Dolphin Mistral 24B Venice Edition, per token on one key.
Dolphin Mistral 24B Venice Edition is an uncensored build, set up to decline fewer requests than a stock model. It costs $0.50 per million input tokens and $2.25 per million output tokens, prepaid, with a 32,768-token context window. Call it at https://api.pentestllm.ai/v1/chat/completions with model "dolphin-mistral-24b-venice" and a PentestLLM key, from any OpenAI SDK or agent that takes a base URL. It is for authorized security testing only.
Price per million tokens
- Input
- $0.50
- Cached input
- $0.50 (input rate)
- Output
- $2.25
- Daily check
- Steady since Oct 23
- As of
- 2026-11-12
First request
curl https://api.pentestllm.ai/v1/chat/completions \
-H "Authorization: Bearer sk-ptl-live-…" \
-H "Content-Type: application/json" \
-d '{"model": "dolphin-mistral-24b-venice", "messages": [{"role": "user", "content": "Hello"}]}'Get a key
- Create a key in the console. Credit is prepaid from $10, with no subscription.
- Set OPENAI_BASE_URL to https://api.pentestllm.ai/v1 and send your sk-ptl- key as the bearer token.
- Send dolphin-mistral-24b-venice as the model. The same key calls every model on PentestLLM.
Dolphin Mistral 24B Venice Edition settings for a coding agent
- Provider
- OpenAI-compatible
- Base URL
- https://api.pentestllm.ai/v1
- Model
- dolphin-mistral-24b-venice
- Context window
- 32,768 tokens
- Tool calling
- not listed in the catalog
- Key prefix
- sk-ptl-
Dolphin Mistral 24B Venice Edition specs
- Kind
- Uncensored
- Developer
- Cognitive Computations
- Context window
- 32,768 tokens
- Input
- text
- Wire formats
- openai
- Endpoints
- /v1/chat/completions, /v1/messages, /v1/completions, /v1/responses, /v1beta/models/{model}:generateContent
What Dolphin Mistral 24B Venice Edition is for
Dolphin Mistral 24B Venice Edition is an uncensored build: it is set up to decline fewer security questions than the stock model. Refusals are reduced, not gone. Testers use it for triaging scanner output, explaining a CVE, reviewing code for vulnerabilities, drafting report findings, writing detection rules and solving CTF challenges.
Use it only on systems you own or have written permission to test. The acceptable use policy lists what is not allowed and applies to every request.
Every request is settled to the token at the prices above. The daily real-model check sends a fixed prompt to every model and records whether the answer still matches; this model’s verdict today is “Steady since Oct 23”. Call it from the OpenAI SDK or a coding agent, or send auto/security and let the router pick a security build per request. Keys and top-ups live in the console.
What Dolphin Mistral 24B Venice Edition costs, worked
An agent turn of 8,000 input and 1,000 output tokens at $0.50 input and $2.25 output per million tokens is $0.0063; 100 turns are $0.625 and 1,000 turns are $6.25. An agent resends its context on every turn, so the input side is most of the bill. All from prepaid credit, no subscription.
- Input, 8,000 tokens at $0.50 per million
- $0.004
- Output, 1,000 tokens at $2.25 per million
- $0.0023
- One turn
- $0.0063
- 1,000 turns
- $6.25
| Uncensored builds | Context | In / out per 1M | 1,000 agent turns |
|---|---|---|---|
| GLM-5.3 Flash Uncensored | n/a | $0.1053 / $0.3685 | $1.2107 |
| GLM-5.3 Uncensored | n/a | $0.282 / $0.846 | $3.102 |
| Dolphin Mistral 24B Venice Edition | 33K | $0.50 / $2.25 | $6.25 |
| Deepseek V4.1 Flash Uncensored | 1000K | $0.5412 / $2.5882 | $6.9176 |
| Gemma 4 26B-A4B Uncensored | 33K | $0.60 / $2.80 | $7.60 |
| Jailbreak-Free Assistant | 1049K | $0.75 / $2.50 | $8.50 |
| SuperGemma 4 26B Uncensored | 256K | $0.78 / $2.40 | $8.64 |
| Amoral Gemma3 27B v2 | 33K | $1.05 / $1.05 | $9.45 |
| Gemma 4 31B K1 v5 | 262K | $1.071 / $1.071 | $9.639 |
| DeepSeek V4 Pro Uncensored | n/a | $0.97 / $1.94 | $9.70 |
| DeepSeek V4.1 Flash 0910 Uncensored | 524K | $0.825 / $3.30 | $9.90 |
| DeepSeek V4.1 Flash 0910 Uncensored Thinking | 524K | $0.825 / $3.30 | $9.90 |
Also try
Dolphin Mistral 24B Venice Edition questions
Dolphin Mistral 24B Venice Edition is an uncensored build, set up to decline fewer requests than a stock model, from Cognitive Computations, with a 32,768-token context window. On PentestLLM it answers as dolphin-mistral-24b-venice.
Dolphin Mistral 24B Venice Edition is set up to decline fewer requests than the stock model, which is what security testers need when a general assistant refuses a question about a vulnerability or a tool. Refusals are reduced, not gone, and the acceptable use policy still applies to every request. See the acceptable use policy.
No. Credit is prepaid from $10 and billed per token: input $0.50 and output $2.25 per million tokens, cached input $0.50 (input rate).
About $0.0063 for 8,000 tokens in and 1,000 tokens out, at $0.50 in and $2.25 out per million tokens. A thousand such turns are $6.25.
Yes. Send dolphin-mistral-24b-venice as the model through the OpenAI SDK, or any agent that takes a custom OpenAI base URL, with base URL https://api.pentestllm.ai/v1. It also answers the Anthropic Messages API at the same host, so agents built on the Anthropic SDK can call it. See the docs.
Yes. The daily real-model check sends every model the same fixed prompt and records whether the answer still matches. Dolphin Mistral 24B Venice Edition’s latest result, from Nov 12: steady since Oct 23. See the daily check.