Skip to content

Commit 2746c0e

Browse files
benchbzhbenchbzh
authored
Merge pull request #8223 from ovh/MB-AI-Endpoints-pricing
[AI Endpoints] - Billing Guide - Update prices, columns name and add new models
2 parents e6f627d + 2bd8a58 commit 2746c0e

File tree

15 files changed

+469
-469
lines changed

15 files changed

+469
-469
lines changed

‎pages/public_cloud/ai_machine_learning/endpoints_guide_04_billing_concept/guide.de-de.md

Lines changed: 31 additions & 31 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: AI Endpoints - Billing and lifecycle
33
excerpt: Learn how we bill AI Endpoints
4-
updated: 2025-04-28
4+
updated: 2025-07-31
55
---
66

77
> [!primary]
@@ -31,36 +31,36 @@ By following this model lifecycle process, OVHcloud ensures that customers are w
3131

3232
## Billing principles
3333

34-
Here is the model billing overview for AI Endpoints.
35-
36-
| Category | Model | Price ($) | Price (€) | Unit Price |
37-
| -------------- | --------------- | ------ | ------ | ---------- |
38-
| Large Language Model (LLM) | Llama 3.3 70B Instruct | 0.74 | 0.67 | per 1M tokens |
39-
| Large Language Model (LLM) | Llama 3.1 70B Instruct | 0.74 | 0.67 | per 1M tokens |
40-
| Large Language Model (LLM) | Mixtral 8x7B Instruct v0.1 | 0.70 | 0.63 | per 1M tokens |
41-
| Large Language Model (LLM) | Mistral-Nemo-Instruct-2407 | 0.14 | 0.13 | per 1M tokens |
42-
| Large Language Model (LLM) | Llama 3.1 8B Instruct | 0.10 | 0.10 | per 1M tokens |
43-
| Large Language Model (LLM) | Mistral 7B Instruct v0.3 | 0.11 | 0.10 | per 1M tokens |
44-
| Reasoning LLM | DeepSeek R1 Distill Llama 70B | 0.74 | 0.67 | per 1M tokens |
45-
| Reasoning LLM | Qwen3 32B | 0.09 | 0.08 | per 1M tokens |
46-
| Code LLM | Qwen2.5 Coder 32B Instruct | 0.96 | 0.87 | per 1M tokens |
47-
| Code LLM | Mamba Codestral 7B v0.1 | 0.21 | 0.19 | per 1M tokens |
48-
| Visual LLM | Mistral Small 3.2 24B Instruct 2506 | 0.10 | 0.09 | per 1M tokens |
49-
| Visual LLM | Qwen2.5 VL 72B Instruct | 1.01 | 0.91 | per 1M tokens |
50-
| Visual LLM | Llava Next Mistral 7B | 0.32 | 0.29 | per 1M tokens |
51-
| Embeddings | BGE Multilingual Gemma2 | 0.01 | 0.01 | per 1M tokens |
52-
| Embeddings | BGE-M3 | 0.01 | 0.01 | per 1M tokens |
53-
| Embeddings | BGE Base EN v1.5 | 0.01 | 0.005 | per 1M tokens |
54-
| Natural Language Processing (NLP) | Roberta Base Go Emotions | Free | Free | per 1M characters |
55-
| Natural Language Processing (NLP) | Bert Base Multilingual uncased sentiment | Free | Free | per 1M characters |
56-
| Natural Language Processing (NLP) | Bert Base NER | Free | Free | per 1M characters |
57-
| Natural Language Processing (NLP) | Bart Large CNN | Free | Free | per 1M characters |
58-
| Image generation| Stable Diffusion XL | Free | Free | per image |
59-
| Speech to Text | RIVA Automatic Speech Recognition | Free | Free | per hour |
60-
| Text to Speech | RIVA Text-to-Speech | Free | Free | per hour |
61-
| Translation | T5-Large | Free | Free | per 1M characters |
62-
| Computer vision | YOLOv11 Object Detection | Free | Free | per image |
63-
| Computer vision | YOLOv11 Image Segmentation | Free | Free | per image |
34+
Here is the model billing overview for AI Endpoints models:
35+
36+
| Category | Model | Input Price (\$) | Output Price (\$) | Input Price (€) | Output Price (€) | Unit Price |
37+
| -------------------------- | -------------------------- | ---------------- | ----------------- | --------------- | ---------------- | --------------------------------- |
38+
| Large Language Model (LLM) | Llama 3.3 70B Instruct | 0.74 | 0.74 | 0.67 | 0.67 | Per 1 million tokens |
39+
| Large Language Model (LLM) | Llama 3.1 70B Instruct | 0.74 | 0.74 | 0.67 | 0.67 | Per 1 million tokens |
40+
| Large Language Model (LLM) | Mixtral 8x7B Instruct v0.1 | 0.70 | 0.70 | 0.63 | 0.63 | Per 1 million tokens |
41+
| Large Language Model (LLM) | Mistral Nemo Instruct 2407 | 0.14 | 0.14 | 0.13 | 0.13 | Per 1 million tokens |
42+
| Large Language Model (LLM) | Llama 3.1 8B Instruct | 0.11 | 0.11 | 0.10 | 0.10 | Per 1 million tokens |
43+
| Large Language Model (LLM) | Mistral 7B Instruct v0.3 | 0.11 | 0.11 | 0.10 | 0.10 | Per 1 million tokens |
44+
| Reasoning LLM | Qwen 3 32B | 0.09 | 0.25 | 0.08 | 0.23 | Per 1 million tokens |
45+
| Reasoning LLM | DeepSeek R1 Distill Llama 70B | 0.74 | 0.74 | 0.67 | 0.67 | Per 1 million tokens |
46+
| Code LLM | Qwen 2.5 Coder 32B Instruct | 0.96 | 0.96 | 0.87 | 0.87 | Per 1 million tokens |
47+
| Code LLM | Mamba Codestral 7B v0.1 | 0.21 | 0.21 | 0.19 | 0.19 | Per 1 million tokens |
48+
| Visual LLM | Mistral Small 3.2 24B Instruct 2506 | 0.10 | 0.31 | 0.09 | 0.28 | Per 1 million tokens |
49+
| Visual LLM | Qwen 2.5 VL 72B Instruct | 1.01 | 1.01 | 0.91 | 0.91 | Per 1 million tokens |
50+
| Visual LLM | Llava Next Mistral 7B | 0.32 | 0.32 | 0.29 | 0.29 | Per 1 million tokens |
51+
| Embeddings | BGE Multilingual Gemma2 | 0.01 | 0.01 | Free | Free | Per 1 million tokens |
52+
| Embeddings | BGE M3 | 0.01 | 0.01 | Free | Free | Per 1 million tokens |
53+
| Embeddings | BGE Base EN v1.5 | 0.01 | 0.01 | Free | Free | Per 1 million tokens |
54+
| Natural Language Processing (NLP) | Roberta Base Go Emotions | Free | Free | Free | Free | Per 1 million characters |
55+
| Natural Language Processing (NLP) | Bert Base Multilingual uncased sentiment | Free | Free | Free | Free | Per 1 million characters |
56+
| Natural Language Processing (NLP) | Bert Base NER | Free | Free | Free | Free | Per 1 million characters |
57+
| Natural Language Processing (NLP) | Bart Large CNN | Free | Free | Free | Free | Per 1 million characters |
58+
| Image generation | Stable Diffusion XL | Free | Free | Free | Free | Per image |
59+
| Audio Analysis | RIVA Automatic Speech Recognition | Free | Free | Free | Free | Per hour |
60+
| Audio Analysis | RIVA Text-to-Speech | Free | Free | Free | Free | Per hour |
61+
| Translation | T5-Large | Free | Free | Free | Free | Per 1 million characters |
62+
| Computer vision | YOLOv11 Object Detection | Free | Free | Free | Free | Per image |
63+
| Computer vision | YOLOv11 Image Segmentation | Free | Free | Free | Free | Per image |
6464

6565
## Feedback
6666

‎pages/public_cloud/ai_machine_learning/endpoints_guide_04_billing_concept/guide.en-asia.md

Lines changed: 31 additions & 31 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: AI Endpoints - Billing and lifecycle
33
excerpt: Learn how we bill AI Endpoints
4-
updated: 2025-04-28
4+
updated: 2025-07-31
55
---
66

77
> [!primary]
@@ -31,36 +31,36 @@ By following this model lifecycle process, OVHcloud ensures that customers are w
3131

3232
## Billing principles
3333

34-
Here is the model billing overview for AI Endpoints.
35-
36-
| Category | Model | Price ($) | Price (€) | Unit Price |
37-
| -------------- | --------------- | ------ | ------ | ---------- |
38-
| Large Language Model (LLM) | Llama 3.3 70B Instruct | 0.74 | 0.67 | per 1M tokens |
39-
| Large Language Model (LLM) | Llama 3.1 70B Instruct | 0.74 | 0.67 | per 1M tokens |
40-
| Large Language Model (LLM) | Mixtral 8x7B Instruct v0.1 | 0.70 | 0.63 | per 1M tokens |
41-
| Large Language Model (LLM) | Mistral-Nemo-Instruct-2407 | 0.14 | 0.13 | per 1M tokens |
42-
| Large Language Model (LLM) | Llama 3.1 8B Instruct | 0.10 | 0.10 | per 1M tokens |
43-
| Large Language Model (LLM) | Mistral 7B Instruct v0.3 | 0.11 | 0.10 | per 1M tokens |
44-
| Reasoning LLM | DeepSeek R1 Distill Llama 70B | 0.74 | 0.67 | per 1M tokens |
45-
| Reasoning LLM | Qwen3 32B | 0.09 | 0.08 | per 1M tokens |
46-
| Code LLM | Qwen2.5 Coder 32B Instruct | 0.96 | 0.87 | per 1M tokens |
47-
| Code LLM | Mamba Codestral 7B v0.1 | 0.21 | 0.19 | per 1M tokens |
48-
| Visual LLM | Mistral Small 3.2 24B Instruct 2506 | 0.10 | 0.09 | per 1M tokens |
49-
| Visual LLM | Qwen2.5 VL 72B Instruct | 1.01 | 0.91 | per 1M tokens |
50-
| Visual LLM | Llava Next Mistral 7B | 0.32 | 0.29 | per 1M tokens |
51-
| Embeddings | BGE Multilingual Gemma2 | 0.01 | 0.01 | per 1M tokens |
52-
| Embeddings | BGE-M3 | 0.01 | 0.01 | per 1M tokens |
53-
| Embeddings | BGE Base EN v1.5 | 0.01 | 0.005 | per 1M tokens |
54-
| Natural Language Processing (NLP) | Roberta Base Go Emotions | Free | Free | per 1M characters |
55-
| Natural Language Processing (NLP) | Bert Base Multilingual uncased sentiment | Free | Free | per 1M characters |
56-
| Natural Language Processing (NLP) | Bert Base NER | Free | Free | per 1M characters |
57-
| Natural Language Processing (NLP) | Bart Large CNN | Free | Free | per 1M characters |
58-
| Image generation| Stable Diffusion XL | Free | Free | per image |
59-
| Speech to Text | RIVA Automatic Speech Recognition | Free | Free | per hour |
60-
| Text to Speech | RIVA Text-to-Speech | Free | Free | per hour |
61-
| Translation | T5-Large | Free | Free | per 1M characters |
62-
| Computer vision | YOLOv11 Object Detection | Free | Free | per image |
63-
| Computer vision | YOLOv11 Image Segmentation | Free | Free | per image |
34+
Here is the model billing overview for AI Endpoints models:
35+
36+
| Category | Model | Input Price (\$) | Output Price (\$) | Input Price (€) | Output Price (€) | Unit Price |
37+
| -------------------------- | -------------------------- | ---------------- | ----------------- | --------------- | ---------------- | --------------------------------- |
38+
| Large Language Model (LLM) | Llama 3.3 70B Instruct | 0.74 | 0.74 | 0.67 | 0.67 | Per 1 million tokens |
39+
| Large Language Model (LLM) | Llama 3.1 70B Instruct | 0.74 | 0.74 | 0.67 | 0.67 | Per 1 million tokens |
40+
| Large Language Model (LLM) | Mixtral 8x7B Instruct v0.1 | 0.70 | 0.70 | 0.63 | 0.63 | Per 1 million tokens |
41+
| Large Language Model (LLM) | Mistral Nemo Instruct 2407 | 0.14 | 0.14 | 0.13 | 0.13 | Per 1 million tokens |
42+
| Large Language Model (LLM) | Llama 3.1 8B Instruct | 0.11 | 0.11 | 0.10 | 0.10 | Per 1 million tokens |
43+
| Large Language Model (LLM) | Mistral 7B Instruct v0.3 | 0.11 | 0.11 | 0.10 | 0.10 | Per 1 million tokens |
44+
| Reasoning LLM | Qwen 3 32B | 0.09 | 0.25 | 0.08 | 0.23 | Per 1 million tokens |
45+
| Reasoning LLM | DeepSeek R1 Distill Llama 70B | 0.74 | 0.74 | 0.67 | 0.67 | Per 1 million tokens |
46+
| Code LLM | Qwen 2.5 Coder 32B Instruct | 0.96 | 0.96 | 0.87 | 0.87 | Per 1 million tokens |
47+
| Code LLM | Mamba Codestral 7B v0.1 | 0.21 | 0.21 | 0.19 | 0.19 | Per 1 million tokens |
48+
| Visual LLM | Mistral Small 3.2 24B Instruct 2506 | 0.10 | 0.31 | 0.09 | 0.28 | Per 1 million tokens |
49+
| Visual LLM | Qwen 2.5 VL 72B Instruct | 1.01 | 1.01 | 0.91 | 0.91 | Per 1 million tokens |
50+
| Visual LLM | Llava Next Mistral 7B | 0.32 | 0.32 | 0.29 | 0.29 | Per 1 million tokens |
51+
| Embeddings | BGE Multilingual Gemma2 | 0.01 | 0.01 | Free | Free | Per 1 million tokens |
52+
| Embeddings | BGE M3 | 0.01 | 0.01 | Free | Free | Per 1 million tokens |
53+
| Embeddings | BGE Base EN v1.5 | 0.01 | 0.01 | Free | Free | Per 1 million tokens |
54+
| Natural Language Processing (NLP) | Roberta Base Go Emotions | Free | Free | Free | Free | Per 1 million characters |
55+
| Natural Language Processing (NLP) | Bert Base Multilingual uncased sentiment | Free | Free | Free | Free | Per 1 million characters |
56+
| Natural Language Processing (NLP) | Bert Base NER | Free | Free | Free | Free | Per 1 million characters |
57+
| Natural Language Processing (NLP) | Bart Large CNN | Free | Free | Free | Free | Per 1 million characters |
58+
| Image generation | Stable Diffusion XL | Free | Free | Free | Free | Per image |
59+
| Audio Analysis | RIVA Automatic Speech Recognition | Free | Free | Free | Free | Per hour |
60+
| Audio Analysis | RIVA Text-to-Speech | Free | Free | Free | Free | Per hour |
61+
| Translation | T5-Large | Free | Free | Free | Free | Per 1 million characters |
62+
| Computer vision | YOLOv11 Object Detection | Free | Free | Free | Free | Per image |
63+
| Computer vision | YOLOv11 Image Segmentation | Free | Free | Free | Free | Per image |
6464

6565
## Feedback
6666

0 commit comments

Comments
 (0)