---
title: "Orion 26B A4B v1.1 API pricing"
canonical: https://uplinkswitch.ai/models/orion-26b-a4b-v1.1
generated: 2026-10-22T19:06:46.439Z
source: https://api.uplinkswitch.com/v1/catalog
base_url: https://api.uplinkswitch.com/v1
---

# Orion 26B A4B v1.1 API pricing

Orion 26B A4B v1.1 API at $0.35/M input and $1.575/M output tokens. 65,536-token context window. Works with the OpenAI SDK.

## Price per million tokens (USD)

| Tokens | TheDrummer list price | UplinkSwitch | Under list |
| --- | --- | --- | --- |
| Input | — | $0.35 | — |
| Cached input | — | billed at the input rate | — |
| Output | — | $1.575 | — |

## Model

- Model id: `orion-26b-a4b-v1.1`
- Formats: OpenAI SDK
- Base URL: https://api.uplinkswitch.com/v1
- Context window: 65,536 tokens
- Max output: 8,192 tokens
- Input: text
- Daily real-model check: No answer at the last check (https://uplinkswitch.ai/proof#orion-26b-a4b-v1.1)

## Request

### Python · OpenAI SDK

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uplinkswitch.com/v1",
    api_key="sk-uplink-live-...",
)

completion = client.chat.completions.create(
    model="orion-26b-a4b-v1.1",
    messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)
```

### TypeScript · OpenAI SDK

```typescript
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.uplinkswitch.com/v1',
  apiKey: 'sk-uplink-live-...',
});

const completion = await client.chat.completions.create({
  model: 'orion-26b-a4b-v1.1',
  messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);
```

### curl

```bash
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"orion-26b-a4b-v1.1","messages":[{"role":"user","content":"Hello"}]}'
```

## Questions

### What is Orion 26B A4B v1.1?

Orion 26B A4B v1.1 is a model from TheDrummer, with a 65,536-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as orion-26b-a4b-v1.1.

### How much does the Orion 26B A4B v1.1 API cost?

$0.35 per million input tokens and $1.575 per million output tokens.

### Is Orion 26B A4B v1.1 free?

It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0011.

### What is the Orion 26B A4B v1.1 context window?

Orion 26B A4B v1.1 has a 65,536-token context window, with up to 8,192 output tokens per request. It takes text input.

### What is the Orion 26B A4B v1.1 model id?

orion-26b-a4b-v1.1. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.

### How do I get a Orion 26B A4B v1.1 API key?

Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls Orion 26B A4B v1.1 and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.

### Is there a Orion 26B A4B v1.1 API?

Yes: orion-26b-a4b-v1.1 on the OpenAI format at https://api.uplinkswitch.com/v1, $0.35 input and $1.575 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.

### What is Orion 26B A4B v1.1 based on?

Google’s Gemma 4 26B-A4B instruction-tuned mixture of experts, fine-tuned by TheDrummer for roleplay, per the Orion 26B A4B v1.1 card.

### What license does Orion 26B A4B v1.1 have?

The Orion card lists no license. Its base, Gemma 4 26B-A4B, is under Google’s Gemma terms of use.

### What does Orion 26B A4B v1.1 cost per 100 messages?

$0.1488 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.35 input and $1.575 output per million tokens, from prepaid credit with no subscription.

### What does 26B-A4B mean?

26B parameters in total, about 4B active on each token: a mixture of experts, so each reply costs the compute of a small model while the weights hold more than a 4B dense model would.

### Orion 26B A4B v1.1 or Artemis v1.1?

Both are TheDrummer’s Gemma 4 tunes: Orion is the roleplay tune of the 26B-A4B mixture of experts; Artemis is the dense 31B writing tune. Orion 26B A4B v1.1 is $0.35 / $1.575 per million tokens in / out, $1.49 for 1,000 chat turns; Artemis v1.1 is $0.35 / $1.575 per million tokens in / out, $1.49 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.

### Orion 26B A4B v1.1 or Gemma 4 26B-A4B DarkSoul?

Same base, two methods: Orion is TheDrummer’s single fine-tune; DarkSoul is a merge of three Gemma 4 26B-A4B tunes. Orion 26B A4B v1.1 is $0.35 / $1.575 per million tokens in / out, $1.49 for 1,000 chat turns; Gemma 4 26B-A4B DarkSoul is $0.484 / $1.52 per million tokens in / out, $1.73 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.

## Related

- Uncensored LLM API: https://uplinkswitch.ai/uncensored
- SillyTavern setup: https://uplinkswitch.ai/guides/sillytavern
- Janitor AI setup: https://uplinkswitch.ai/guides/janitor-ai
- Chub AI setup: https://uplinkswitch.ai/guides/chub-ai
- SDKs setup: https://uplinkswitch.ai/guides/sdks
- Every model and price: https://uplinkswitch.ai/llms-full.txt
- Machine catalog: https://uplinkswitch.ai/ai-catalog.json