models: measure the Regolo context windows — all four are 262,144, not 30K/60K/100K

A member read Regolo's own catalogue, where the input-limits column reads 30K for
apertus-70b (and for the MXFP4 gpt-oss models we do not serve from Regolo), 60K for
mistral-small-4-119b and 100K for gemma4-31b, and asked whether >30K input is
possible at all on Regolo. It is: probed through the co-op gateway, every Regolo
chat model we serve accepts 262,144 tokens and rejects above it, so the ceilings are
exact rather than approximate. gemma4-31b and mistral-small-4-119b therefore move
from their catalogued 100K/60K to the measured 262K.

The 'Context figures are measured' paragraph now says what was measured, when, and
how — and names the Regolo catalogue as the source of the smaller numbers, so the
next reader comparing the two does not file the difference as a bug.
This commit is contained in:
inference-admin committed 2026-11-13 18:30:42 +00:00
1 parent 030dd1d5c4
commit 808e54505f
1 file changed
+12 -5
+12 -5
View File
@@ -88,16 +88,23 @@ The emoji in the model name marks its **value tier** (the same icons used in the
| `🌱 greenpt/glm-5.3` | GreenPT | policy | ✅ 100% renewable | — | 1M | $1.10 / $4.40 / $0.275 | GLM flagship — strongest agentic model in the green tier. | | `🌱 greenpt/glm-5.3` | GreenPT | policy | ✅ 100% renewable | — | 1M | $1.10 / $4.40 / $0.275 | GLM flagship — strongest agentic model in the green tier. |
| `🌱 regolo/apertus-70b` | Regolo | policy + ZDR | ✅ 100% renewable | ✅ | 262K | $1.16 / $3.94 / — | Fully open sovereign model (Apache-2.0), large/capable, image understanding. | | `🌱 regolo/apertus-70b` | Regolo | policy + ZDR | ✅ 100% renewable | ✅ | 262K | $1.16 / $3.94 / — | Fully open sovereign model (Apache-2.0), large/capable, image understanding. |
| `🌱 regolo/qwen3.5-122b` | Regolo | policy + ZDR | ✅ 100% renewable | ✅ | 262K | $0.70 / $3.94 / — | Large vision+reasoning MoE (Qwen 3.5, 122B-A10B); 262K context. | | `🌱 regolo/qwen3.5-122b` | Regolo | policy + ZDR | ✅ 100% renewable | ✅ | 262K | $0.70 / $3.94 / — | Large vision+reasoning MoE (Qwen 3.5, 122B-A10B); 262K context. |
| `🌱 regolo/gemma4-31b` | Regolo | policy + ZDR | ✅ 100% renewable | ✅ | 100K | $0.40 / $0.60 / — | Google's dense multimodal Gemma 4 (31B); image input, native function calling. Served from Regolo's EU renewable-powered infrastructure. | | `🌱 regolo/gemma4-31b` | Regolo | policy + ZDR | ✅ 100% renewable | ✅ | 262K | $0.40 / $0.60 / — | Google's dense multimodal Gemma 4 (31B); image input, native function calling. Served from Regolo's EU renewable-powered infrastructure. |
| `🌱 regolo/mistral-small-4-119b` | Regolo | policy + ZDR | ✅ 100% renewable | ✅ | 60K | $0.20 / $0.70 / — | Mistral's hybrid Small 4 (119B) — instruct + reasoning + coding unified; image input, tool calling. Served from Regolo's EU renewable-powered infrastructure. | | `🌱 regolo/mistral-small-4-119b` | Regolo | policy + ZDR | ✅ 100% renewable | ✅ | 262K | $0.20 / $0.70 / — | Mistral's hybrid Small 4 (119B) — instruct + reasoning + coding unified; image input, tool calling. Served from Regolo's EU renewable-powered infrastructure. |
Vision is verified working through the co-op gateway (base64 image input via Vision is verified working through the co-op gateway (base64 image input via
`/v1/chat/completions`, standard OpenAI format). In the chat UI, just attach `/v1/chat/completions`, standard OpenAI format). In the chat UI, just attach
an image to your message while using a ✅ model. an image to your message while using a ✅ model.
Context figures are measured the same way, through the gateway. Where a Context figures are **measured on the served model**, not copied from a
provider's public catalog advertises a smaller limit than the model actually provider's catalogue: a prompt of that size is sent through the gateway and the
accepts, the measured figure is the one shown here. token count is read back. Where the two disagree, the measured figure is the one
shown here — and on Regolo they disagree a lot. Its catalogue advertises a
**30K input limit** for `regolo/apertus-70b`, **60K** for
`regolo/mistral-small-4-119b` and **100K** for `regolo/gemma4-31b`; all four
Regolo chat models the co-op serves accept **262,144 tokens** and reject anything
above it (measured 2026-11-13 by probing at 262,144 and above, so the ceiling is
exact rather than approximate). If a limit matters to you, ask us to probe the
model you intend to use rather than trusting a published number.
**Reading the Privacy column:** *architectural* means the protection is built **Reading the Privacy column:** *architectural* means the protection is built
into the infrastructure (TEE enclaves) — even the provider can't read your into the infrastructure (TEE enclaves) — even the provider can't read your