbo

3182a9e7d0a04e1a95e37d0de6366572
$0.013 / audio hour

PixVerse: Text-to-Video

f43b8723aed84886b5a6c888b30f45c4
$0.220 / video

PixVerse: Text-to-Video HD

30d7de07af38473f8afa0b778ba4a3a9
$0.440 / video

PixVerse: V6 Image-to-Video

92942af9a2d54fe8b0a8012246b33ad2
$0.0275 / sec

PixVerse: V6 Text-to-Video

4d70afb47f8e4654b3d857e387c45d61
$0.0275 / sec

Pruna AI: P-Image

16c47c5ded6c436593b3e074b9b9b4fa
$0.0055 / image

Pruna AI: P-Image Edit

6c6dc187857b4a9bad38a6455441a52d
$0.011 / image

Pruna AI: P-Video

3624f939f0b748c2aafb3d442e132f45
$0.0220 / sec

Pruna AI: P-Video Avatar

5f4389eed2ab4938b711d60459fa9949
$0.0275 / sec

Qwen: Qwen 2.5 72B Instruct

f50e5b4c7f81485590889058ed4bbc7f
$0.380 in / $0.400 out

Qwen: Qwen3 14B

279a2f8bcb684c6db65c55a3ed39510b
$0.132 in / $0.264 out

Qwen: Qwen3 235B A22B Instruct 2507

54e08f6db16a4e6999c8b038cea1bc7a
$0.090 in / $0.580 out

Qwen: Qwen3 30B A3B

8f8687a8ea824a10acf78472ae5fc034
$0.132 in / $0.550 out

Qwen: Qwen3 32B

a7031bd141d44fb1b3903a36701bb319
$0.088 in / $0.308 out

Qwen: Qwen3 Coder 480B A35B Instruct FP8

2ad7c37b5f1b4d9d8a01e3a171369d13
$0.380 in / $1.550 out

Qwen: Qwen3 Embedding 0.6B

be49637ad67c402da6035d6c539d4320
$0.011 / 1M input tokens

Qwen: Qwen3 Embedding 4B

f16d4261488847d080d031ef87f815a3
$0.022 / 1M input tokens

Qwen: Qwen3 Embedding 8B

5ff2808afecb4c029030d98c50f552bd
$0.011 / 1M input tokens

Qwen: Qwen3 Next 80B A3B Instruct

7f1ff617b45c466d99fb19d26cb7e49b
$0.150 in / $1.500 out

Qwen: Qwen3 Reranker 0.6B

88486c59da684036a59df33cbdde4fec
$0.011 / 1M input tokens

Qwen: Qwen3 Reranker 4B

50dc539b733f49d9af63869c615cf10b
$0.028 / 1M input tokens

Qwen: Qwen3 Reranker 8B

578d2adccf2646788ef47055350c029a
$0.055 / 1M input tokens

Qwen: Qwen3 VL 235B A22B Instruct

80a40e84fb6d4baab3d12eda8327d8dc
$0.220 in / $0.968 out

Qwen: Qwen3 VL 30B A3B Instruct

7b2ff6bfbf3b459dad916e759e89fdad
$0.165 in / $0.660 out

Qwen: Qwen3-ASR 0.6B

707be098a95047139e09707ff9a3c888
$0.013 / audio hour

Qwen: Qwen3-ASR 1.7B

b7342e7c56e04b7fbb8451b66ecd3735
$0.030 / audio hour

Qwen: Qwen3-TTS

2fc9319d44894848bd548a3009345ca0
$22.000 / 1M chars

Qwen: Qwen3-TTS VoiceDesign

6eafbd341cf9473cb506946fc02142f7
$22.000 / 1M chars

Qwen: Qwen3.5 9B

60f171be06b6450798bc3834901f2796
$0.110 in / $0.165 out

Qwen: Qwen3.8 Flash

477233e87af648af8730c9e7c3a42a04
$0.150 in / $0.470 out

Qwen: Qwen3.8 Max

6687bfcfb52d4945aa836220b5b4cf16
$2.000 in / $6.000 out

Resemble AI: Chatterbox Multilingual

6522d4957d094ece872b47307265f54e
$1.100 / 1M chars

Resemble AI: Chatterbox Turbo

294745de5eed4ffd998715a5b544e0d2
$1.100 / 1M chars

Sao10K: L31 70B Euryale V2.2

9695f980-1418-4cf3-8bbb-4cba42d914d0
$0.935 in / $0.935 out

Sao10K: Llama 3 8B Lunaris

c15db9d9b0794ca9b27a1c720ea9757e
$0.044 in / $0.055 out

Sentence Transformers: all-MiniLM-L12-v2

9db4072c50cd4aaabd05867f6d2e90fa
$0.0055 / 1M input tokens

Sentence Transformers: all-MiniLM-L6-v2

484e8176cec84a16bf0013f3733cf3f8
$0.0055 / 1M input tokens

Sentence Transformers: all-mpnet-base-v2

aed252a0470043738665ce6571a0519a
$0.0055 / 1M input tokens

Sentence Transformers: CLIP ViT-B/32

e6729019ac2f4e888c8694bb1671bede
$0.0055 / 1M input tokens

Sentence Transformers: CLIP ViT-B/32 Multilingual

03a6c4c35f6c43078d648a47a0c3a775
$0.0055 / 1M input tokens

Sentence Transformers: multi-qa-mpnet-base-dot-v1

aaabeaae0ad94f49a4f0402c16e1c34c
$0.0055 / 1M input tokens

Sentence Transformers: paraphrase-MiniLM-L6-v2

583ebab53db043b39e0e7bd8a173eac4
$0.0055 / 1M input tokens

Sesame: CSM 1B

991db2fdb1b44bf284f7eb8b43c6dcc3
$7.700 / 1M chars

shibing624: text2vec Base Chinese

264a29aad0d242f980ecaa857229ae70
$0.0055 / 1M input tokens

Stability AI: SDXL Turbo

9e4b372c8c304fb9a17f32a895cec26e
$0.00022 / 1024x1024 image

Tencent: Hy4 Preview

bd3ddf4e80e744c68f1bf947a7b9389b
$0.917 in / $2.751 out

Wan: Wan2.6 Image Edit

d6069ec0697f41cfbb88a383efa13699
$0.033 / image

Wan: Wan2.6 Text-to-Image

1de5e2a9c03e4b98ac41bc61570e495a
$0.033 / image

Wan: Wan2.7 Image

d6f8f80d77534e67a4f0ca0913920389
$0.033 / image

Wan: Wan2.7 Image-to-Video

9289ce45dd864aee9942ffbe3f479703
$0.1100 / sec

Wan: Wan2.7 Reference-to-Video

b5eea9660e9b422ba60c6528f4023d59
$0.1100 / sec

Xiaomi: MiMo-V2.6-Flash

1c47258e90894b9eaf791122fee11059
$0.140 in / $0.280 out

Xiaomi: MiMo-V2.6-Pro

3a6b5c82ff8040c08aaaff689a5d8386
$0.435 in / $0.870 out

Z.ai: GLM 4.6

f763a93d3e3a44e0a581f416d1691533
$0.550 in / $2.200 out

Z.ai: GLM 4.7

0cbd861c491f4e589fa4ca9ec354f4ba
$0.600 in / $2.200 out

Z.ai: GLM 5.2

d7b7ad781cc64967a06e1047e65414b0
$1.400 in / $4.400 out

ZAI: GLM 5.3 Flash

17530b712f79494f827aa57b770d65fa
$0.150 in / $0.500 out