# Cogito v2.1 671B vs GLM 4.7 FP8

On provider list prices, GLM 4.7 FP8 costs $0.45 per million input tokens against $1.25 for Cogito v2.1 671B: 2.8x apart. Output is $2 against $1.25. On Allocate both bill at list plus the 7% transaction fee.

## Specifications

| | Cogito v2.1 671B | GLM 4.7 FP8 |
| --- | --- | --- |
| Lab | Deepcogito | Zai Org |
| Access | Open weights | Open weights |
| Context window | 160K tokens | 198K tokens |
| List price, input | $1.25 / M tokens | $0.45 / M tokens |
| List price, output | $1.25 / M tokens | $2 / M tokens |
| Cached input | n/a | n/a |
| License | Not listed | MIT |
| 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 $1,240 a month on GLM 4.7 FP8 and $1,938 on Cogito v2.1 671B at list: a gap of $697.50, or 1.6x.

GLM 4.7 FP8 reads 198K tokens per request against 160K for Cogito v2.1 671B, 1.2x the window. That decides which one can take whole documents without splitting them.

## Choose Cogito v2.1 671B for

- Training toward a model you own

## Choose GLM 4.7 FP8 for

- The lower list price ($0.45 in / $2 out per M tokens)
- The longer context window (198K vs 160K tokens)
- Fine-tuning under a permissive license (MIT)

## Common questions

### Which is cheaper, Cogito v2.1 671B or GLM 4.7 FP8?

GLM 4.7 FP8, on this workload shape. At list prices it is $0.45/$2 per million tokens in and out against $1.25/$1.25 for Cogito v2.1 671B. Billed on Allocate: $0.48/$2.14 against $1.34/$1.34, list plus 7%.

### Which has the bigger context window?

GLM 4.7 FP8: 202,752 tokens (198K) against 163,840 (160K) for Cogito v2.1 671B.

### Can I fine-tune Cogito v2.1 671B or GLM 4.7 FP8?

Both publish open weights (Cogito v2.1 671B: Not listed; GLM 4.7 FP8: MIT), 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/deepcogito-cogito-v2-1-671b-vs-z-ai-glm-4-7) · [Cogito v2.1 671B](https://allocate.network/models/deepcogito-cogito-v2-1-671b.md) · [GLM 4.7 FP8](https://allocate.network/models/z-ai-glm-4-7.md) · [Machine-readable catalog](https://allocate.network/catalog.json)