2 models · 1,093 observations · under measurement since 2 May
MiniMax M2.5 vs Qwen 3 Coder
Kyma serves all of these, so the availability, throughput and latency below are its own readings rather than anybody's marketing. What each creator publishes about its own model is further down, kept separate, and clearly theirs.
MiniMax M2.5MiniMax
359 obs
since 2 May
270 from Kyma's own probe
Qwen 3 CoderAlibaba
734 obs
since 2 May
254 from Kyma's own probe
Availability, and how much of it we can actually see
Successful observations divided by total observations over the last 30 days, counting Kyma's own probe and real customer requests the same way. Same method and same figures as /models.
MiniMax M2.5Qwen 3 CoderThe tinted band is the measurement's own grain. It is 0.8 points wide, which is what three failed requests are worth in the thinnest sample on this page. One or two is what luck looks like, so a lead has to clear all three before this page will call it. Scale starts at 96%, not at zero, and dot size is the size of the sample behind the figure.
MiniMax M2.5 is ahead at 99.7%, by more than the thinnest sample here could produce by chance on 359 observations.
Throughput
Median tokens per second, from one identical prompt sent to every model every six hours, so the only variable left between two rows is the model.
MiniMax M2.5Qwen 3 CoderLatency
Median time to a complete response on that same fixed prompt. It moves with output length, so it is a reading on one prompt rather than a promise about yours.
MiniMax M2.5Qwen 3 CoderWhat a request costs today, per 1M tokens. A model on offer shows the rate you are actually charged and the date it returns to list.
| Fact | MiniMax M2.5 | Qwen 3 Coder |
|---|---|---|
Input per 1M tokens | $0.3826 | $0.334 |
Output per 1M tokens | $1.346 | $1.519 |
Cached input repeated prefixes | not supported | $0.135 |
The specification each creator publishes for its own model, read straight from the catalogue Kyma serves from. Nothing in this block is a Kyma opinion.
| Fact | MiniMax M2.5 | Qwen 3 Coder |
|---|---|---|
Context window tokens in one request | 197K | 131K |
Max output ceiling on one response | 33K | 33K |
Accepts | Text | Text |
Tool calling | Yes | Yes |
Reasoning | Yes | No |
Vision input | No | No |
Weights | OpenMiniMaxAI/MiniMax-M2.5 | OpenQwen/Qwen3-Coder-480B-A35B-Instruct |
Below release precision narrower than the creator shipped | fp4 | fp4 · fp8 |
What this instrument does not measure
This page carries no benchmark scores, so it will not tell you which model is smarter. It tells you which is cheaper, which is faster, which stays up, and what each one accepts. For the quality question, run both on your own prompts: one key, one line changed, and the answer is about your work rather than someone else's test set.