$ AIPriceBoardbeta

Models

406 models in the catalog. Prices are the best (lowest) input price per million tokens across providers.

Models — best input prices

The live catalog of 406 AI models: text, image, video, audio, transcription and embedding models served by 81 inference providers. Every price is pulled directly from provider APIs during the nightly sync — no manual reports — and shown as the best (lowest) input rate per provider in USD per 1M tokens. Click any model to compare input and output prices, context windows and provider availability side by side.

ModelTypeProvidersInputOutputLast sync
0A 01-ai/yi-large logo 01-ai/yi-large LLM 0 — —
AM All MiniLM L6 v2 logo All MiniLM L6 v2 Embeddings 1 $0.009 —
AC Anthropic Claude 4.5 Haiku logo Anthropic Claude 4.5 Haiku LLM 0 — —
AC Anthropic Claude 4.5 Sonnet logo Anthropic Claude 4.5 Sonnet LLM 1 $3 $15
AC Anthropic Claude 5.5 Haiku logo Anthropic Claude 5.5 Haiku LLM 1 $0.1 $0.5
AC Anthropic Claude Fable 5.1 logo Anthropic Claude Fable 5.1 LLM 1 $10 $50
AC Anthropic Claude Opus 4.5 logo Anthropic Claude Opus 4.5 LLM 1 $5 $25
AC Anthropic Claude Opus 4.6 logo Anthropic Claude Opus 4.6 LLM 1 $5 $25
AC Anthropic Claude Sonnet 5.5 logo Anthropic Claude Sonnet 5.5 LLM 2 $2 $10
A1 Apodex 1.1 Mini LLM 0 — —
AT Arcee Trinity Large Thinking (Public Preview) logo Arcee Trinity Large Thinking (Public Preview) LLM 1 $0.25 $0.9
AT Audio8/Audio8-TTS-Preview-0.6b Speech 0 — —
BB BAAI/bge-base-en-v1.5 logo BAAI/bge-base-en-v1.5 LLM 0 — —
BE BAAI/bge-en-icl logo BAAI/bge-en-icl LLM 0 — —
BL BAAI/bge-large-en-v1.5 logo BAAI/bge-large-en-v1.5 LLM 0 — —
BM BAAI/bge-m3 logo BAAI/bge-m3 LLM 0 — —
BM BAAI/bge-m3-multi logo BAAI/bge-m3-multi LLM 0 — —
BM BAAI/bge-m3-multi-8k logo BAAI/bge-m3-multi-8k LLM 0 — —
BR BGE Reranker v2 m3 logo BGE Reranker v2 m3 Rerank 1 $0.01 —
BM Bge M3 logo Bge M3 Embeddings 1 $0.02 —
B3 Bria/Bria-3.2 logo Bria/Bria-3.2 LLM 0 — —
B3 Bria/Bria-3.2-vector logo Bria/Bria-3.2-vector LLM 0 — —
B Bria/blur_background logo Bria/blur_background LLM 0 — —
B Bria/erase_foreground logo Bria/erase_foreground LLM 0 — —
B Bria/expand logo Bria/expand LLM 0 — —
B Bria/fibo logo Bria/fibo LLM 0 — —
B1 Bria/fibo-1.5 logo Bria/fibo-1.5 LLM 0 — —
B Bria/fibo_edit logo Bria/fibo_edit LLM 0 — —
B1 Bria/fibo_edit-1.5 logo Bria/fibo_edit-1.5 LLM 0 — —
B Bria/remove_background logo Bria/remove_background LLM 0 — —
B1 ByteDance/Seed-1.8 logo ByteDance/Seed-1.8 LLM 1 $0.25 $2
B2 ByteDance/Seed-2.0-pro logo ByteDance/Seed-2.0-pro LLM 1 $0.5 $3
B1 ByteDance/Seedance-1.5-Pro logo ByteDance/Seedance-1.5-Pro LLM 0 — —
B2 ByteDance/Seedance-2.0 logo ByteDance/Seedance-2.0 LLM 0 — —
B4 ByteDance/Seedream-4 logo ByteDance/Seedream-4 LLM 0 — —
DV DeepSeek V3 logo DeepSeek V3 LLM 2 $0.32 $0.89
DV DeepSeek V3.1 logo DeepSeek V3.1 LLM 1 $0.25 $0.95
DV DeepSeek V3.2 logo DeepSeek V3.2 LLM 1 $0.26 $0.38
DV DeepSeek V4 Flash 0731 logo DeepSeek V4 Flash 0731 LLM 3 $0.06 $0.18
DV DeepSeek V4 Flash Vision Exp logo DeepSeek V4 Flash Vision Exp LLM 1 $0.44 $1.32
DV DeepSeek V4 Pro 0813 logo DeepSeek V4 Pro 0813 LLM 3 $1.3 $2.6
DV DeepSeek V4.1 Flash logo DeepSeek V4.1 Flash LLM 1 $0.3 $1.2
D3 Deepseek 3.2 logo Deepseek 3.2 LLM 1 $0.5 $1.6
DV Deepseek V4 Flash logo Deepseek V4 Flash LLM 1 $0.14 $0.28
DV Deepseek V4 Pro logo Deepseek V4 Pro LLM 1 $1.74 $3.48
EL E5 Large V2 Embeddings 1 $0.02 —
E4 ERNIE 4.5 VL 424B A47B  logo ERNIE 4.5 VL 424B A47B LLM 0 — —
FE Fal ElevenLabs TTS Multilingual v2 Speech 0 — —
FF Fal Fast SDXL Image 0 — —
FF Fal Flux Schnell Image 0 — —
FS Fal Stable Audio 2.5 Speech 0 — —
G4 GLM 4.5 Air logo GLM 4.5 Air LLM 1 $0.13 $0.85
G4 GLM 4.5V logo GLM 4.5V LLM 1 $0.6 $1.8
G4 GLM 4.6 logo GLM 4.6 LLM 2 $0.5 $2
G4 GLM 4.6V logo GLM 4.6V LLM 1 $0.3 $0.9
G4 GLM 4.7 logo GLM 4.7 LLM 2 $0.4 $1.75
G4 GLM 4.7 Flash logo GLM 4.7 Flash LLM 1 $0.07 $0.4
G5 GLM 5 logo GLM 5 LLM 1 $1 $3.2
G5 GLM 5 Turbo logo GLM 5 Turbo LLM 0 — —
G5 GLM 5.1 logo GLM 5.1 LLM 1 $1.38 $4.4
G5 GLM 5.2 logo GLM 5.2 LLM 3 $0.75 $2.4
G5 GLM 5V Turbo logo GLM 5V Turbo LLM 0 — —
G3 GLM5.3 logo GLM5.3 LLM 1 $1.4 $4.4
G3 GLM5.3 Flash logo GLM5.3 Flash LLM 1 $0.15 $0.5
G4 GPT-4o (batch) logo GPT-4o (batch) LLM 1 $2.5 $10
G4 GPT-4o-mini (batch) logo GPT-4o-mini (batch) LLM 1 $0.15 $0.6
GL GTE Large EN v1.5 Embeddings 1 $0.09 —
G2 Gemini 2.5 Flash (batch) logo Gemini 2.5 Flash (batch) Transcription 1 $0.3 $2.5
G2 Gemini 2.5 Pro (batch) logo Gemini 2.5 Pro (batch) Transcription 1 $1.25 $10
G3 Gemma 3 12B logo Gemma 3 12B LLM 2 $0.05 $0.1
G3 Gemma 3 27B logo Gemma 3 27B LLM 2 $0.08 $0.16
G3 Gemma 3 4B logo Gemma 3 4B LLM 1 $0.05 $0.1
G4 Gemma 4 logo Gemma 4 LLM 1 $0.18 $0.5
G4 Granite 4.2 8B logo Granite 4.2 8B LLM 1 $0.06 $0.25
H3 Hermes 3 405B Instruct logo Hermes 3 405B Instruct LLM 1 $1 $1
H3 Hermes 3 70B Instruct logo Hermes 3 70B Instruct LLM 1 $0.7 $0.7
H Hy3 logo Hy3 LLM 1 $0.14 $0.58
HP Hy4 preview logo Hy4 preview LLM 2 $0.834 $2.501
KK Kimi K2 0905 logo Kimi K2 0905 LLM 1 $0.6 $2.5
KK Kimi K2 Thinking logo Kimi K2 Thinking LLM 1 $0.6 $2.5
KK Kimi K2.5 logo Kimi K2.5 LLM 1 $0.6 $3
KK Kimi K2.6 logo Kimi K2.6 LLM 3 $0.75 $3.4
KK Kimi K2.7 Code logo Kimi K2.7 Code LLM 1 $0.95 $4
KK Kimi K3 logo Kimi K3 LLM 2 $3 $15
L3 Ling 3.0 Flash logo Ling 3.0 Flash LLM 2 $0.06 $0.18
L3 Ling 3.0 Flash Fin logo Ling 3.0 Flash Fin LLM 1 $0.075 $0.22
L3 Ling 3.0 Flash VL logo Ling 3.0 Flash VL LLM 2 $0.06 $0.18
L3 Llama 3.1 8B Instruct logo Llama 3.1 8B Instruct LLM 1 $0.02 $0.05
L3 Llama 3.1 Instruct (8B) logo Llama 3.1 Instruct (8B) LLM 1 $0.198 $0.198
L3 Llama 3.2 1B Instruct logo Llama 3.2 1B Instruct LLM 1 $0.02 $0.02
L3 Llama 3.3 70B Instruct logo Llama 3.3 70B Instruct LLM 1 $0.135 $0.4
L4 Llama 4 Maverick logo Llama 4 Maverick LLM 1 $0.25 $0.87
L4 Llama 4 Scout logo Llama 4 Scout LLM 2 $0.1 $0.3
LG Llama Guard 4 12B logo Llama Guard 4 12B LLM 1 $0.18 $0.18
MV MiMo-V2.5 logo MiMo-V2.5 Transcription 1 $0.168 $0.336
MV MiMo-V2.5-Pro logo MiMo-V2.5-Pro LLM 2 $0.522 $1.044
MV MiMo-V2.6-Flash logo MiMo-V2.6-Flash Transcription 2 $0.14 $0.28
MV MiMo-V2.6-Pro logo MiMo-V2.6-Pro Transcription 2 $0.43 $0.87
MV MiMo-V2.6-Pro-UltraSpeed logo MiMo-V2.6-Pro-UltraSpeed Transcription 0 — —
MM MiniMax M2 logo MiniMax M2 LLM 0 — —
MM MiniMax M2.1 logo MiniMax M2.1 LLM 0 — —
MM MiniMax M2.5 logo MiniMax M2.5 LLM 2 $0.3 $1.2
MM MiniMax M2.7 logo MiniMax M2.7 LLM 1 $0.3 $1.2
MM MiniMax M3 logo MiniMax M3 LLM 2 $0.28 $1.1
MM MiniMaxAI/MiniMax-M2.7-Turbo logo MiniMaxAI/MiniMax-M2.7-Turbo LLM 0 — —
M3 Ministral 3 14B LLM 1 $0.2 $0.2
M3 Ministral 3 8B LLM 0 — —
M7 Mistral 7B Instruct v0.3 logo Mistral 7B Instruct v0.3 LLM 0 — —
ML Mistral Large logo Mistral Large LLM 0 — —
MN Mistral Nemo logo Mistral Nemo LLM 0 — —
MS Mistral Small 3 logo Mistral Small 3 LLM 1 $0.05 $0.08
MS Mistral Small 3.2 24B logo Mistral Small 3.2 24B LLM 1 $0.075 $0.2
MQ Multi QA MPNet Base Dot v1 Embeddings 1 $0.009 —
MG Muse Glimmer 30B logo Muse Glimmer 30B LLM 1 $0.3 $1.2
M1 MythoMax 13B LLM 2 $0.09 $0.09
N3 Nemotron 3 Diarization logo Nemotron 3 Diarization Transcription 0 — —
N3 Nemotron 3 Nano 30B A3B logo Nemotron 3 Nano 30B A3B LLM 1 $0.05 $0.2
N3 Nemotron 3 Nano Omni logo Nemotron 3 Nano Omni LLM 1 $0.5 $0.9
N3 Nemotron 3 Ultra logo Nemotron 3 Ultra LLM 1 $0.9 $1.7
NN Nemotron-nano 12b v2-vl logo Nemotron-nano 12b v2-vl LLM 1 $0.2 $0.6
OG OpenAI GPT Image 1 logo OpenAI GPT Image 1 Image 1 $5 $40
OG OpenAI GPT Image 1.5 logo OpenAI GPT Image 1.5 Image 1 $5 $10
OG OpenAI GPT Image 2 logo OpenAI GPT Image 2 Image 1 $8 $30
OG OpenAI GPT-4.1 logo OpenAI GPT-4.1 LLM 1 $2 $8
OG OpenAI GPT-5 logo OpenAI GPT-5 LLM 1 $1.25 $10
OG OpenAI GPT-5 Mini logo OpenAI GPT-5 Mini LLM 1 $0.25 $2
OG OpenAI GPT-5 Nano logo OpenAI GPT-5 Nano LLM 1 $0.05 $0.4
OG OpenAI GPT-5.2 logo OpenAI GPT-5.2 LLM 1 $1.75 $14
OG OpenAI GPT-5.2 Pro logo OpenAI GPT-5.2 Pro LLM 1 $21 $0.000168
OG OpenAI GPT-5.3 Codex logo OpenAI GPT-5.3 Codex LLM 1 $1.75 $14
OG OpenAI GPT-5.4 logo OpenAI GPT-5.4 LLM 1 $2.5 $15
OG OpenAI GPT-5.4 Mini logo OpenAI GPT-5.4 Mini LLM 1 $0.75 $4.5
OG OpenAI GPT-5.4 Nano logo OpenAI GPT-5.4 Nano LLM 1 $0.2 $1.25
OG OpenAI GPT-5.4 Pro logo OpenAI GPT-5.4 Pro LLM 1 $30 $0.00018
OG OpenAI GPT-5.5 logo OpenAI GPT-5.5 LLM 1 $5 $30
OG OpenAI GPT-5.6 Luna logo OpenAI GPT-5.6 Luna LLM 1 $0.2 $1.2
OG OpenAI GPT-5.6 Sol logo OpenAI GPT-5.6 Sol LLM 1 $4 $19.999998
OG OpenAI GPT-5.6 Terra logo OpenAI GPT-5.6 Terra LLM 1 $2 $12
OG OpenAI GPT-6 Astra logo OpenAI GPT-6 Astra LLM 1 $10 $50
OG OpenAI GPT-6 Luna logo OpenAI GPT-6 Luna LLM 1 $0.1 $0.5
OG OpenAI GPT-6 Sol logo OpenAI GPT-6 Sol LLM 1 $2 $10
OG OpenAI GPT-6.1 Sol logo OpenAI GPT-6.1 Sol LLM 1 $2 $10
OO OpenAI o1 logo OpenAI o1 LLM 1 $15 $60
OO OpenAI o3 logo OpenAI o3 LLM 1 $2 $8
OO OpenAI o3 mini logo OpenAI o3 mini LLM 1 $1.1 $4.4
P4 Phi 4 logo Phi 4 LLM 1 $0.07 $0.14
P6 Pixverse/Pixverse-6-T2V logo Pixverse/Pixverse-6-T2V LLM 0 — —
PT Pixverse/Pixverse-T2V logo Pixverse/Pixverse-T2V LLM 0 — —
PT Pixverse/Pixverse-T2V-HD logo Pixverse/Pixverse-T2V-HD LLM 0 — —
PI PrunaAI/p-image logo PrunaAI/p-image Image 0 — —
PV PrunaAI/p-video logo PrunaAI/p-video Video 0 — —
Q2 Qwen 2.5 14B Instruct logo Qwen 2.5 14B Instruct LLM 0 — —
QI Qwen/Qwen-Image-Edit logo Qwen/Qwen-Image-Edit Image 0 — —
QI Qwen/Qwen-Image-Max logo Qwen/Qwen-Image-Max Image 0 — —
QA Qwen/Qwen3-ASR-0.6B logo Qwen/Qwen3-ASR-0.6B LLM 0 — —
QA Qwen/Qwen3-ASR-1.7B logo Qwen/Qwen3-ASR-1.7B LLM 0 — —
QC Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo logo Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo LLM 1 $0.3 $1
QE Qwen/Qwen3-Embedding-0.6B logo Qwen/Qwen3-Embedding-0.6B Embeddings 0 — —
QE Qwen/Qwen3-Embedding-4B logo Qwen/Qwen3-Embedding-4B Embeddings 0 — —
QE Qwen/Qwen3-Embedding-8B logo Qwen/Qwen3-Embedding-8B Embeddings 0 — —
QT Qwen/Qwen3-TTS logo Qwen/Qwen3-TTS Speech 0 — —
QT Qwen/Qwen3-TTS-VoiceDesign logo Qwen/Qwen3-TTS-VoiceDesign Speech 0 — —
Q8 Qwen/Qwen3.8-27B logo Qwen/Qwen3.8-27B LLM 2 $0.2 $2.5
Q8 Qwen/Qwen3.8-Max logo Qwen/Qwen3.8-Max LLM 2 $1.65 $4.951
Q5 Qwen2.5 72B Instruct logo Qwen2.5 72B Instruct LLM 1 $0.36 $0.4
Q1 Qwen3 14B logo Qwen3 14B LLM 1 $0.12 $0.24
Q2 Qwen3 235B A22B Instruct 2507 logo Qwen3 235B A22B Instruct 2507 LLM 1 $0.09 $0.55
Q2 Qwen3 235B A22B Thinking 2507 logo Qwen3 235B A22B Thinking 2507 LLM 0 — —
Q3 Qwen3 30B A3B logo Qwen3 30B A3B LLM 1 $0.12 $0.5
Q3 Qwen3 32B logo Qwen3 32B LLM 1 $0.08 $0.28
QC Qwen3 Coder 30B A3B Instruct logo Qwen3 Coder 30B A3B Instruct LLM 0 — —
QC Qwen3 Coder Next logo Qwen3 Coder Next LLM 0 — —
QE Qwen3 Embedding 0.6B logo Qwen3 Embedding 0.6B Embeddings 1 $0.04 —
QM Qwen3 Max logo Qwen3 Max LLM 0 — —
QM Qwen3 Max Thinking logo Qwen3 Max Thinking LLM 0 — —
QN Qwen3 Next 80B A3B Instruct logo Qwen3 Next 80B A3B Instruct LLM 1 $0.09 $1.1
QT Qwen3 TTS logo Qwen3 TTS Speech 0 — —
QV Qwen3 VL 235B A22B Instruct logo Qwen3 VL 235B A22B Instruct LLM 1 $0.2 $0.88
QV Qwen3 VL 235B A22B Thinking logo Qwen3 VL 235B A22B Thinking LLM 0 — —
QV Qwen3 VL 30B A3B Instruct logo Qwen3 VL 30B A3B Instruct LLM 2 $0.15 $0.6
Q5 Qwen3.5 397B A17B logo Qwen3.5 397B A17B LLM 3 $0.45 $3
Q5 Qwen3.5-122B-A10B logo Qwen3.5-122B-A10B LLM 1 $0.4 $3.2
Q5 Qwen3.5-27B logo Qwen3.5-27B LLM 2 $0.26 $2.4
Q5 Qwen3.5-35B-A3B logo Qwen3.5-35B-A3B LLM 2 $0.14 $1
Q5 Qwen3.5-9B logo Qwen3.5-9B LLM 1 $0.1 $0.15
Q6 Qwen3.6 27B logo Qwen3.6 27B LLM 2 $0.32 $3.2
Q6 Qwen3.6 35B A3B logo Qwen3.6 35B A3B LLM 2 $0.1 $0.95
Q6 Qwen3.6 Plus logo Qwen3.6 Plus LLM 0 — —
Q7 Qwen3.7 Max logo Qwen3.7 Max LLM 2 $1.25 $3.75
Q8 Qwen3.8 2.4T A95B logo Qwen3.8 2.4T A95B LLM 1 $2 $6
Q8 Qwen3.8 Flash logo Qwen3.8 Flash LLM 2 $0.113 $0.382
Q8 Qwen3.8-Max LLM 1 $2 $6
R0 R1 0528 logo R1 0528 LLM 1 $0.7 $2.5
RM ResembleAI/chatterbox-multilingual logo ResembleAI/chatterbox-multilingual LLM 0 — —
RT ResembleAI/chatterbox-turbo logo ResembleAI/chatterbox-turbo LLM 0 — —
S8 Sao10K/L3-8B-Lunaris-v1-Turbo LLM 1 $0.04 $0.05
S8 Sao10K/L3-8B-Stheno-v3.2 LLM 1 $0.05 $0.05
S1 Sao10K/L3.1-70B-Euryale-v2.2 LLM 1 $0.85 $0.85
S2 Seed-2.0-Code logo Seed-2.0-Code LLM 1 $0.5 $3
S2 Seed-2.0-Mini logo Seed-2.0-Mini LLM 1 $0.1 $0.4
SD Stable Diffusion 3.5 Large Image 0 — —
S3 Step 3.7 Flash logo Step 3.7 Flash LLM 1 $0.2 $1.15
TJ TypeSafe Jev 1.13.0 LLM 1 $0.042 —
VS Voxtral Small 24B 2507 logo Voxtral Small 24B 2507 Transcription 0 — —
W2 Wan 2.2 T2V logo Wan 2.2 T2V LLM 0 — —
WA Wan-AI/Wan2.2-T2V-A14B logo Wan-AI/Wan2.2-T2V-A14B LLM 0 — —
WA Wan-AI/Wan2.6-T2I logo Wan-AI/Wan2.6-T2I LLM 0 — —
WA Wan-AI/Wan2.6-T2V logo Wan-AI/Wan2.6-T2V LLM 0 — —
W2 WizardLM-2 8x22B logo WizardLM-2 8x22B LLM 1 $0.62 $0.62
XV XiaomiMiMo/MiMo-V2.5-tts logo XiaomiMiMo/MiMo-V2.5-tts Speech 0 — —
XV XiaomiMiMo/MiMo-V2.5-tts-voicedesign logo XiaomiMiMo/MiMo-V2.5-tts-voicedesign Speech 0 — —
A8 adept/fuyu-8b logo adept/fuyu-8b LLM 0 — —
A1 ai21labs/jamba-1.5-large-instruct logo ai21labs/jamba-1.5-large-instruct LLM 0 — —
AL aisingapore/sea-lion-7b-instruct logo aisingapore/sea-lion-7b-instruct LLM 0 — —
AF anthropic/claude-fable-5 logo anthropic/claude-fable-5 LLM 2 $10 $50
AH anthropic/claude-haiku-4-5 logo anthropic/claude-haiku-4-5 LLM 2 $1 $5
AO anthropic/claude-opus-4-7 logo anthropic/claude-opus-4-7 LLM 2 $5 $25
AO anthropic/claude-opus-4-8 logo anthropic/claude-opus-4-8 LLM 2 $5 $25
AO anthropic/claude-opus-5 logo anthropic/claude-opus-5 LLM 2 $5 $25
AO anthropic/claude-opus-5-5 logo anthropic/claude-opus-5-5 LLM 2 $4 $20
AS anthropic/claude-sonnet-4-6 logo anthropic/claude-sonnet-4-6 LLM 2 $3 $15
AS anthropic/claude-sonnet-5 logo anthropic/claude-sonnet-5 LLM 2 $2 $10
BM baichuan/baichuan-m2-32b logo baichuan/baichuan-m2-32b LLM 1 $0.07 $0.07
B baidu/cobuddy logo baidu/cobuddy LLM 1 $0.28 $1.13
B4 baidu/ernie-4.5-21B-a3b logo baidu/ernie-4.5-21B-a3b LLM 1 $0.07 $0.28
B1 bigcode/starcoder2-15b logo bigcode/starcoder2-15b LLM 0 — —
BF black-forest-labs/FLUX-1-Redux-dev logo black-forest-labs/FLUX-1-Redux-dev LLM 0 — —
BF black-forest-labs/FLUX-1-dev logo black-forest-labs/FLUX-1-dev LLM 0 — —
BF black-forest-labs/FLUX-1-schnell logo black-forest-labs/FLUX-1-schnell LLM 0 — —
BF black-forest-labs/FLUX-1.1-pro logo black-forest-labs/FLUX-1.1-pro LLM 0 — —
BF black-forest-labs/FLUX-2-dev logo black-forest-labs/FLUX-2-dev LLM 0 — —
BF black-forest-labs/FLUX-2-klein-4b logo black-forest-labs/FLUX-2-klein-4b LLM 0 — —
BF black-forest-labs/FLUX-2-klein-9b logo black-forest-labs/FLUX-2-klein-9b LLM 0 — —
BF black-forest-labs/FLUX-2-max logo black-forest-labs/FLUX-2-max LLM 0 — —
BF black-forest-labs/FLUX-2-pro logo black-forest-labs/FLUX-2-pro LLM 0 — —
BF black-forest-labs/FLUX.1-Kontext-dev logo black-forest-labs/FLUX.1-Kontext-dev LLM 0 — —
B5 bosonai/HiggsAudioV2.5 logo bosonai/HiggsAudioV2.5 LLM 0 — —
B bunny LLM 0 — —
DI databricks/dbrx-instruct logo databricks/dbrx-instruct LLM 0 — —
DA deepseek-ai/DeepSeek-R1-0528 logo deepseek-ai/DeepSeek-R1-0528 LLM 1 $0.5 $2.15
DA deepseek-ai/DeepSeek-V4-Flash logo deepseek-ai/DeepSeek-V4-Flash LLM 1 $0.09 $0.18
DA deepseek-ai/DeepSeek-V4-Pro logo deepseek-ai/DeepSeek-V4-Pro LLM 1 $1.3 $2.6
DA deepseek-ai/DeepSeek-V4.1-Flash logo deepseek-ai/DeepSeek-V4.1-Flash LLM 1 $0.2 $0.6
DA deepseek-ai/deepseek-coder-6.7b-instruct logo deepseek-ai/deepseek-coder-6.7b-instruct LLM 0 — —
DO deepseek/deepseek-ocr-2 logo deepseek/deepseek-ocr-2 LLM 1 $0.03 $0.03
DR deepseek/deepseek-r1-0528-qwen3-8b logo deepseek/deepseek-r1-0528-qwen3-8b LLM 1 $0.06 $0.09
DR deepseek/deepseek-r1-turbo logo deepseek/deepseek-r1-turbo LLM 1 $0.7 $2.5
DR deepseek/deepseek-r1/community logo deepseek/deepseek-r1/community LLM 1 $4 $4
DV deepseek/deepseek-v4-flash logo deepseek/deepseek-v4-flash LLM 0 — —
DV deepseek/deepseek-v4-flash-0731-p logo deepseek/deepseek-v4-flash-0731-p LLM 1 $0.44 $1.32
DV deepseek/deepseek-v4-pro logo deepseek/deepseek-v4-pro LLM 1 $1.6 $3.2
DV deepseek/deepseek-v4-pro-0813-p logo deepseek/deepseek-v4-pro-0813-p LLM 1 $1.32 $3.96
DV deepseek/deepseek-v4.1-flash logo deepseek/deepseek-v4.1-flash LLM 1 $0.3 $1.2
DV deepseek/deepseek-v4.1-flash-dst logo deepseek/deepseek-v4.1-flash-dst LLM 1 $0.3 $1.2
DV deepseek/deepseek-v4.1-flash-p logo deepseek/deepseek-v4.1-flash-p LLM 1 $0.3 $1.2
G1 google/codegemma-1.1-7b logo google/codegemma-1.1-7b LLM 0 — —
G7 google/codegemma-7b logo google/codegemma-7b LLM 0 — —
G google/deplot logo google/deplot LLM 0 — —
G2 google/diffusiongemma-26b-a4b-it logo google/diffusiongemma-26b-a4b-it LLM 0 — —
G3 google/embeddinggemma-300m logo google/embeddinggemma-300m Embeddings 0 — —
G3 google/gemini-3-pro-image logo google/gemini-3-pro-image Image 0 — —
G3 google/gemini-3.1-flash-lite logo google/gemini-3.1-flash-lite LLM 1 $0.25 $1.5
G3 google/gemini-3.1-pro logo google/gemini-3.1-pro LLM 1 $2 $12
G3 google/gemini-3.5-flash logo google/gemini-3.5-flash LLM 1 $1.5 $9
G3 google/gemini-3.7-flash logo google/gemini-3.7-flash LLM 1 $0.75 $3.75
G2 google/gemma-2b logo google/gemma-2b LLM 0 — —
G4 google/gemma-4-26B-A4B-it logo google/gemma-4-26B-A4B-it LLM 2 $0.07 $0.34
G4 google/gemma-4-31B-it logo google/gemma-4-31B-it LLM 2 $0.14 $0.4
G4 google/gemma-4-31B-it-Ultra logo google/gemma-4-31B-it-Ultra LLM 1 $0.27 $0.76
G4 google/gemma-4-31B-it-turbo logo google/gemma-4-31B-it-turbo LLM 1 $0.09 $0.34
GB google/nano-banana-2 logo google/nano-banana-2 LLM 0 — —
GB google/nano-banana-2-lite logo google/nano-banana-2-lite LLM 0 — —
GB google/nano-banana-pro logo google/nano-banana-pro LLM 0 — —
G2 google/recurrentgemma-2b logo google/recurrentgemma-2b LLM 0 — —
G3 google/veo-3.1 logo google/veo-3.1 LLM 0 — —
G3 google/veo-3.1-fast logo google/veo-3.1-fast LLM 0 — —
GO gpt-oss-120b (batch) logo gpt-oss-120b (batch) LLM 3 $0.037 $0.17
GO gpt-oss-20b (batch) logo gpt-oss-20b (batch) LLM 2 $0.03 $0.14
H8 hexgrad/Kokoro-82M LLM 0 — —
IG ibm-granite/granite-4.2-30b logo ibm-granite/granite-4.2-30b LLM 1 $0.16 $0.65
IG ibm-granite/granite-4.2-3b logo ibm-granite/granite-4.2-3b LLM 1 $0.03 $0.12
I3 ibm/granite-3.0-3b-a800m-instruct logo ibm/granite-3.0-3b-a800m-instruct LLM 0 — —
I3 ibm/granite-3.0-8b-instruct logo ibm/granite-3.0-8b-instruct LLM 0 — —
I3 ibm/granite-34b-code-instruct logo ibm/granite-34b-code-instruct LLM 0 — —
I8 ibm/granite-8b-code-instruct logo ibm/granite-8b-code-instruct LLM 0 — —
I3 inclusionai/ling-3.0-flash-sante logo inclusionai/ling-3.0-flash-sante LLM 1 $0.075 $0.22
I3 inclusionai/ling-3.1-flash logo inclusionai/ling-3.1-flash LLM 0 — —
IB intfloat/e5-base-v2 LLM 0 — —
IL intfloat/e5-large-v2 LLM 0 — —
IE intfloat/multilingual-e5-large LLM 0 — —
IE intfloat/multilingual-e5-large-instruct LLM 0 — —
IA inworld-ai/realtime-tts-1.5-max logo inworld-ai/realtime-tts-1.5-max Speech 0 — —
IA inworld-ai/realtime-tts-1.5-mini logo inworld-ai/realtime-tts-1.5-mini Speech 0 — —
IA inworld-ai/realtime-tts-2 logo inworld-ai/realtime-tts-2 Speech 0 — —
ML meta-llama/Llama-3.3-70B-Instruct-Turbo logo meta-llama/Llama-3.3-70B-Instruct-Turbo LLM 1 $0.1 $0.32
ML meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo logo meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo LLM 1 $0.4 $0.4
ML meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo logo meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo LLM 1 $0.02 $0.04
ML meta-llama/llama-4-maverick-17b-128e-instruct-fp8 logo meta-llama/llama-4-maverick-17b-128e-instruct-fp8 LLM 1 $0.27 $0.85
M7 meta/codellama-70b logo meta/codellama-70b LLM 0 — —
M3 meta/llama-3.2-11b-vision-instruct logo meta/llama-3.2-11b-vision-instruct LLM 0 — —
M3 meta/llama-3.2-90b-vision-instruct logo meta/llama-3.2-90b-vision-instruct LLM 0 — —
M7 meta/llama2-70b logo meta/llama2-70b LLM 0 — —
M2 microsoft/kosmos-2 logo microsoft/kosmos-2 LLM 0 — —
M3 microsoft/phi-3-vision-128k-instruct logo microsoft/phi-3-vision-128k-instruct LLM 0 — —
M3 microsoft/phi-3.5-moe-instruct logo microsoft/phi-3.5-moe-instruct LLM 0 — —
MV mimo-v2.5-asr logo mimo-v2.5-asr Transcription 0 — —
MV mimo-v2.5-tts logo mimo-v2.5-tts Speech 0 — —
MV mimo-v2.5-tts-voiceclone logo mimo-v2.5-tts-voiceclone Speech 0 — —
MV mimo-v2.5-tts-voicedesign logo mimo-v2.5-tts-voicedesign Speech 0 — —
MV mindai/macaron-v1-tall LLM 1 $0.2475 $1.43
MV mindai/macaron-v1-venti LLM 1 $0.825 $2.475
MI ming-image-0.1-design Image 1 $1 $1
MI ming-image-0.1-design-layer Image 1 $1 $1
MM minimax/minimax-m2.5-highspeed logo minimax/minimax-m2.5-highspeed LLM 0 — —
MM minimax/minimax-m2.7-highspeed logo minimax/minimax-m2.7-highspeed LLM 1 $0.6 $2.4
MM minimaxai/minimax-m1-80k logo minimaxai/minimax-m1-80k LLM 1 $0.55 $2.2
MN mistralai/Mistral-Nemo-Instruct-2407 logo mistralai/Mistral-Nemo-Instruct-2407 LLM 1 $0.029 $0.03
MM mistralai/Voxtral-Mini-3B-2507 logo mistralai/Voxtral-Mini-3B-2507 LLM 0 — —
M2 mistralai/codestral-22b-instruct-v0.1 logo mistralai/codestral-22b-instruct-v0.1 LLM 0 — —
M7 mistralai/mistral-7b-instruct-v0.3 logo mistralai/mistral-7b-instruct-v0.3 LLM 0 — —
ML mistralai/mistral-large-2-instruct logo mistralai/mistral-large-2-instruct LLM 0 — —
M8 mistralai/mixtral-8x22b-v0.1 logo mistralai/mixtral-8x22b-v0.1 LLM 0 — —
MK moonshotai/Kimi-K3 logo moonshotai/Kimi-K3 LLM 2 $2.85 $14.25
MK moonshotai/kimi-k2-instruct logo moonshotai/kimi-k2-instruct LLM 1 $0.57 $2.3
N2 nousresearch/hermes-2-pro-llama-3-8b logo nousresearch/hermes-2-pro-llama-3-8b LLM 1 $0.14 $0.14
NM nv-mistralai/mistral-nemo-12b-instruct logo nv-mistralai/mistral-nemo-12b-instruct LLM 0 — —
NN nvidia/NVIDIA-Nemotron-3-Super-120B-A12B logo nvidia/NVIDIA-Nemotron-3-Super-120B-A12B LLM 1 $0.085 $0.4
NN nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B logo nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B LLM 1 $0.5 $2.2
NN nvidia/NVIDIA-Nemotron-3.5-Lightning logo nvidia/NVIDIA-Nemotron-3.5-Lightning LLM 1 $0.06 $0.16
N3 nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b logo nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b LLM 0 — —
NC nvidia/Nemotron-Content-Safety-3.5 logo nvidia/Nemotron-Content-Safety-3.5 LLM 1 $0.2 $0.2
NS nvidia/ai-synthetic-video-detector logo nvidia/ai-synthetic-video-detector Video 0 — —
NR nvidia/cosmos-reason2-8b logo nvidia/cosmos-reason2-8b LLM 0 — —
NQ nvidia/embed-qa-4 logo nvidia/embed-qa-4 Embeddings 0 — —
NC nvidia/ising-calibration-1.5-31b logo nvidia/ising-calibration-1.5-31b LLM 0 — —
N3 nvidia/llama-3.1-nemoguard-8b-content-safety logo nvidia/llama-3.1-nemoguard-8b-content-safety LLM 0 — —
N3 nvidia/llama-3.1-nemoguard-8b-topic-control logo nvidia/llama-3.1-nemoguard-8b-topic-control LLM 0 — —
N3 nvidia/llama-3.1-nemotron-51b-instruct logo nvidia/llama-3.1-nemotron-51b-instruct LLM 0 — —
N3 nvidia/llama-3.1-nemotron-70b-instruct logo nvidia/llama-3.1-nemotron-70b-instruct LLM 0 — —
N3 nvidia/llama-3.1-nemotron-safety-guard-8b-v3 logo nvidia/llama-3.1-nemotron-safety-guard-8b-v3 LLM 0 — —
N3 nvidia/llama-3.1-nemotron-ultra-253b-v1 logo nvidia/llama-3.1-nemotron-ultra-253b-v1 LLM 0 — —
N3 nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1 logo nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1 Embeddings 0 — —
N3 nvidia/llama-3.2-nv-embedqa-1b-v1 logo nvidia/llama-3.2-nv-embedqa-1b-v1 Embeddings 0 — —
NN nvidia/llama-nemotron-embed-vl-1b-v2 logo nvidia/llama-nemotron-embed-vl-1b-v2 Embeddings 0 — —
NC nvidia/llama3-chatqa-1.5-70b logo nvidia/llama3-chatqa-1.5-70b LLM 0 — —
NN nvidia/mistral-nemo-minitron-8b-8k-instruct logo nvidia/mistral-nemo-minitron-8b-8k-instruct LLM 0 — —
N3 nvidia/nemotron-3-embed-1b logo nvidia/nemotron-3-embed-1b Embeddings 0 — —
N3 nvidia/nemotron-3-nano-omni-30b-a3b-reasoning logo nvidia/nemotron-3-nano-omni-30b-a3b-reasoning LLM 0 — —
N3 nvidia/nemotron-3-super-120b-a12b logo nvidia/nemotron-3-super-120b-a12b LLM 0 — —
N3 nvidia/nemotron-3-ultra-550b-a55b logo nvidia/nemotron-3-ultra-550b-a55b LLM 0 — —
N3 nvidia/nemotron-3.5-content-safety logo nvidia/nemotron-3.5-content-safety LLM 0 — —
N3 nvidia/nemotron-3.5-lightning-30b-a3b logo nvidia/nemotron-3.5-lightning-30b-a3b LLM 0 — —
N4 nvidia/nemotron-4-340b-instruct logo nvidia/nemotron-4-340b-instruct LLM 0 — —
N4 nvidia/nemotron-4-340b-reward logo nvidia/nemotron-4-340b-reward LLM 0 — —
NN nvidia/nemotron-nano-3-30b-a3b logo nvidia/nemotron-nano-3-30b-a3b LLM 0 — —
NP nvidia/nemotron-parse logo nvidia/nemotron-parse LLM 0 — —
NP nvidia/nemotron-parse-2.0 logo nvidia/nemotron-parse-2.0 LLM 0 — —
N2 nvidia/neva-22b logo nvidia/neva-22b LLM 0 — —
NE nvidia/nv-embedqa-mistral-7b-v2 logo nvidia/nv-embedqa-mistral-7b-v2 Embeddings 0 — —
N nvidia/nvclip logo nvidia/nvclip LLM 0 — —
NT nvidia/riva-translate-4b-instruct logo nvidia/riva-translate-4b-instruct LLM 0 — —
NT nvidia/riva-translate-4b-instruct-v1.1 logo nvidia/riva-translate-4b-instruct-v1.1 LLM 0 — —
NT nvidia/riva-translate-4b-instruct-v2 logo nvidia/riva-translate-4b-instruct-v2 LLM 0 — —
N nvidia/vila logo nvidia/vila LLM 0 — —
OO openai/gpt-oss-120b-Turbo logo openai/gpt-oss-120b-Turbo LLM 1 $0.15 $0.6
OO openai/gpt-oss-120b-Ultra logo openai/gpt-oss-120b-Ultra LLM 1 $0.2 $0.95
OL openai/whisper-large-v3 logo openai/whisper-large-v3 Transcription 0 — —
OL openai/whisper-large-v3-turbo logo openai/whisper-large-v3-turbo Transcription 0 — —
PV paddlepaddle/paddleocr-vl logo paddlepaddle/paddleocr-vl LLM 1 $0.02 $0.02
PX poolside/laguna-xs-2.1 logo poolside/laguna-xs-2.1 LLM 0 — —
QM qwen/qwen-mt-plus logo qwen/qwen-mt-plus LLM 1 $0.25 $0.75
Q2 qwen/qwen3-235b-a22b-fp8 logo qwen/qwen3-235b-a22b-fp8 LLM 0 — —
QC qwen/qwen3-coder-480b-a35b-instruct logo qwen/qwen3-coder-480b-a35b-instruct LLM 0 — —
QO qwen/qwen3-omni-30b-a3b-instruct logo qwen/qwen3-omni-30b-a3b-instruct LLM 0 — —
QO qwen/qwen3-omni-30b-a3b-thinking logo qwen/qwen3-omni-30b-a3b-thinking LLM 1 $0.25 $0.97
Q5 qwen/qwen3.5-plus logo qwen/qwen3.5-plus LLM 0 — —
S7 sao10k/l3-70b-euryale-v2.1 LLM 1 $1.48 $1.48
S8 sao10k/l3-8b-lunaris LLM 0 — —
ST sentence-transformers/all-MiniLM-L12-v2 logo sentence-transformers/all-MiniLM-L12-v2 LLM 0 — —
ST sentence-transformers/all-MiniLM-L6-v2 logo sentence-transformers/all-MiniLM-L6-v2 LLM 0 — —
ST sentence-transformers/all-mpnet-base-v2 logo sentence-transformers/all-mpnet-base-v2 LLM 0 — —
ST sentence-transformers/clip-ViT-B-32 logo sentence-transformers/clip-ViT-B-32 LLM 0 — —
ST sentence-transformers/clip-ViT-B-32-multilingual-v1 logo sentence-transformers/clip-ViT-B-32-multilingual-v1 LLM 0 — —
ST sentence-transformers/multi-qa-mpnet-base-dot-v1 logo sentence-transformers/multi-qa-mpnet-base-dot-v1 LLM 0 — —
ST sentence-transformers/paraphrase-MiniLM-L6-v2 logo sentence-transformers/paraphrase-MiniLM-L6-v2 LLM 0 — —
S1 sesame/csm-1b logo sesame/csm-1b LLM 0 — —
SB shibing624/text2vec-base-chinese LLM 0 — —
SE snowflake/arctic-embed-l logo snowflake/arctic-embed-l Embeddings 0 — —
ST stabilityai/sdxl-turbo logo stabilityai/sdxl-turbo LLM 0 — —
TB thenlper/gte-base LLM 0 — —
TL thenlper/gte-large LLM 0 — —
T thinkingmachines/Inkling logo thinkingmachines/Inkling Video 1 $0.95 $4.05
TS thinkingmachines/Inkling-Small logo thinkingmachines/Inkling-Small Video 1 $0.45 $1.2
T4 thudm/glm-4-32b-0414 logo thudm/glm-4-32b-0414 LLM 0 — —
WC writer/palmyra-creative-122b logo writer/palmyra-creative-122b LLM 0 — —
WF writer/palmyra-fin-70b-32k logo writer/palmyra-fin-70b-32k LLM 0 — —
WM writer/palmyra-med-70b logo writer/palmyra-med-70b LLM 0 — —
WM writer/palmyra-med-70b-32k logo writer/palmyra-med-70b-32k LLM 0 — —
ZA z-ai/glm-5.3 logo z-ai/glm-5.3 LLM 0 — —
ZA z-ai/glm-5.3-flash logo z-ai/glm-5.3-flash LLM 0 — —
ZO zai-org/GLM-5.3 logo zai-org/GLM-5.3 LLM 2 $0.9 $4
ZO zai-org/GLM-5.3-Flash logo zai-org/GLM-5.3-Flash LLM 2 $0.15 $0.5
ZO zai-org/autoglm-phone-9b-multilingual logo zai-org/autoglm-phone-9b-multilingual LLM 1 $0.035 $0.138
ZO zai-org/glm-4.7-h logo zai-org/glm-4.7-h LLM 1 $0.6 $2.2
ZO zai-org/glm-5.3-p logo zai-org/glm-5.3-p LLM 1 $1.4 $4.4
Z7 zyphra/zamba2-7b-instruct logo zyphra/zamba2-7b-instruct LLM 0 — —

Frequently asked questions

How are AI model prices collected?

Prices are pulled straight from each provider's public API during the nightly sync and stored as USD per 1M tokens — the same rates your API key would pay. Nothing is entered by hand, and the "last checked" column shows when a provider's data was last verified.

Why does the same model cost different amounts across providers?

One model is often served by several inference providers that run it on their own GPU fleet. Each sets its own input and output rates, so the same model can differ several times over in price — that spread is exactly what this catalog tracks.

What does "best input price" mean?

It is the lowest available input price for the model across all providers that currently serve it and publish a price. The model page lists every provider side by side, including their output rates.

How often is the catalog updated?

The catalog syncs nightly and the "last checked" column on every row shows the exact time a provider's prices were last fetched.