Pricing
Explore pricing for our Model APIs and GPU resources. Find the right plan to match your needs with transparent rates and flexible options.
Explore pricing for our Model APIs and GPU resources. Find the right plan to match your needs with transparent rates and flexible options.
Explore pricing for our Model APIs and GPU resources. Find the right plan to match your needs with transparent rates and flexible options.
Advanced AI models from DeepSeek, offering cutting-edge reasoning capabilities and competitive pricing for enterprise and research applications.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
deepseek/deepseek-v3-0324 | 163,840 | $0.28 /M Tokens | $1.14 /M Tokens | More |
deepseek/deepseek-r1-0528 | 163,840 | $0.7 /M Tokens | $2.5 /M Tokens | More |
deepseek/deepseek-r1-0528-qwen3-8b | 128,000 | $0.06 /M Tokens | $0.09 /M Tokens | More |
deepseek/deepseek-v3-turbo | 64,000 | $0.4 /M Tokens | $1.3 /M Tokens | More |
deepseek/deepseek-r1-turbo | 64,000 | $0.7 /M Tokens | $2.5 /M Tokens | More |
deepseek/deepseek-prover-v2-671b | 160,000 | $0.7 /M Tokens | $2.5 /M Tokens | More |
deepseek/deepseek-r1-distill-llama-8b | 32,000 | $0.04 /M Tokens | $0.04 /M Tokens | More |
deepseek/deepseek-r1-distill-qwen-14b | 64,000 | $0.15 /M Tokens | $0.15 /M Tokens | More |
deepseek/deepseek-r1-distill-qwen-32b | 64,000 | $0.3 /M Tokens | $0.3 /M Tokens | More |
deepseek/deepseek-r1-distill-llama-70b | 32,000 | $0.8 /M Tokens | $0.8 /M Tokens | More |
Meta's Llama models providing state-of-the-art language understanding with open architecture designed for diverse applications.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | 1,048,576 | $0.17 /M Tokens | $0.85 /M Tokens | More |
meta-llama/llama-4-scout-17b-16e-instruct | 131,072 | $0.1 /M Tokens | $0.5 /M Tokens | More |
meta-llama/llama-3.1-8b-instruct | 16,384 | $0.02 /M Tokens | $0.05 /M Tokens | More |
meta-llama/llama-3.3-70b-instruct | 131,072 | $0.13 /M Tokens | $0.39 /M Tokens | More |
meta-llama/llama-3-8b-instruct | 8,192 | $0.04 /M Tokens | $0.04 /M Tokens | More |
meta-llama/llama-3-70b-instruct | 8,192 | $0.51 /M Tokens | $0.74 /M Tokens | More |
meta-llama/llama-3.2-1b-instruct | 131,000 | Free | Free | More |
meta-llama/llama-3.2-3b-instruct | 32,768 | $0.03 /M Tokens | $0.05 /M Tokens | More |
Qwen series models offering efficient language processing with various parameter sizes, from lightweight to enterprise-grade solutions.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
qwen/qwen3-coder-480b-a35b-instruct | 262,144 | $0.64 /M Tokens | $2.5 /M Tokens | More |
qwen/qwen3-235b-a22b-thinking-2507 | 131,072 | $0.3 /M Tokens | $3 /M Tokens | More |
qwen/qwen3-235b-a22b-instruct-2507 | 262,144 | $0.15 /M Tokens | $0.8 /M Tokens | More |
qwen/qwen3-30b-a3b-fp8 | 40,960 | $0.1 /M Tokens | $0.45 /M Tokens | More |
qwen/qwen3-32b-fp8 | 40,960 | $0.1 /M Tokens | $0.45 /M Tokens | More |
qwen/qwen2.5-vl-72b-instruct | 32,768 | $0.8 /M Tokens | $0.8 /M Tokens | More |
qwen/qwen3-235b-a22b-fp8 | 40,960 | $0.2 /M Tokens | $0.8 /M Tokens | More |
qwen/qwen-2.5-72b-instruct | 32,000 | $0.38 /M Tokens | $0.4 /M Tokens | More |
qwen/qwen3-8b-fp8 | 128,000 | $0.035 /M Tokens | $0.138 /M Tokens | More |
qwen/qwen3-4b-fp8 | 128,000 | Free | Free | More |
qwen/qwen2.5-7b-instruct | 32,000 | $0.07 /M Tokens | $0.07 /M Tokens | More |
Baidu's ERNIE models providing advanced Chinese language understanding and multimodal capabilities, optimized for Chinese applications with competitive pricing.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
baidu/ernie-4.5-vl-424b-a47b | 123,000 | $0.42 /M Tokens | $1.25 /M Tokens | More |
baidu/ernie-4.5-300b-a47b-paddle | 123,000 | $0.28 /M Tokens | $1.1 /M Tokens | More |
baidu/ernie-4.5-vl-28b-a3b | 30,000 | $0.14 /M Tokens | $0.56 /M Tokens | More |
baidu/ernie-4.5-21B-a3b | 120,000 | $0.07 /M Tokens | $0.28 /M Tokens | More |
baidu/ernie-4.5-0.3b | 120,000 | Free | Free | More |
Google's Gemma models offering high-quality language processing with excellent performance for various NLP tasks.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
google/gemma-3-27b-it | 32,000 | $0.119 /M Tokens | $0.2 /M Tokens | More |
google/gemma-3-1b-it | 32,768 | Free | Free | More |
GLM series models from Tsinghua University, featuring advanced Chinese language understanding and generation capabilities.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
zai-org/glm-4.5v | 65,536 | $0.6 /M Tokens | $1.8 /M Tokens | More |
zai-org/glm-4.5 | 131,072 | $0.6 /M Tokens | $2.2 /M Tokens | More |
thudm/glm-4.1v-9b-thinking | 65,536 | $0.035 /M Tokens | $0.138 /M Tokens | More |
thudm/glm-4-32b-0414 | 32,000 | $0.24 /M Tokens | $0.24 /M Tokens | More |
Specialized fine-tuned models optimized for creative and roleplay applications with enhanced storytelling capabilities.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
Sao10K/L3-8B-Stheno-v3.2 | 8,192 | $0.05 /M Tokens | $0.05 /M Tokens | More |
sao10k/l3-70b-euryale-v2.1 | 8,192 | $1.48 /M Tokens | $1.48 /M Tokens | More |
sao10k/l3-8b-lunaris | 8,192 | $0.05 /M Tokens | $0.05 /M Tokens | More |
sao10k/l31-70b-euryale-v2.2 | 8,192 | $1.48 /M Tokens | $1.48 /M Tokens | More |
Efficient and powerful language models from Mistral AI, designed for both commercial and open-source applications.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
mistralai/mistral-nemo | 60,288 | $0.04 /M Tokens | $0.17 /M Tokens | More |
mistralai/mistral-7b-instruct | 32,768 | $0.029 /M Tokens | $0.059 /M Tokens | More |
Research-focused AI models designed for advanced reasoning and enhanced instruction following capabilities.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
nousresearch/hermes-2-pro-llama-3-8b | 8,192 | $0.14 /M Tokens | $0.14 /M Tokens | More |
Specialized AI models focused on advanced cognitive tasks and complex reasoning applications.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
cognitivecomputations/dolphin-mixtral-8x22b | 16,000 | $0.9 /M Tokens | $0.9 /M Tokens | More |
Fine-tuned models designed for enhanced emotional intelligence and nuanced conversational capabilities.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
sophosympatheia/midnight-rose-70b | 4,096 | $0.8 /M Tokens | $0.8 /M Tokens | More |
Innovative AI models from Gryphe, delivering specialized language understanding with a focus on efficiency and adaptability for niche applications.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
gryphe/mythomax-l2-13b | 4,096 | $0.09 /M Tokens | $0.09 /M Tokens | More |
Minimax AI's advanced language models delivering robust conversational AI capabilities with optimized performance for customer service, content generation, and creative applications, featuring strong multilingual support and enterprise-ready scalability.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
minimaxai/minimax-m1-80k | 1,000,000 | $0.55 /M Tokens | $2.2 /M Tokens | More |
Microsoft’s models deliver state-of-the-art multilingual capabilities with enterprise-grade security, seamlessly integrated into the Azure cloud ecosystem. Optimized for cross-platform collaboration and business intelligence, these models excel in document understanding and generation—key strengths for Microsoft 365 workflows.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
microsoft/wizardlm-2-8x22b | 65,535 | $0.62 /M Tokens | $0.62 /M Tokens | More |
Premium collection of state-of-the-art AI models featuring advanced reasoning, mathematical proof capabilities, and cutting-edge language understanding across multiple domains.
Model Name | Context | Input | Output | Actions |
---|---|---|---|---|
deepseek/deepseek-v3-0324 | 163,840 | $0.28 /M Tokens | $1.14 /M Tokens | More |
zai-org/glm-4.5v | 65,536 | $0.6 /M Tokens | $1.8 /M Tokens | More |
openai/gpt-oss-120b | 131,072 | $0.1 /M Tokens | $0.5 /M Tokens | More |
openai/gpt-oss-20b | 131,072 | $0.05 /M Tokens | $0.2 /M Tokens | More |
zai-org/glm-4.5 | 131,072 | $0.6 /M Tokens | $2.2 /M Tokens | More |
qwen/qwen3-235b-a22b-thinking-2507 | 131,072 | $0.3 /M Tokens | $3 /M Tokens | More |
moonshotai/kimi-k2-instruct | 131,072 | $0.57 /M Tokens | $2.3 /M Tokens | More |
deepseek/deepseek-r1-0528 | 163,840 | $0.7 /M Tokens | $2.5 /M Tokens | More |
baidu/ernie-4.5-vl-424b-a47b | 123,000 | $0.42 /M Tokens | $1.25 /M Tokens | More |
baidu/ernie-4.5-300b-a47b-paddle | 123,000 | $0.28 /M Tokens | $1.1 /M Tokens | More |
qwen/qwen3-30b-a3b-fp8 | 40,960 | $0.1 /M Tokens | $0.45 /M Tokens | More |
minimaxai/minimax-m1-80k | 1,000,000 | $0.55 /M Tokens | $2.2 /M Tokens | More |
qwen/qwen3-32b-fp8 | 40,960 | $0.1 /M Tokens | $0.45 /M Tokens | More |
qwen/qwen3-235b-a22b-fp8 | 40,960 | $0.2 /M Tokens | $0.8 /M Tokens | More |
deepseek/deepseek-v3-turbo | 64,000 | $0.4 /M Tokens | $1.3 /M Tokens | More |
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | 1,048,576 | $0.17 /M Tokens | $0.85 /M Tokens | More |
deepseek/deepseek-r1-turbo | 64,000 | $0.7 /M Tokens | $2.5 /M Tokens | More |
deepseek/deepseek-prover-v2-671b | 160,000 | $0.7 /M Tokens | $2.5 /M Tokens | More |
meta-llama/llama-4-scout-17b-16e-instruct | 131,072 | $0.1 /M Tokens | $0.5 /M Tokens | More |
baidu/ernie-4.5-vl-28b-a3b | 30,000 | $0.14 /M Tokens | $0.56 /M Tokens | More |
baidu/ernie-4.5-21B-a3b | 120,000 | $0.07 /M Tokens | $0.28 /M Tokens | More |
baidu/ernie-4.5-0.3b | 120,000 | Free | Free | More |
Pricing may vary based on image dimensions, inference steps, and upscaling factors. Use thePricing Calculatorfor an estimate.
API Name | Width&Height | Steps/Scale | Pricing |
---|---|---|---|
Text to Image | 512*512 | 5 | $0.001 /image |
Image to Image | 512*512 | 5 | $0.001 /image |
Remove Background | - | - | $0.017 /image |
Replace Background | - | - | $0.0255 /image |
Inpainting | 512*512 | 5 | $0.0015 /image |
Remove Text | - | - | $0.017 /image |
Cleanup | - | - | $0.017 /image |
Merge Face | - | - | $0.0255 /image |
API Name | Width&Height | Pricing |
---|---|---|
Seedream 3.0 Text to Image | - | $0.03 /image |
Qwen-Image Text to Image | - | $0.02 /image |
Pricing may vary based on the number of frames, chosen model, and inference steps. Use thePricing Calculatorfor an estimate.
API Name | Total Frames | Steps | Pricing |
---|---|---|---|
Text to Video | 32 | 20 | $0.0307 /video |
API Name | Mode | Duration | Resolution | Pricing |
---|---|---|---|---|
Kling V1.6 Text to Video | Standard | 5s | 720P | $0.27 /video |
Standard | 10s | 720P | $0.54 /video | |
Kling V1.6 Image to Video | Standard | 5s | 720P | $0.27 /video |
Standard | 10s | 720P | $0.54 /video | |
Professional | 5s | 1080P | $0.46 /video | |
Professional | 10s | 1080P | $0.92 /video | |
MiniMax Video 01 | - | 6s | 720P | $0.40 /video |
MiniMax Video 02 | - | 6s | 768P | $0.25 /video |
- | 10s | 768P | $0.50 /video | |
- | 6s | 1080P | $0.44 /video | |
Hunyuan Video Fast | - | 5s | 1280*720 | 720*1280 | $0.30 /video |
Wan 2.1 Text to Video | - | 5s | 1280*720 | 720*1280 | $0.30 /video |
- | 5s | 832*480 | 480*832 | $0.20 /video | |
fast_mode | 5s | 1280*720 | 720*1280 | $0.225 /video | |
fast_mode | 5s | 832*480 | 480*832 | $0.125 /video | |
Wan 2.1 Image to Video | - | 5s | 1280*720 | 720*1280 | $0.30 /video |
- | 5s | 832*480 | 480*832 | $0.20 /video | |
fast_mode | 5s | 1280*720 | 720*1280 | $0.225 /video | |
fast_mode | 5s | 832*480 | 480*832 | $0.125 /video | |
Wan 2.2 Text to Video | - | 5s | 480P | $0.09 /video |
- | 5s | 1080p | $0.40 /video | |
Wan 2.2 Image to Video | - | 5s | 480P | $0.09 /video |
- | 5s | 1080P | $0.40 /video | |
Vidu Q1 Text to Video | general style | 5s | 1080P | $0.36 /video |
anime style | 5s | 1080P | $0.36 /video | |
Vidu Q1 Image to Video | - | 5s | 1080P | $0.36 /video |
Vidu Q1 Start End to Video | - | 5s | 1080P | $0.36 /video |
Vidu Q1 Reference to Video | - | 5s | 1080P | $0.36 /video |
Vidu 2.0 Image to Video | - | 4s | 360P | $0.09 /video |
- | 4s | 720P | $0.18 /video | |
- | 4s | 1080P | $0.27 /video | |
- | 8s | 720P | $0.27 /video | |
Vidu 2.0 Reference to Video | - | 4s | 360P | $0.09 /video |
- | 4s | 720P | $0.18 /video | |
Vidu 2.0 Start End to Video | - | 4s | 360P | $0.09 /video |
- | 4s | 720P | $0.18 /video | |
- | 4s | 1080P | $0.27 /video | |
- | 8s | 720P | $0.27 /video |
API Name | Model | Steps | Pricing |
---|---|---|---|
Image to Video | SVD-XT | 20 | $0.024 /video |
SVD | 20 | $0.0134 /video |
API Name | Mode | Pricing |
---|---|---|
Text to Speech | - | $15 /1M characters |
MiniMax speech-02-hd | T2A / T2A Async | $80 /1M characters |
MiniMax speech-02-turbo | T2A / T2A Async | $48 /1M characters |
MiniMax Voice-Cloning | - | $2.4 /voice |