Side-by-side comparison
Devstral Small 1.1 vs GLM 4.7 Flash
Mistral
Devstral Small 1.1
🔧 Tools
{} JSON
Input / 1M
$0.1000
Output / 1M
$0.3000
| Devstral Small 1.1 | GLM 4.7 Flash | |
|---|---|---|
| Provider | Mistral | Z.ai |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 131,072 | 202,752 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | tools, json_mode | tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.1000 | 0.0600 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.3000 | 0.4000 |
Frequently asked questions
Which is cheaper, Devstral Small 1.1 or GLM 4.7 Flash?
Devstral Small 1.1 is cheaper than GLM 4.7 Flash on a 50/50 input/output blend by about $0.03 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, Devstral Small 1.1 or GLM 4.7 Flash?
GLM 4.7 Flash has the larger context window at 203k tokens versus 131k tokens for Devstral Small 1.1. That means GLM 4.7 Flash can ingest about 1.5x as much text per request.
What is the difference between Devstral Small 1.1 and GLM 4.7 Flash?
Devstral Small 1.1 comes from Mistral; GLM 4.7 Flash comes from Z.ai. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.