D
DeepInfra
synced
| Model | Type | Input | Output | Context | Last sync | |
|---|---|---|---|---|---|---|
MN
mistralai/Mistral-Nemo-Instruct-2407
None
|
LLM | $0.019 | $0.03 | 131,072 | ||
ML
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
None
|
LLM | $0.02 | $0.04 | 131,072 | ||
|
GO
|
LLM | $0.03 | $0.14 | 131,072 | ||
IG
ibm-granite/granite-4.2-3b
None
|
LLM | $0.03 | $0.12 | 131,072 | ||
|
GO
|
LLM | $0.037 | $0.17 | 131,072 | ||
| S8 Sao10K/L3-8B-Lunaris-v1-Turbo None | LLM | $0.04 | $0.05 | 8,192 | ||
|
G3
|
LLM | $0.05 | $0.15 | 131,072 | ||
|
G3
|
LLM | $0.05 | $0.1 | 131,072 | ||
MS
Mistral Small 3
mistralai
|
LLM | $0.05 | $0.08 | 32,768 | ||
DV
DeepSeek V4 Flash 0731
deepseek
|
LLM | $0.06 | $0.18 | 1,048,576 | ||
G4
Granite 4.2 8B
ibm-granite
|
LLM | $0.06 | $0.25 | 131,072 | ||
L3
Ling 3.0 Flash
inclusionai
|
LLM | $0.06 | $0.18 | 131,072 | ||
L3
Ling 3.0 Flash Fin
inclusionai
|
LLM | $0.06 | $0.18 | 262,144 | ||
L3
Ling 3.0 Flash VL
inclusionai
|
LLM | $0.06 | $0.18 | 131,072 | ||
NN
nvidia/NVIDIA-Nemotron-3.5-Lightning
None
|
LLM | $0.06 | $0.16 | 262,144 | ||
P4
Phi 4
microsoft
|
LLM | $0.07 | $0.14 | 16,384 | ||
|
G4
|
LLM | $0.07 | $0.34 | 262,144 | ||
MS
Mistral Small 3.2 24B
mistralai
|
LLM | $0.075 | $0.2 | 128,000 | ||
|
G3
|
LLM | $0.08 | $0.16 | 131,072 | ||
Q3
Qwen3 32B
qwen
|
LLM | $0.08 | $0.28 | 40,960 | ||
NN
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
None
|
LLM | $0.085 | $0.4 | 262,144 | ||
Q2
Qwen3 235B A22B Instruct 2507
qwen
|
LLM | $0.09 | $0.55 | 262,144 | ||
QN
Qwen3 Next 80B A3B Instruct
qwen
|
LLM | $0.09 | $1.1 | 262,144 | ||
DA
deepseek-ai/DeepSeek-V4-Flash
None
|
LLM | $0.09 | $0.18 | 1,048,576 | ||
|
G4
|
LLM | $0.09 | $0.34 | 262,144 | ||
L4
Llama 4 Scout
meta-llama
|
LLM | $0.1 | $0.3 | 327,680 | ||
Q5
Qwen3.5-9B
qwen
|
LLM | $0.1 | $0.15 | 262,144 | ||
Q6
Qwen3.6 35B A3B
qwen
|
LLM | $0.1 | $0.95 | 262,144 | ||
S2
Seed-2.0-Mini
bytedance-seed
|
LLM | $0.1 | $0.4 | 256,000 | ||
ML
meta-llama/Llama-3.3-70B-Instruct-Turbo
None
|
LLM | $0.1 | $0.32 | 131,072 | ||
Q8
Qwen3.8 Flash
qwen
|
LLM | $0.113 | $0.382 | 1,000,000 | ||
Q1
Qwen3 14B
qwen
|
LLM | $0.12 | $0.24 | 40,960 | ||
Q3
Qwen3 30B A3B
qwen
|
LLM | $0.12 | $0.5 | 40,960 | ||
MV
MiMo-V2.6-Flash
xiaomi
|
Transcription | $0.14 | $0.28 | 1,048,576 | ||
Q5
Qwen3.5-35B-A3B
qwen
|
LLM | $0.14 | $1 | 262,144 | ||
QV
Qwen3 VL 30B A3B Instruct
qwen
|
LLM | $0.15 | $0.6 | 262,144 | ||
|
G4
|
LLM | $0.15 | $0.4 | 262,144 | ||
|
OO
|
LLM | $0.15 | $0.6 | 131,072 | ||
ZO
zai-org/GLM-5.3-Flash
None
|
LLM | $0.15 | $0.5 | 1,048,576 | ||
IG
ibm-granite/granite-4.2-30b
None
|
LLM | $0.16 | $0.65 | 131,072 | ||
LG
Llama Guard 4 12B
meta-llama
|
LLM | $0.18 | $0.18 | 163,840 | ||
Q8
Qwen/Qwen3.8-27B
None
|
LLM | $0.2 | $2.5 | 262,144 | ||
QV
Qwen3 VL 235B A22B Instruct
qwen
|
LLM | $0.2 | $0.88 | 262,144 | ||
DA
deepseek-ai/DeepSeek-V4.1-Flash
None
|
LLM | $0.2 | $0.6 | 1,048,576 | ||
NC
nvidia/Nemotron-Content-Safety-3.5
None
|
LLM | $0.2 | $0.2 | 131,072 | ||
|
OO
|
LLM | $0.2 | $0.95 | 131,072 | ||
B1
ByteDance/Seed-1.8
None
|
LLM | $0.25 | $2 | 256,000 | ||
DV
DeepSeek V3.1
deepseek
|
LLM | $0.25 | $0.95 | 163,840 | ||
|
G3
|
LLM | $0.25 | $1.5 | 1,000,000 | ||
DV
DeepSeek V3.2
deepseek
|
LLM | $0.26 | $0.38 | 163,840 | ||
Q5
Qwen3.5-27B
qwen
|
LLM | $0.26 | $2.6 | 262,144 | ||
|
G4
|
LLM | $0.27 | $0.76 | 131,072 | ||
MM
MiniMax M3
minimax
|
LLM | $0.28 | $1.1 | 524,288 | ||
|
G2
|
Transcription | $0.3 | $2.5 | 1,000,000 | ||
MG
Muse Glimmer 30B
meta
|
LLM | $0.3 | $1.2 | 131,072 | ||
QC
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
None
|
LLM | $0.3 | $1 | 262,144 | ||
DV
DeepSeek V3
deepseek
|
LLM | $0.32 | $0.89 | 163,840 | ||
Q6
Qwen3.6 27B
qwen
|
LLM | $0.32 | $3.2 | 262,144 | ||
Q5
Qwen2.5 72B Instruct
qwen
|
LLM | $0.36 | $0.4 | 32,768 | ||
G4
GLM 4.7
z-ai
|
LLM | $0.4 | $1.75 | 202,752 | ||
| M1 MythoMax 13B gryphe | LLM | $0.4 | $0.4 | 4,096 | ||
ML
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
None
|
LLM | $0.4 | $0.4 | 131,072 | ||
MV
MiMo-V2.6-Pro
xiaomi
|
Transcription | $0.43 | $0.87 | 1,048,576 | ||
DV
DeepSeek V4 Flash Vision Exp
deepseek
|
LLM | $0.44 | $1.32 | 1,048,576 | ||
Q5
Qwen3.5 397B A17B
qwen
|
LLM | $0.45 | $3 | 262,144 | ||
TS
thinkingmachines/Inkling-Small
None
|
Video | $0.45 | $1.2 | 524,288 | ||
B2
ByteDance/Seed-2.0-pro
None
|
LLM | $0.5 | $3 | 256,000 | ||
G4
GLM 4.6
z-ai
|
LLM | $0.5 | $2 | 202,752 | ||
S2
Seed-2.0-Code
bytedance-seed
|
LLM | $0.5 | $3 | 256,000 | ||
DA
deepseek-ai/DeepSeek-R1-0528
None
|
LLM | $0.5 | $2.15 | 163,840 | ||
NN
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
None
|
LLM | $0.5 | $2.2 | 262,144 | ||
H3
Hermes 3 70B Instruct
nousresearch
|
LLM | $0.7 | $0.7 | 131,072 | ||
G5
GLM 5.2
z-ai
|
LLM | $0.75 | $2.4 | 1,048,576 | ||
KK
Kimi K2.6
moonshotai
|
LLM | $0.75 | $3.5 | 262,144 | ||
|
G3
|
LLM | $0.75 | $3.75 | 1,000,000 | ||
HP
Hy4 preview
tencent
|
LLM | $0.834 | $2.501 | 1,048,576 | ||
| S1 Sao10K/L3.1-70B-Euryale-v2.2 None | LLM | $0.85 | $0.85 | 131,072 | ||
ZO
zai-org/GLM-5.3
None
|
LLM | $0.9 | $4 | 1,048,576 | ||
T
thinkingmachines/Inkling
None
|
Video | $0.95 | $4.05 | 524,288 | ||
H3
Hermes 3 405B Instruct
nousresearch
|
LLM | $1 | $1 | 131,072 | ||
|
AH
|
LLM | $1 | $5 | 200,000 | ||
QM
Qwen3 Max
qwen
|
LLM | $1.2 | $6 | 256,000 | ||
QM
Qwen3 Max Thinking
qwen
|
LLM | $1.2 | $6 | 256,000 | ||
|
G2
|
Transcription | $1.25 | $10 | 1,000,000 | ||
DV
DeepSeek V4 Pro 0813
deepseek
|
LLM | $1.3 | $2.6 | 1,048,576 | ||
DA
deepseek-ai/DeepSeek-V4-Pro
None
|
LLM | $1.3 | $2.6 | 1,048,576 | ||
|
G3
|
LLM | $1.5 | $9 | 1,000,000 | ||
Q8
Qwen/Qwen3.8-Max
None
|
LLM | $1.65 | $4.951 | 256,000 | ||
|
AC
|
LLM | $2 | $10 | 1,000,000 | ||
Q8
Qwen3.8 2.4T A95B
qwen
|
LLM | $2 | $6 | 262,144 | ||
|
G3
|
LLM | $2 | $12 | 1,000,000 | ||
Q7
Qwen3.7 Max
qwen
|
LLM | $2.5 | $7.5 | 256,000 | ||
MK
moonshotai/Kimi-K3
None
|
LLM | $2.85 | $14.25 | 1,048,576 | ||
|
AS
|
LLM | $3 | $15 | 1,000,000 | ||
|
AS
|
LLM | $3 | $15 | 1,000,000 | ||
|
AO
|
LLM | $4 | $20 | 1,000,000 | ||
|
AO
|
LLM | $5 | $25 | 1,000,000 | ||
|
AO
|
LLM | $5 | $25 | 1,000,000 | ||
|
AO
|
LLM | $5 | $25 | 1,000,000 | ||
|
AF
|
LLM | $10 | $50 | 1,000,000 | ||
| AT Audio8/Audio8-TTS-Preview-0.6b None | Speech | — | — | — | ||
BB
BAAI/bge-base-en-v1.5
None
|
LLM | — | — | 512 | ||
BE
BAAI/bge-en-icl
None
|
LLM | — | — | 8,192 | ||
BL
BAAI/bge-large-en-v1.5
None
|
LLM | — | — | 512 | ||
BM
BAAI/bge-m3
None
|
LLM | — | — | 8,192 | ||
BM
BAAI/bge-m3-multi
None
|
LLM | — | — | 512 | ||
BM
BAAI/bge-m3-multi-8k
None
|
LLM | — | — | 8,192 | ||
B3
Bria/Bria-3.2
None
|
LLM | — | — | — | ||
B3
Bria/Bria-3.2-vector
None
|
LLM | — | — | — | ||
B
Bria/blur_background
None
|
LLM | — | — | — | ||
B
Bria/erase_foreground
None
|
LLM | — | — | — | ||
B
Bria/expand
None
|
LLM | — | — | — | ||
B
Bria/fibo
None
|
LLM | — | — | — | ||
B1
Bria/fibo-1.5
None
|
LLM | — | — | — | ||
B
Bria/fibo_edit
None
|
LLM | — | — | — | ||
B1
Bria/fibo_edit-1.5
None
|
LLM | — | — | — | ||
B
Bria/remove_background
None
|
LLM | — | — | — | ||
B1
ByteDance/Seedance-1.5-Pro
None
|
LLM | — | — | — | ||
B2
ByteDance/Seedance-2.0
None
|
LLM | — | — | — | ||
B4
ByteDance/Seedream-4
None
|
LLM | — | — | — | ||
P6
Pixverse/Pixverse-6-T2V
None
|
LLM | — | — | — | ||
PT
Pixverse/Pixverse-T2V
None
|
LLM | — | — | — | ||
PT
Pixverse/Pixverse-T2V-HD
None
|
LLM | — | — | — | ||
PI
PrunaAI/p-image
None
|
Image | — | — | — | ||
PV
PrunaAI/p-video
None
|
Video | — | — | — | ||
QI
Qwen/Qwen-Image-Max
None
|
Image | — | — | — | ||
QA
Qwen/Qwen3-ASR-0.6B
None
|
LLM | — | — | — | ||
QA
Qwen/Qwen3-ASR-1.7B
None
|
LLM | — | — | — | ||
QE
Qwen/Qwen3-Embedding-0.6B
None
|
Embeddings | — | — | 32,768 | ||
QE
Qwen/Qwen3-Embedding-4B
None
|
Embeddings | — | — | 32,768 | ||
QE
Qwen/Qwen3-Embedding-8B
None
|
Embeddings | — | — | 32,768 | ||
QT
Qwen/Qwen3-TTS
None
|
Speech | — | — | — | ||
QT
Qwen/Qwen3-TTS-VoiceDesign
None
|
Speech | — | — | — | ||
RM
ResembleAI/chatterbox-multilingual
None
|
LLM | — | — | — | ||
RT
ResembleAI/chatterbox-turbo
None
|
LLM | — | — | — | ||
VS
Voxtral Small 24B 2507
mistralai
|
Transcription | — | — | 32,768 | ||
WA
Wan-AI/Wan2.2-T2V-A14B
None
|
LLM | — | — | — | ||
WA
Wan-AI/Wan2.6-T2I
None
|
LLM | — | — | — | ||
WA
Wan-AI/Wan2.6-T2V
None
|
LLM | — | — | — | ||
XV
XiaomiMiMo/MiMo-V2.5-tts
None
|
Speech | — | — | — | ||
XV
XiaomiMiMo/MiMo-V2.5-tts-voicedesign
None
|
Speech | — | — | — | ||
BF
black-forest-labs/FLUX-1-Redux-dev
None
|
LLM | — | — | — | ||
BF
black-forest-labs/FLUX-1-dev
None
|
LLM | — | — | — | ||
BF
black-forest-labs/FLUX-1-schnell
None
|
LLM | — | — | — | ||
BF
black-forest-labs/FLUX-1.1-pro
None
|
LLM | — | — | — | ||
BF
black-forest-labs/FLUX-2-dev
None
|
LLM | — | — | — | ||
BF
black-forest-labs/FLUX-2-klein-4b
None
|
LLM | — | — | — | ||
BF
black-forest-labs/FLUX-2-klein-9b
None
|
LLM | — | — | — | ||
BF
black-forest-labs/FLUX-2-max
None
|
LLM | — | — | — | ||
BF
black-forest-labs/FLUX-2-pro
None
|
LLM | — | — | — | ||
B5
bosonai/HiggsAudioV2.5
None
|
LLM | — | — | — | ||
|
G3
|
Embeddings | — | — | 2,048 | ||
|
G3
|
Image | — | — | — | ||
|
GB
|
LLM | — | — | — | ||
|
GB
|
LLM | — | — | — | ||
|
GB
|
LLM | — | — | — | ||
|
G3
|
LLM | — | — | — | ||
|
G3
|
LLM | — | — | — | ||
| H8 hexgrad/Kokoro-82M None | LLM | — | — | — | ||
| IB intfloat/e5-base-v2 None | LLM | — | — | 512 | ||
| IL intfloat/e5-large-v2 None | LLM | — | — | 512 | ||
| IE intfloat/multilingual-e5-large None | LLM | — | — | 512 | ||
| IE intfloat/multilingual-e5-large-instruct None | LLM | — | — | 512 | ||
IA
inworld-ai/realtime-tts-1.5-max
None
|
Speech | — | — | — | ||
IA
inworld-ai/realtime-tts-1.5-mini
None
|
Speech | — | — | — | ||
IA
inworld-ai/realtime-tts-2
None
|
Speech | — | — | — | ||
MM
mistralai/Voxtral-Mini-3B-2507
None
|
LLM | — | — | — | ||
N3
nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b
None
|
LLM | — | — | — | ||
NN
nvidia/llama-nemotron-embed-vl-1b-v2
None
|
Embeddings | — | — | 10,240 | ||
|
OL
|
Transcription | — | — | — | ||
|
OL
|
Transcription | — | — | — | ||
ST
sentence-transformers/all-MiniLM-L12-v2
None
|
LLM | — | — | 512 | ||
ST
sentence-transformers/all-MiniLM-L6-v2
None
|
LLM | — | — | 512 | ||
ST
sentence-transformers/all-mpnet-base-v2
None
|
LLM | — | — | 512 | ||
ST
sentence-transformers/clip-ViT-B-32
None
|
LLM | — | — | 77 | ||
ST
sentence-transformers/clip-ViT-B-32-multilingual-v1
None
|
LLM | — | — | 512 | ||
ST
sentence-transformers/multi-qa-mpnet-base-dot-v1
None
|
LLM | — | — | 512 | ||
ST
sentence-transformers/paraphrase-MiniLM-L6-v2
None
|
LLM | — | — | 512 | ||
S1
sesame/csm-1b
None
|
LLM | — | — | — | ||
| SB shibing624/text2vec-base-chinese None | LLM | — | — | 512 | ||
ST
stabilityai/sdxl-turbo
None
|
LLM | — | — | — | ||
| TB thenlper/gte-base None | LLM | — | — | 512 | ||
| TL thenlper/gte-large None | LLM | — | — | 512 |