2 models · 2,735 observations · under measurement since 2 May
GPT-OSS 120B vs Llama 3.3 70B
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.
GPT-OSS 120BOpenAI
639 obs
since 2 May
268 from Kyma's own probe
Llama 3.3 70BMeta
2,096 obs
since 2 May
265 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.
GPT-OSS 120BLlama 3.3 70BThe tinted band is the measurement's own grain. It is 0.5 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 98%, not at zero, and dot size is the size of the sample behind the figure.
No winner here. GPT-OSS 120B, Llama 3.3 70B sit inside the band, so this measurement cannot separate them. The honest claim is that they are all up between 99.4 and 99.4%.
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.
GPT-OSS 120BLlama 3.3 70BLatency
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.
GPT-OSS 120BLlama 3.3 70BWhat 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 | GPT-OSS 120B | Llama 3.3 70B |
|---|---|---|
Input per 1M tokens | $0.0494 | $0.135 |
Output per 1M tokens | $0.2406 | $0.432 |
Cached input repeated prefixes | not supported | not supported |
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 | GPT-OSS 120B | Llama 3.3 70B |
|---|---|---|
Context window tokens in one request | 128K | 128K |
Max output ceiling on one response | 8K | 8K |
Accepts | Text | Text |
Tool calling | Yes | Yes |
Reasoning | No | Yes |
Vision input | No | No |
Weights | Openopenai/gpt-oss-120b | Openmeta-llama/Llama-3.3-70B-Instruct |
Below release precision narrower than the creator shipped | not measured | not measured |
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.