Ovhcloud API pricing
Hosted15 language models
As of Oct 14, 2026, Ovhcloud lists 15 language models through its API. Its cheapest language model is gpt-oss-20b at $0.04 input / $0.15 output per million tokens.
Language models (15)
Prices per million tokens.
ovhcloud/DeepSeek-R1-Distill-Llama-70B
- Input
- $0.67
- Output
- $0.67
- Context
- 131K
ovhcloud/gpt-oss-20b
- Input
- $0.04
- Output
- $0.15
- Context
- 131K
ovhcloud/gpt-oss-120b
- Input
- $0.08
- Output
- $0.40
- Context
- 131K
ovhcloud/Llama-3.1-8B-Instruct
- Input
- $0.10
- Output
- $0.10
- Context
- 131K
ovhcloud/Meta-Llama-3_1-70B-Instruct
- Input
- $0.67
- Output
- $0.67
- Context
- 131K
ovhcloud/Mistral-Nemo-Instruct-2407
- Input
- $0.13
- Output
- $0.13
- Context
- 118K
Mistral Small 3.2 24B Instruct 2506
ovhcloud/Mistral-Small-3.2-24B-Instruct-2506
- Input
- $0.09
- Output
- $0.28
- Context
- 128K
ovhcloud/Mixtral-8x7B-Instruct-v0.1
- Input
- $0.63
- Output
- $0.63
- Context
- 32K
ovhcloud/Qwen3-32B
- Input
- $0.08
- Output
- $0.23
- Context
- 32K
ovhcloud/Qwen2.5-Coder-32B-Instruct
- Input
- $0.87
- Output
- $0.87
- Context
- 32K
ovhcloud/Qwen2.5-VL-72B-Instruct
- Input
- $0.91
- Output
- $0.91
- Context
- 32K
Llava V1.6 Mistral 7B Hf
ovhcloud/llava-v1.6-mistral-7b-hf
- Input
- $0.29
- Output
- $0.29
- Context
- 32K
Mamba Codestral 7B V0.1
ovhcloud/mamba-codestral-7B-v0.1
- Input
- $0.19
- Output
- $0.19
- Context
- 256K
Meta Llama 3.3 70B Instruct
ovhcloud/Meta-Llama-3_3-70B-Instruct
- Input
- $0.67
- Output
- $0.67
- Context
- 131K
Mistral 7B Instruct V0.3
ovhcloud/Mistral-7B-Instruct-v0.3
- Input
- $0.10
- Output
- $0.10
- Context
- 127K
Prices in USD from LiteLLM and models.dev, checked daily; confirm on Ovhcloud's pricing page before you rely on a number.