Using Dolphin 2.6 Mixtral 8x7B on DeepInfra
Implementation guide · Dolphin · Cognitive Computations
DeepInfra exposes Dolphin 2.6 Mixtral 8x7B through model ID dolphin-2.6-mixtral-8x7b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-06-15. Next refresh: weekly.
Quick Start
- 1
- 2Use the DeepInfra SDK or REST API to call
dolphin-2.6-mixtral-8x7b— see the documentation for request format. - 3
Code Examples
pip install openaiDEEPINFRA_API_KEYdolphin-2.6-mixtral-8x7bDeepInfra uses "organization/model-name" format, e.g. "meta-llama/Meta-Llama-3-8B-Instruct" or "mistralai/Mistral-7B-Instruct-v0.3". See the DeepInfra model catalog for exact IDs.
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["DEEPINFRA_API_KEY"],
base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
model="dolphin-2.6-mixtral-8x7b",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on DeepInfra
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.15 |
| Output tokens | $0.45 |
Capabilities
No model capability flags are currently sourced.
About Dolphin 2.6 Mixtral 8x7B
Dolphin 2.6 Mixtral 8x7B is a large language model fine-tuned from the Mixtral-8x7B base, known for its robust coding abilities and high compliance with user prompts. Despite not being tuned with Direct Preference Optimization, it performs exceptionally well in coding tasks due to extensive training with coding datasets, including MagiCoder. The model's architecture features a context window reduced to 16k, and training was carried out using techniques like qLoRA. However, it is uncensored, exposing potential ethical concerns and prompting caution for deployment without additional safeguards.