# The cheapest uncensored LLM API: real prices per million tokens

_2026-11-08. The cheapest uncensored and abliterated models you can call by API, with per token prices, no markup, and which cheap models are actually good according to measured rankings._

Uncensored models are open weight models, so they are cheap to serve. The real costs are hidden: a GPU you rent by
the hour, a subscription you forget, or a router that adds a percentage on top. This page lists the cheapest
uncensored models you can call by API, with real prices, and which of the cheap ones are actually good.

## The cheapest uncensored models, per million tokens

Prices are what the cheapest provider for each model charges, which is exactly what you pay on Open Uncensored: there
is no markup and no platform fee.

| Model | id | $ per 1M input | $ per 1M output | Rank (score) | Context |
|---|---|---|---|---|---|
| [GLM 4.7 Flash Heretic](https://openuncensored.com/models/olafangensan-glm-4.7-flash-heretic) | `olafangensan-glm-4.7-flash-heretic` | $0.070 | $0.400 | #20 (52.7) | 200K |
| [Gemma 4 26B A4B Chimera X Heretic](https://openuncensored.com/models/gemma-4-26b-a4b-it-chimeraxheretic) | `gemma-4-26b-a4b-it-chimeraxheretic` | $0.120 | $0.380 | not ranked yet | 262K |
| [Grayline Qwen3 8B](https://openuncensored.com/models/grayline-qwen3-8b) | `grayline-qwen3-8b` | $0.300 | $0.300 | not ranked yet | 33K |
| [Gemma 4 31B Cognitive Unshackled](https://openuncensored.com/models/gemma-4-31b-cognitive-unshackled) | `gemma-4-31b-cognitive-unshackled` | $0.306 | $0.306 | not ranked yet | 262K |
| [Gemma 4 31B Gembrain Uncensored Heretic](https://openuncensored.com/models/gemma-4-31b-gembrain-uncensored-heretic) | `gemma-4-31b-gembrain-uncensored-heretic` | $0.306 | $0.306 | #13 (58.5) | 262K |
| [Gemma 4 31B SDFT Heretic RP](https://openuncensored.com/models/gemma-4-31b-sdft-heretic-rp) | `gemma-4-31b-sdft-heretic-rp` | $0.306 | $0.306 | not ranked yet | 262K |
| [Qwen3.5 27B Blossom V6.4 Derestricted](https://openuncensored.com/models/qwen3.5-27b-blossom-v6.4-derestricted) | `qwen3.5-27b-blossom-v6.4-derestricted` | $0.306 | $0.306 | #17 (56.3) | 262K |
| [Qwen3.5 27B BlueStar v3 Derestricted](https://openuncensored.com/models/qwen3.5-27b-bluestar-v3-derestricted) | `qwen3.5-27b-bluestar-v3-derestricted` | $0.306 | $0.306 | #16 (56.4) | 262K |
| [Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted](https://openuncensored.com/models/qwen3.5-27b-claude-4.6-opus-reasoning-distilled-derestricted) | `qwen3.5-27b-claude-4.6-opus-reasoning-distilled-derestricted` | $0.306 | $0.306 | #14 (57.8) | 262K |
| [Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite](https://openuncensored.com/models/qwen3.5-27b-claude-4.6-opus-reasoning-distilled-derestricted-lite) | `qwen3.5-27b-claude-4.6-opus-reasoning-distilled-derestricted-lite` | $0.306 | $0.306 | #22 (49.8) | 262K |
| [Qwen3.5 27B Queen Derestricted](https://openuncensored.com/models/qwen3.5-27b-queen-derestricted) | `qwen3.5-27b-queen-derestricted` | $0.306 | $0.306 | #15 (57.3) | 262K |
| [Apex Flash 1 Abliterated](https://openuncensored.com/models/glm-5.3-flash-apex-abliterated) | `glm-5.3-flash-apex-abliterated` | $0.150 | $0.500 | #8 (63.2) | 1049K |
| [Gemma 4 Uncensored](https://openuncensored.com/models/gemma-4-uncensored) | `gemma-4-uncensored` | $0.163 | $0.500 | #18 (54.6) | 256K |
| [Gemma 4 26B A4B Uncensored TEE](https://openuncensored.com/models/gemma-4-26b-a4b-uncensored) | `gemma-4-26b-a4b-uncensored` | $0.150 | $0.700 | #19 (52.8) | 262K |
| [Neural Daredevil 8B abliterated](https://openuncensored.com/models/neuraldaredevil-8b-abliterated) | `neuraldaredevil-8b-abliterated` | $0.440 | $0.440 | #29 (35.8) | 8K |

## Best value: cheap and good

Price alone is a trap: a cheap model that loops in agent tasks or still refuses costs you retries. Dividing the
[OpenUncensored Score](https://openuncensored.com/rankings) by price, the best value models right now are:

1. [Abliterated Large v2](https://openuncensored.com/chat?model=abliterated-large-v2): score 62.0 (rank #11), $8.00 per million input plus output tokens.
2. [Qwen 3.8 27B Uncensored Fast by Heabsy](https://openuncensored.com/chat?model=qwen3.8-27b-uncensored-fast): score 66.8 (rank #3), $4.00 per million input plus output tokens.
3. [GLM 5.3 Uncensored](https://openuncensored.com/chat?model=glm-5.3-uncensored): score 63.0 (rank #9), $3.50 per million input plus output tokens.

## Why it is cheapest on Open Uncensored

- **No markup.** You pay the provider's per token price. Every response says what the request cost.
- **Cheapest provider first.** Send `"routing": {"strategy": "cost"}` and each request goes to the cheapest provider
  serving those weights, falling back to the next one if it is down.
- **Cached prompts at the cached price.** Prompt tokens a provider serves from its cache are billed at its lower rate.
- **Prepaid, no subscription.** You load $5 or more, spend it per token, and credits never expire.

Compared with renting a GPU: a 27B model needs one large GPU at roughly $1 to $4 an hour, about $700 to $3,000 a month
if it is always on. At the prices above, that buys hundreds of millions of tokens.

## Try any of them in a minute

No account and no sign up. Buy a prepaid key at [openuncensored.com/credits](https://openuncensored.com/credits), or hand your
agent [openuncensored.com/agents.md](https://openuncensored.com/agents.md) and let it get one for you. Then:

```bash
curl https://openuncensored.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OU_API_KEY" -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4.1-flash-1017-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'
```

The full, always current table is on the [rankings page](https://openuncensored.com/rankings).