# Qwen3 Coder Next Fp8 vs Inkling Small

On provider list prices, Qwen3 Coder Next Fp8 costs $0.50 per million input tokens against $0.50 for Inkling Small: effectively level. Output is $1.20 against $1.20.

## Specifications

| | Qwen3 Coder Next Fp8 | Inkling Small |
| --- | --- | --- |
| Lab | Qwen | Thinking Machines |
| Access | Open weights | Open weights |
| Context window | 256K tokens | 512K tokens |
| List price, input | $0.50 / M tokens | $0.50 / M tokens |
| List price, output | $1.20 / M tokens | $1.20 / M tokens |
| Cached input | n/a | $0.10 / M tokens |
| License | Apache 2.0 | Not listed |
| Fine-tunable | Yes | Yes |

Specifications and provider list prices from the Allocate catalog, checked 2026-09-12.

## What the numbers say

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each. That workload costs $1,020 a month on Qwen3 Coder Next Fp8 and $1,020 on Inkling Small at list: a gap of $0.

Inkling Small reads 512K tokens per request against 256K for Qwen3 Coder Next Fp8, 2.0x the window. That decides which one can take whole documents without splitting them.

## Choose Qwen3 Coder Next Fp8 for

- Fine-tuning under a permissive license (Apache 2.0)

## Choose Inkling Small for

- The longer context window (512K vs 256K tokens)
- Published cached-input pricing ($0.10 per M tokens)

## Common questions

### Which is cheaper, Qwen3 Coder Next Fp8 or Inkling Small?

Qwen3 Coder Next Fp8, on this workload shape. At list prices it is $0.50/$1.20 per million tokens in and out against $0.50/$1.20 for Inkling Small. Billed on Allocate: $0.54/$1.28 against $0.54/$1.28.

### Which has the bigger context window?

Inkling Small: 524,288 tokens (512K) against 262,144 (256K) for Qwen3 Coder Next Fp8.

### Can I fine-tune Qwen3 Coder Next Fp8 or Inkling Small?

Both publish open weights (Qwen3 Coder Next Fp8: Apache 2.0; Inkling Small: Not listed), so both can be fine-tuned. On Allocate the trained weights stay inside your boundary and belong to you.

---

[HTML page](https://allocate.network/compare/qwen-qwen3-coder-next-fp8-vs-thinkingmachines-inkling-small) · [Qwen3 Coder Next Fp8](https://allocate.network/models/qwen-qwen3-coder-next-fp8.md) · [Inkling Small](https://allocate.network/models/thinkingmachines-inkling-small.md) · [Machine-readable catalog](https://allocate.network/catalog.json)