# Kimi K2.5 vs Qwen3 235B A22B Instruct 2507 FP8 Throughput

On provider list prices, Qwen3 235B A22B Instruct 2507 FP8 Throughput costs $0.20 per million input tokens against $0.50 for Kimi K2.5: 2.5x apart. Output is $0.60 against $2.80 (4.7x). On Allocate both bill at list plus the 7% transaction fee.

## Specifications

| | Kimi K2.5 | Qwen3 235B A22B Instruct 2507 FP8 Throughput |
| --- | --- | --- |
| Lab | Togethercomputer | Qwen |
| Access | Open weights | Open weights |
| Context window | 256K tokens | 256K tokens |
| List price, input | $0.50 / M tokens | $0.20 / M tokens |
| List price, output | $2.80 / M tokens | $0.60 / M tokens |
| Cached input | n/a | n/a |
| License | Not listed | Apache 2.0 |
| Fine-tunable | Yes | Yes |

Specifications and provider list prices from the Allocate catalog, checked 2026-07-08. Billed price is list plus the 7% transaction fee.

## What the numbers say

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each. That workload costs $450 a month on Qwen3 235B A22B Instruct 2507 FP8 Throughput and $1,580 on Kimi K2.5 at list: a gap of $1,130, or 3.5x.

## Choose Kimi K2.5 for

- Whole-document reasoning
- Long-context retrieval
- Open-weight fine-tuning

## Choose Qwen3 235B A22B Instruct 2507 FP8 Throughput for

- The lower list price ($0.20 in / $0.60 out per M tokens)
- Fine-tuning under a permissive license (Apache 2.0)

## Common questions

### Which is cheaper, Kimi K2.5 or Qwen3 235B A22B Instruct 2507 FP8 Throughput?

Qwen3 235B A22B Instruct 2507 FP8 Throughput, on this workload shape. At list prices it is $0.20/$0.60 per million tokens in and out against $0.50/$2.80 for Kimi K2.5. Billed on Allocate: $0.21/$0.64 against $0.54/$3.00, list plus 7%.

### Which has the bigger context window?

They match: both read 262,144 tokens (256K) per request.

### Can I fine-tune Kimi K2.5 or Qwen3 235B A22B Instruct 2507 FP8 Throughput?

Both publish open weights (Kimi K2.5: Not listed; Qwen3 235B A22B Instruct 2507 FP8 Throughput: Apache 2.0), 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/kimi-k2-5-vs-qwen-qwen3-235b-a22b-instruct-2507-tput) · [Kimi K2.5](https://allocate.network/models/kimi-k2-5.md) · [Qwen3 235B A22B Instruct 2507 FP8 Throughput](https://allocate.network/models/qwen-qwen3-235b-a22b-instruct-2507-tput.md) · [Machine-readable catalog](https://allocate.network/catalog.json)