# All Pricing

<table data-full-width="true"><thead><tr><th>Provider</th><th width="237">Model</th><th>Category</th><th>Price/Input [USD]</th><th>Price/Output [USD]</th></tr></thead><tbody><tr><td>Anthropic</td><td>Claude-3-5-Haiku</td><td>chat</td><td>0.8</td><td>4.0</td></tr><tr><td>AWS Bedrock</td><td>Command-r-plus</td><td>chat</td><td>18.0</td><td>18.0</td></tr><tr><td>AWS Bedrock</td><td>Llama-3-70b-Chat</td><td>chat</td><td>6.15</td><td>6.15</td></tr><tr><td>AWS Bedrock</td><td>Llama-3-8b-Chat</td><td>chat</td><td>0.9</td><td>0.9</td></tr><tr><td>AWS Bedrock</td><td>Mistral-7b-Instruct-v0.2</td><td>chat</td><td>0.35</td><td>0.35</td></tr><tr><td>AWS Bedrock</td><td>Nova-Micro-v1</td><td>chat</td><td>0.035</td><td>0.14</td></tr><tr><td>Deepinfra</td><td>Gemma-2-27b-it</td><td>chat</td><td>0.27</td><td>0.27</td></tr><tr><td>Deepinfra</td><td>Gemma-2-9b-it</td><td>chat</td><td>0.03</td><td>0.06</td></tr><tr><td>Deepinfra</td><td>Hermes-3-Llama-3.1-405B</td><td>chat</td><td>0.9</td><td>0.9</td></tr><tr><td>Deepinfra</td><td>L3-70B-Euryale-v2.1</td><td>chat</td><td>0.35</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>L3-8B-Lunaris-v1</td><td>chat</td><td>0.03</td><td>0.06</td></tr><tr><td>Deepinfra</td><td>L3.1-70B-Euryale-v2.2</td><td>chat</td><td>0.35</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Llama-3-70B-Instruct</td><td>chat</td><td>0.23</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Llama-3-8B-Instruct</td><td>chat</td><td>0.03</td><td>0.06</td></tr><tr><td>Deepinfra</td><td>Llama-3.1-8B-Instruct</td><td>chat</td><td>0.03</td><td>0.05</td></tr><tr><td>Deepinfra</td><td>Llama-3.1-8B-Instruct-Turbo</td><td>chat</td><td>0.02</td><td>0.05</td></tr><tr><td>Deepinfra</td><td>Llama-3.1-Nemotron-70B-Instruct</td><td>chat</td><td>0.23</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Llama-3.2-11B-Vision-Instruct</td><td>chat</td><td>0.055</td><td>0.055</td></tr><tr><td>Deepinfra</td><td>Llama-3.2-1B-Instruct</td><td>chat</td><td>0.01</td><td>0.02</td></tr><tr><td>Deepinfra</td><td>Llama-3.2-3B-Instruct</td><td>chat</td><td>0.018</td><td>0.03</td></tr><tr><td>Deepinfra</td><td>Llama-3.2-90B-Vision-Instruct</td><td>chat</td><td>0.35</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Llama-3.3-70B-Instruct</td><td>chat</td><td>0.23</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Llama-3.3-70B-Instruct-Turbo</td><td>chat</td><td>0.13</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Lzlv_70b_fp16_hf</td><td>chat</td><td>0.35</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Meta-Llama-3.1-405B-Instruct</td><td>chat</td><td>0.9</td><td>0.9</td></tr><tr><td>Deepinfra</td><td>Meta-Llama-3.1-70B-Instruct</td><td>chat</td><td>0.23</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Meta-Llama-3.1-70B-Instruct-Turbo</td><td>chat</td><td>0.13</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Mistral-7b-Instruct-v0.3</td><td>chat</td><td>0.03</td><td>0.055</td></tr><tr><td>Deepinfra</td><td>Mixtral-8x7b-Instruct-v0.1</td><td>chat</td><td>0.24</td><td>0.24</td></tr><tr><td>Deepinfra</td><td>MythoMax-L2-13b</td><td>chat</td><td>0.08</td><td>0.08</td></tr><tr><td>Deepinfra</td><td>Nemo-Instruct-2407</td><td>chat</td><td>0.04</td><td>0.1</td></tr><tr><td>Deepinfra</td><td>Openchat_3.5</td><td>chat</td><td>0.055</td><td>0.055</td></tr><tr><td>Deepinfra</td><td>QwQ-32B-Preview</td><td>chat</td><td>0.15</td><td>0.6</td></tr><tr><td>Deepinfra</td><td>Qwen2.5-72B-Instruct</td><td>chat</td><td>0.23</td><td>0.4</td></tr><tr><td>Deepinfra</td><td>Qwen2.5-Coder-32B-Instruct</td><td>chat</td><td>0.08</td><td>0.18</td></tr><tr><td>Deepinfra</td><td>WizardLM-2-7B</td><td>chat</td><td>0.055</td><td>0.055</td></tr><tr><td>Deepinfra</td><td>WizardLM-2-8x22B</td><td>chat</td><td>0.5</td><td>0.5</td></tr><tr><td>Deepseek</td><td>Deepseek-R1</td><td>chat</td><td>0.55</td><td>2.19</td></tr><tr><td>Fireworks AI</td><td>Llama-3-70b-Chat</td><td>chat</td><td>1.8</td><td>1.8</td></tr><tr><td>Fireworks AI</td><td>Llama-3-8b-Chat</td><td>chat</td><td>0.4</td><td>0.4</td></tr><tr><td>Fireworks AI</td><td>Llama-3.1-405b-Chat</td><td>chat</td><td>6.0</td><td>6.0</td></tr><tr><td>Fireworks AI</td><td>Llama-3.1-8b-Chat</td><td>chat</td><td>0.4</td><td>0.4</td></tr><tr><td>Fireworks AI</td><td>Mixtral-8x22b-Instruct-v0.1</td><td>chat</td><td>2.4</td><td>2.4</td></tr><tr><td>Google</td><td>Gemma 2 27B</td><td>chat</td><td>0.65</td><td>0.65</td></tr><tr><td>Google</td><td>Gemma 2 9B</td><td>chat</td><td>0.004</td><td>0.004</td></tr><tr><td>Google</td><td>Gemma 3n 4B</td><td>chat</td><td>0.02</td><td>0.04</td></tr><tr><td>Groq</td><td>Llama-3-70b-Chat</td><td>chat</td><td>1.38</td><td>1.38</td></tr><tr><td>Groq</td><td>Llama-3-8b-Chat</td><td>chat</td><td>0.13</td><td>0.13</td></tr><tr><td>Lepton AI</td><td>Llama-3-70b-Chat</td><td>chat</td><td>1.6</td><td>1.6</td></tr><tr><td>Lepton AI</td><td>Llama-3-8b-Chat</td><td>chat</td><td>0.14</td><td>0.14</td></tr><tr><td>Lepton AI</td><td>Mistral-7b-Instruct-v0.3</td><td>chat</td><td>8.0</td><td>0.14</td></tr><tr><td>Microsoft</td><td>MAI DS R1</td><td>chat</td><td>0.302</td><td>0.302</td></tr><tr><td>Microsoft</td><td>Phi 4</td><td>chat</td><td>0.06</td><td>0.14</td></tr><tr><td>Microsoft</td><td>Phi 4 Reasoning Plus</td><td>chat</td><td>0.07</td><td>0.35</td></tr><tr><td>Microsoft</td><td>Phi-3 Medium 128K Instruct</td><td>chat</td><td>1.0</td><td>1.0</td></tr><tr><td>Microsoft</td><td>Phi-3 Mini 128K Instruct</td><td>chat</td><td>0.1</td><td>0.1</td></tr><tr><td>Microsoft</td><td>Phi-3.5 Mini 128K Instruct</td><td>chat</td><td>0.1</td><td>0.1</td></tr><tr><td>Microsoft</td><td>WizardLM-2 8x22B</td><td>chat</td><td>0.48</td><td>0.48</td></tr><tr><td>Mistral AI</td><td>Mistral-7b-Instruct-v0.3</td><td>chat</td><td>0.5</td><td>0.5</td></tr><tr><td>Mistral AI</td><td>Mistral-small</td><td>chat</td><td>0.8</td><td>0.8</td></tr><tr><td>Mistral AI</td><td>Mixtral-8x22b-Instruct-v0.1</td><td>chat</td><td>0.14</td><td>0.14</td></tr><tr><td>Mistral AI</td><td>Mixtral-8x7b-Instruct-v0.1</td><td>chat</td><td>1.4</td><td>1.4</td></tr><tr><td>OpenAI</td><td>ChatGPT-4o-Latest</td><td>chat</td><td>5.0</td><td>15.0</td></tr><tr><td>OpenAI</td><td>GPT-3.5 Turbo 16k</td><td>chat</td><td>3.0</td><td>4.0</td></tr><tr><td>OpenAI</td><td>GPT-3.5-Turbo</td><td>chat</td><td>0.5</td><td>1.5</td></tr><tr><td>OpenAI</td><td>GPT-3.5-Turbo-0125</td><td>chat</td><td>0.5</td><td>1.5</td></tr><tr><td>OpenAI</td><td>GPT-3.5-Turbo-1106</td><td>chat</td><td>1.0</td><td>2.0</td></tr><tr><td>OpenAI</td><td>GPT-4</td><td>chat</td><td>30.0</td><td>60.0</td></tr><tr><td>OpenAI</td><td>GPT-4-0125-Preview</td><td>chat</td><td>10.0</td><td>30.0</td></tr><tr><td>OpenAI</td><td>GPT-4-1106-Preview</td><td>chat</td><td>10.0</td><td>30.0</td></tr><tr><td>OpenAI</td><td>GPT-4-Turbo-Preview</td><td>chat</td><td>10.0</td><td>30.0</td></tr><tr><td>OpenAI</td><td>GPT-4o Search Preview</td><td>chat</td><td>2.5</td><td>10.0</td></tr><tr><td>OpenAI</td><td>GPT-4o-mini Search Preview</td><td>chat</td><td>0.15</td><td>0.6</td></tr><tr><td>OpenAI</td><td>o1-Preview</td><td>chat</td><td>15.0</td><td>60.0</td></tr><tr><td>OpenAI</td><td>o1-Preview-2024-09-12</td><td>chat</td><td>15.0</td><td>60.0</td></tr><tr><td>OpenAI</td><td>o1-mini</td><td>chat</td><td>3.0</td><td>12.0</td></tr><tr><td>OpenAI</td><td>o1-mini-2024-09-12</td><td>chat</td><td>3.0</td><td>12.0</td></tr><tr><td>OpenAI</td><td>o3-mini</td><td>chat</td><td>1.1</td><td>4.4</td></tr><tr><td>Perplexity</td><td>Sonar-Pro</td><td>chat</td><td>0.3</td><td>1.5</td></tr><tr><td>Perplexity</td><td>Sonar-Reasoning-Pro</td><td>chat</td><td>0.2</td><td>0.8</td></tr><tr><td>Perplexity</td><td>Sonar-deep-research</td><td>chat</td><td>0.2</td><td>0.8</td></tr><tr><td>Replicate</td><td>Llama-3-70b-Chat</td><td>chat</td><td>3.4</td><td>3.4</td></tr><tr><td>Replicate</td><td>Llama-3-8b-Chat</td><td>chat</td><td>0.3</td><td>0.3</td></tr><tr><td>Together</td><td>DBRX-Instruct</td><td>chat</td><td>1.2</td><td>1.2</td></tr><tr><td>Together</td><td>Deepseek-v3</td><td>chat</td><td>1.25</td><td>1.25</td></tr><tr><td>Together</td><td>Gemma-2-27b-it</td><td>chat</td><td>0.8</td><td>0.8</td></tr><tr><td>Together</td><td>Gemma-2-9b-it</td><td>chat</td><td>0.3</td><td>0.3</td></tr><tr><td>Together</td><td>Gemma-2b-it</td><td>chat</td><td>0.1</td><td>0.1</td></tr><tr><td>Together</td><td>Llama-3-70B-Instruct-Lite</td><td>chat</td><td>0.54</td><td>0.54</td></tr><tr><td>Together</td><td>Llama-3-70B-Instruct-Turbo</td><td>chat</td><td>0.88</td><td>0.88</td></tr><tr><td>Together</td><td>Llama-3-70b-Chat</td><td>chat</td><td>0.88</td><td>0.88</td></tr><tr><td>Together</td><td>Llama-3-8B-Instruct-Lite</td><td>chat</td><td>0.1</td><td>0.1</td></tr><tr><td>Together</td><td>Llama-3-8B-Instruct-Turbo</td><td>chat</td><td>0.18</td><td>0.18</td></tr><tr><td>Together</td><td>Llama-3-8b-Chat</td><td>chat</td><td>0.2</td><td>0.2</td></tr><tr><td>Together</td><td>Llama-3.1-405B-Instruct-Turbo</td><td>chat</td><td>3.5</td><td>3.5</td></tr><tr><td>Together</td><td>Llama-3.1-70B-Instruct-Turbo</td><td>chat</td><td>0.88</td><td>0.88</td></tr><tr><td>Together</td><td>Llama-3.1-Nemotron-70B-Instruct-HF</td><td>chat</td><td>0.88</td><td>0.88</td></tr><tr><td>Together</td><td>Llama-3.2-3B-Instruct-Turbo</td><td>chat</td><td>0.06</td><td>0.06</td></tr><tr><td>Together</td><td>Llama-3.3-70B-Instruct-Turbo</td><td>chat</td><td>0.88</td><td>0.88</td></tr><tr><td>Together</td><td>Meta-Llama-3.1-8B-Instruct-Turbo</td><td>chat</td><td>0.18</td><td>0.18</td></tr><tr><td>Together</td><td>Mistral-7B-Instruct-v0.1</td><td>chat</td><td>0.2</td><td>0.2</td></tr><tr><td>Together</td><td>Mistral-7b-Instruct-v0.2</td><td>chat</td><td>0.2</td><td>0.2</td></tr><tr><td>Together</td><td>Mistral-7b-Instruct-v0.3</td><td>chat</td><td>0.2</td><td>0.2</td></tr><tr><td>Together</td><td>Mixtral-8x22b-Instruct-v0.1</td><td>chat</td><td>1.2</td><td>1.2</td></tr><tr><td>Together</td><td>Mixtral-8x7b-Instruct-v0.1</td><td>chat</td><td>0.6</td><td>0.6</td></tr><tr><td>Together</td><td>MythoMax-L2-13b</td><td>chat</td><td>0.3</td><td>0.3</td></tr><tr><td>Together</td><td>Nous-Hermes-2-Mixtral-8x7B-DPO</td><td>chat</td><td>0.6</td><td>0.6</td></tr><tr><td>Together</td><td>QwQ-32B-Preview</td><td>chat</td><td>1.2</td><td>1.2</td></tr><tr><td>Together</td><td>Qwen2-72B-Instruct</td><td>chat</td><td>0.9</td><td>0.9</td></tr><tr><td>Together</td><td>Qwen2.5-72B-Instruct-Turbo</td><td>chat</td><td>1.2</td><td>1.2</td></tr><tr><td>Together</td><td>Qwen2.5-7B-Instruct-Turbo</td><td>chat</td><td>0.3</td><td>0.3</td></tr><tr><td>Together</td><td>Qwen2.5-Coder-32B-Instruct</td><td>chat</td><td>0.8</td><td>0.8</td></tr><tr><td>Together</td><td>SOLAR-10.7B-Instruct-v1.0</td><td>chat</td><td>0.3</td><td>0.3</td></tr><tr><td>Together</td><td>WizardLM-2-8x22B</td><td>chat</td><td>1.2</td><td>1.2</td></tr><tr><td>X</td><td>Grok 2</td><td>chat</td><td>2.0</td><td>10.0</td></tr><tr><td>X</td><td>Grok 3</td><td>chat</td><td>3.0</td><td>15.0</td></tr><tr><td>X</td><td>Grok 3 Fast</td><td>chat</td><td>5.0</td><td>25.0</td></tr><tr><td>X</td><td>Grok 3 Mini</td><td>chat</td><td>0.3</td><td>0.5</td></tr><tr><td>X</td><td>Grok 3 Mini Fast</td><td>chat</td><td>0.6</td><td>4.0</td></tr><tr><td>cohere</td><td>Cohere</td><td>embedding</td><td>0.1</td><td>0.0</td></tr><tr><td>Google</td><td>Google</td><td>embedding</td><td>0.1</td><td>0.0</td></tr><tr><td>jina</td><td>Jina</td><td>embedding</td><td>0.018</td><td>0.0</td></tr><tr><td>Mistral AI</td><td>Mistral</td><td>embedding</td><td>0.1</td><td>0.0</td></tr><tr><td>OpenAI</td><td>text-embedding-3-large</td><td>embedding</td><td>0.13</td><td>0.0</td></tr><tr><td>OpenAI</td><td>text-embedding-3-small</td><td>embedding</td><td>0.02</td><td>0.0</td></tr><tr><td>OpenAI</td><td>text-embedding-ada-002</td><td>embedding</td><td>0.1</td><td>0.0</td></tr><tr><td>Amazon</td><td>titan-image-generator-v1_premium</td><td>image</td><td>0.012</td><td>0.012</td></tr><tr><td>Amazon</td><td>titan-image-generator-v1_premium</td><td>image</td><td>0.01</td><td>0.01</td></tr><tr><td>Amazon</td><td>titan-image-generator-v1_standard</td><td>image</td><td>0.01</td><td>0.01</td></tr><tr><td>Amazon</td><td>titan-image-generator-v1_standard</td><td>image</td><td>0.008</td><td>0.008</td></tr><tr><td>OpenAI</td><td>Dall-E-2</td><td>image</td><td>0.016</td><td>0.016</td></tr><tr><td>OpenAI</td><td>Dall-E-2</td><td>image</td><td>0.02</td><td>0.02</td></tr><tr><td>OpenAI</td><td>Dall-E-2</td><td>image</td><td>0.018</td><td>0.018</td></tr><tr><td>OpenAI</td><td>Dall-E-3</td><td>image</td><td>0.04</td><td>0.04</td></tr><tr><td>OpenAI</td><td>Dall-E-3</td><td>image</td><td>0.08</td><td>0.08</td></tr><tr><td>OpenAI</td><td>Dall-E-3</td><td>image</td><td>0.12</td><td>0.12</td></tr><tr><td>OpenAI</td><td>Dall-E-3</td><td>image</td><td>0.08</td><td>0.08</td></tr><tr><td>OpenAI</td><td>Dall-E-3</td><td>image</td><td>0.08</td><td>0.08</td></tr><tr><td>OpenAI</td><td>Dall-E-3</td><td>image</td><td>0.12</td><td>0.12</td></tr><tr><td>Replicate</td><td>anime-style</td><td>image</td><td>0.000225</td><td>0.000225</td></tr><tr><td>Replicate</td><td>anime-style</td><td>image</td><td>0.000225</td><td>0.000225</td></tr><tr><td>Replicate</td><td>anime-style</td><td>image</td><td>0.000225</td><td>0.000225</td></tr><tr><td>Replicate</td><td>classic</td><td>image</td><td>0.00115</td><td>0.00115</td></tr><tr><td>Replicate</td><td>classic</td><td>image</td><td>0.00115</td><td>0.00115</td></tr><tr><td>Replicate</td><td>classic</td><td>image</td><td>0.00115</td><td>0.00115</td></tr><tr><td>Replicate</td><td>vintedois-diffusion</td><td>image</td><td>0.000225</td><td>0.000225</td></tr><tr><td>Replicate</td><td>vintedois-diffusion</td><td>image</td><td>0.000225</td><td>0.000225</td></tr><tr><td>Replicate</td><td>vintedois-diffusion</td><td>image</td><td>0.000225</td><td>0.000225</td></tr><tr><td>Stability AI</td><td>stable-diffusion-v1-6</td><td>image</td><td>0.01</td><td>0.01</td></tr><tr><td>Stability AI</td><td>stable-diffusion-v1-6</td><td>image</td><td>0.01</td><td>0.01</td></tr><tr><td>Stability AI</td><td>stable-diffusion-xl-1024-v1-0</td><td>image</td><td>0.006</td><td>0.006</td></tr><tr><td>Amazon</td><td>Amazon</td><td>image embedding</td><td>0.06</td><td>0.06</td></tr><tr><td>Google</td><td>Google</td><td>image embedding</td><td>0.1</td><td>0.1</td></tr><tr><td>Anthropic</td><td>Claude-3-5-Sonnet</td><td>multimodal</td><td>3.0</td><td>15.0</td></tr><tr><td>Anthropic</td><td>Claude-3-7-Sonnet</td><td>multimodal</td><td>3.0</td><td>15.0</td></tr><tr><td>Anthropic</td><td>Claude-3-Haiku</td><td>multimodal</td><td>0.25</td><td>1.25</td></tr><tr><td>Anthropic</td><td>Claude-3-Opus</td><td>multimodal</td><td>15.0</td><td>75.0</td></tr><tr><td>Anthropic</td><td>Claude-3-Sonnet</td><td>multimodal</td><td>3.0</td><td>15.0</td></tr><tr><td>Anthropic</td><td>Claude-4-Opus</td><td>multimodal</td><td>15.0</td><td>75.0</td></tr><tr><td>Anthropic</td><td>Claude-4-Sonnet</td><td>multimodal</td><td>3.0</td><td>15.0</td></tr><tr><td>AWS Bedrock</td><td>Nova-Lite-v1</td><td>multimodal</td><td>0.06</td><td>0.24</td></tr><tr><td>AWS Bedrock</td><td>Nova-Pro-v1</td><td>multimodal</td><td>0.8</td><td>3.2</td></tr><tr><td>Google</td><td>Gemini 1.5 Pro</td><td>multimodal</td><td>1.25</td><td>5.0</td></tr><tr><td>Google</td><td>Gemini 2.0 Flash Lite</td><td>multimodal</td><td>0.075</td><td>0.3</td></tr><tr><td>Google</td><td>Gemini 2.5 Flash</td><td>multimodal</td><td>0.3</td><td>2.5</td></tr><tr><td>Google</td><td>Gemini 2.5 Flash Lite</td><td>multimodal</td><td>0.1</td><td>0.4</td></tr><tr><td>Google</td><td>Gemini 2.5 Flash Lite Preview 06-17</td><td>multimodal</td><td>0.1</td><td>0.4</td></tr><tr><td>Google</td><td>Gemini 2.5 Pro</td><td>multimodal</td><td>1.25</td><td>10.0</td></tr><tr><td>Google</td><td>Gemini 2.5 Pro Preview 05-06</td><td>multimodal</td><td>1.25</td><td>10.0</td></tr><tr><td>Google</td><td>Gemini 2.5 Pro Preview 06-05</td><td>multimodal</td><td>1.25</td><td>10.0</td></tr><tr><td>Google</td><td>Gemini-1.5-Flash</td><td>multimodal</td><td>token - 0.075 / token - 0.15</td><td>token - 0.3 / token - 0.6</td></tr><tr><td>Google</td><td>Gemini-1.5-Flash-8B</td><td>multimodal</td><td>token - 0.0375 / token - 0.075</td><td>token - 0.15 / token - 0.3</td></tr><tr><td>Google</td><td>Gemini-2.0-Flash</td><td>multimodal</td><td>0.1</td><td>0.4</td></tr><tr><td>Google</td><td>Gemini-2.5-Flash-Preview</td><td>multimodal</td><td>0.15</td><td>0.6</td></tr><tr><td>Google</td><td>Gemini-2.5-Flash-Preview-(thinking)</td><td>multimodal</td><td>0.15</td><td>3.5</td></tr><tr><td>Google</td><td>Gemini-2.5-Pro-Preview</td><td>multimodal</td><td>2.5</td><td>15.0</td></tr><tr><td>Google</td><td>Gemma 3 12B</td><td>multimodal</td><td>0.03</td><td>0.03</td></tr><tr><td>Google</td><td>Gemma 3 27B</td><td>multimodal</td><td>0.09</td><td>0.17</td></tr><tr><td>Google</td><td>Gemma 3 4B</td><td>multimodal</td><td>0.02</td><td>0.04</td></tr><tr><td>Microsoft</td><td>Phi 4 Multimodal Instruct</td><td>multimodal</td><td>0.05</td><td>0.1</td></tr><tr><td>OpenAI</td><td>GPT-4-Turbo</td><td>multimodal</td><td>10.0</td><td>30.0</td></tr><tr><td>OpenAI</td><td>GPT-4-Turbo-2024-04-09</td><td>multimodal</td><td>10.0</td><td>30.0</td></tr><tr><td>OpenAI</td><td>GPT-4.1</td><td>multimodal</td><td>2.0</td><td>8.0</td></tr><tr><td>OpenAI</td><td>GPT-4.1 mini</td><td>multimodal</td><td>0.4</td><td>1.6</td></tr><tr><td>OpenAI</td><td>GPT-4.1 nano</td><td>multimodal</td><td>0.1</td><td>0.4</td></tr><tr><td>OpenAI</td><td>GPT-4.5-Preview</td><td>multimodal</td><td>75.0</td><td>150.0</td></tr><tr><td>OpenAI</td><td>GPT-4o</td><td>multimodal</td><td>2.5</td><td>10.0</td></tr><tr><td>OpenAI</td><td>GPT-4o-2024-05-13</td><td>multimodal</td><td>5.0</td><td>15.0</td></tr><tr><td>OpenAI</td><td>GPT-4o-2024-08-06</td><td>multimodal</td><td>2.5</td><td>10.0</td></tr><tr><td>OpenAI</td><td>GPT-4o-2024-11-20</td><td>multimodal</td><td>2.5</td><td>10.0</td></tr><tr><td>OpenAI</td><td>GPT-4o-Audio-Preview</td><td>multimodal</td><td>audio - 100.0 / token - 2.5</td><td>audio - 200.0 / token - 10.0</td></tr><tr><td>OpenAI</td><td>GPT-4o-Audio-Preview-2024-12-17</td><td>multimodal</td><td>audio - 40.0 / token - 2.5</td><td>audio - 80.0 / token - 10.0</td></tr><tr><td>OpenAI</td><td>GPT-4o-Audio-preview-2024-10-01</td><td>multimodal</td><td>audio - 100.0 / token - 2.5</td><td>audio - 200.0 / token - 10.0</td></tr><tr><td>OpenAI</td><td>GPT-4o-mini</td><td>multimodal</td><td>0.15</td><td>0.6</td></tr><tr><td>OpenAI</td><td>GPT-4o-mini (2024-07-18)</td><td>multimodal</td><td>0.15</td><td>0.6</td></tr><tr><td>OpenAI</td><td>GPT-4o-mini-Audio-Preview</td><td>multimodal</td><td>audio - 10.0 / token - 0.15</td><td>audio - 20.0 / token - 0.6</td></tr><tr><td>OpenAI</td><td>GPT-4o-mini-Audio-Preview-2024-12-17</td><td>multimodal</td><td>audio - 10.0 / token - 0.15</td><td>audio - 20.0 / token - 0.6</td></tr><tr><td>OpenAI</td><td>o1</td><td>multimodal</td><td>15.0</td><td>60.0</td></tr><tr><td>OpenAI</td><td>o3</td><td>multimodal</td><td>10.0</td><td>40.0</td></tr><tr><td>OpenAI</td><td>o4-mini</td><td>multimodal</td><td>1.1</td><td>4.4</td></tr><tr><td>X</td><td>Grok 2 Vision</td><td>multimodal</td><td>2.0</td><td>10.0</td></tr><tr><td>X</td><td>Grok 4</td><td>multimodal</td><td>3.0</td><td>15.0</td></tr><tr><td>Amazon</td><td>Amazon</td><td>object detection</td><td>1.0</td><td>1.0</td></tr><tr><td>api4ai</td><td>api4ai</td><td>object detection</td><td>0.5</td><td>0.5</td></tr><tr><td>Clarifai</td><td>Clarifai</td><td>object detection</td><td>2.0</td><td>2.0</td></tr><tr><td>Google</td><td>Google</td><td>object detection</td><td>2.25</td><td>2.25</td></tr><tr><td>Microsoft</td><td>Microsoft</td><td>object detection</td><td>1.0</td><td>1.0</td></tr><tr><td>SentiSight</td><td>Sentisight</td><td>object detection</td><td>0.75</td><td>0.75</td></tr><tr><td>Amazon</td><td>Amazon</td><td>ocr</td><td>1.5</td><td>1.5</td></tr><tr><td>api4ai</td><td>api4ai</td><td>ocr</td><td>0.003</td><td>0.003</td></tr><tr><td>clarifai</td><td>Clarifai</td><td>ocr</td><td>2.0</td><td>2.0</td></tr><tr><td>Google</td><td>Google</td><td>ocr</td><td>1.5</td><td>1.5</td></tr><tr><td>Microsoft</td><td>Microsoft</td><td>ocr</td><td>1.0</td><td>1.0</td></tr><tr><td>sentisight</td><td>Sentisight</td><td>ocr</td><td>0.75</td><td>0.75</td></tr><tr><td>Groq</td><td>whisper-large-v3</td><td>stt</td><td>0.1109988</td><td>0.1109988</td></tr><tr><td>Groq</td><td>whisper-large-v3-Turbo</td><td>stt</td><td>0.0399996</td><td>0.0399996</td></tr><tr><td>OpenAI</td><td>GPT-4o Transcribe</td><td>stt</td><td>0.0216</td><td>0.036</td></tr><tr><td>OpenAI</td><td>GPT-4o mini Transcribe</td><td>stt</td><td>0.0108</td><td>0.018</td></tr><tr><td>OpenAI</td><td>Whisper-1</td><td>stt</td><td>0.36</td><td>0.36</td></tr><tr><td>Amazon</td><td>Amazon</td><td>translation</td><td>15.0</td><td>15.0</td></tr><tr><td>DeepL</td><td>DeepL</td><td>translation</td><td>20.0</td><td>20.0</td></tr><tr><td>Google</td><td>Google</td><td>translation</td><td>20.0</td><td>20.0</td></tr><tr><td>Microsoft</td><td>Microsoft</td><td>translation</td><td>10.0</td><td>10.0</td></tr><tr><td>modernMT</td><td>ModernMT</td><td>translation</td><td>8.0</td><td>8.0</td></tr><tr><td>Amazon</td><td>Amazon</td><td>tts</td><td>4.0</td><td>4.0</td></tr><tr><td>Deepgram</td><td>Deepgram</td><td>tts</td><td>15.0</td><td>15.0</td></tr><tr><td>ElevenLabs</td><td>ElevenLabs</td><td>tts</td><td>300.0</td><td>300.0</td></tr><tr><td>Google</td><td>Google</td><td>tts</td><td>4.0</td><td>4.0</td></tr><tr><td>Microsoft</td><td>Microsoft</td><td>tts</td><td>16.0</td><td>16.0</td></tr><tr><td>OpenAI</td><td>GPT-4o mini TTS</td><td>tts</td><td>0.6</td><td>12.0</td></tr><tr><td>OpenAI</td><td>TTS-1</td><td>tts</td><td>15.0</td><td>15.0</td></tr><tr><td>OpenAI</td><td>TTS-1-HD</td><td>tts</td><td>30.0</td><td>30.0</td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aibrary.dev/all-pricing.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
