Creekside Get a key

Status

Checked from the edge every minute · checking…

API · api.creeksidecompute.ai
Checking readiness…
Website
If you can read this, it is up.
creeksidecompute.ai
Poe · CreeksideCompute
Public, and answers through the API above while Qwen3.8 27B is serving.

Incidents

No incidents recorded.

What "ready" means

The check calls the API's /readyz, the endpoint our own alerting watches. It answers 200 when the API can serve requests and 503 when it cannot. A 503 is either a planned pause, which this page then labels as one, or an outage. Under load a request waits up to 35 seconds for room and then gets a 429 with Retry-After, so a request refused during a busy minute is not an outage.

Measured, and dated

NumberValueWorkloadMeasured
Requests completed in full99.94%All models, real traffic, 7 days; every refusal for load counted as a failure2026-11-09
Speed, each caller108 tok/sQwen3.8 27B, NVFP4, real traffic through the public endpoint, median per request; first token 0.52 s at the median, on prompts of 12,743 tokens at the median2026-11-09
Long prompt, first token34.4 sQwen3.8 27B, a 200,000-token prompt read from cold, through the public endpoint; 100,000 tokens in 12.9 s2026-11-08
Context window1,048,576Qwen3.8 27B, per request; 65,536 output2026-10-23
Speed, each caller98 tok/sGemma 4 31B, NVFP4, real traffic through the public endpoint, median per request; first token 0.69 s at the median, on prompts of 12,367 tokens at the median2026-11-09
Long prompt, first token52.2 sGemma 4 31B, a 250,000-token prompt read from cold, through the public endpoint; 200,000 tokens in 36.0 s2026-11-08
Context window262,144Gemma 4 31B, per request; 65,536 output2026-10-31
Speed, each caller280 tok/sQwen3.6 35B A3B, FP8, real traffic through the public endpoint over 24 hours, median per request; first token 0.43 s at the median2026-11-09
Time to first token188 msQwen3.6 35B A3B, short prompt, one stream, through the public endpoint2026-10-14
Speed, one user320 tok/sQwen3.6 35B A3B, one stream, through the public endpoint2026-10-14
Speed, each of 16 users104 tok/sQwen3.6 35B A3B, users who pause between turns, sent straight to a server with the settings we serve; first token 0.30 s at the median2026-10-14
Speed, each of 32 users68 tok/sQwen3.6 35B A3B, users who pause between turns, sent straight to a server with the settings we serve; first token 0.36 s at the median2026-10-14
Context window1,048,576Qwen3.6 35B A3B, per request; 65,536 output2026-10-23
Time to first token890 msMuse Glimmer 30B, one user in agent sessions, sent straight to a server with the settings we serve; the first token starts its reasoning2026-10-13
Speed, one user63 tok/sMuse Glimmer 30B, one user in agent sessions, sent straight to a server with the settings we serve2026-10-13
Speed, each user at full load41 tok/sMuse Glimmer 30B, users who pause between turns, sent straight to a server with the settings we serve; first token 1.40 s at the median2026-10-14
Context window131,072Muse Glimmer 30B, per request; 65,536 output. A 114,886-token prompt answered correctly in 17.9 s2026-10-14

Every figure on the site comes from a run, or a read of our request records, that we keep; ask for the raw runs and we send them. API reference · Privacy · Content policy