Qwen3.8 Flash
inferway/qwen3.8-flashQwen's efficiency-focused Flash model.
- Model input
- TextImage
- Model output
- Text
Zero data retention
Privacy-first inference Lower costs
Zero data retention: your data is not our data.
or read the quickstartPOST /v1/chat/completionsbase_urlhttps://api.inferway.ai/v1stream true
01
Request sent
TLS-encrypted, straight to a dedicated endpoint.
02
Routed
No shared queue in the path.
03
Inference in memory
Paged KV, never written to disk.
04
Destroyed
Erased on completion; only metadata remains.
02Model & pricing
Curated models, honest prices.
from catalogMiMo-V2.6 Flash
Live262K ctxFP8max out 131,072Zero retention
Per token, metered from metadata. No seats, no minimums.
MiniMax H3 768P
Live768pINT8Audio7-day retention
Per second of video delivered. No seats, no minimums.
Coming soon
DeepSeek V4.1 Flash
inferway/deepseek-v4.1-flashDeepSeek's efficiency-focused V4.1 Flash release.
- Model input
- TextImage
- Model output
- Text
GLM-5.3 Flash
inferway/glm-5.3-flashZ.ai's Flash model for coding and agentic workloads.
- Model input
- TextImage
- Model output
- Text
03Playground
Try it without an account.
Open full Console PlaygroundFree trial — requests are not counted in your account.
Checking live model availability…
04Benchmarks
Numbers are being re-measured.
Measuring nowFirst-token latencypendingMeasured at fixed concurrency
Output throughputpendingTokens per second, single stream
90-day uptimependingPer service, from the status page
Throughput and latency are being re-measured on the current hardware and model. Until that finishes, this section stays empty — we publish measurements with the precision served, concurrency, prompt shape and timestamp attached, or we publish nothing.
05Integrate
Keep your SDK.
Create an accountSign up
no credit cardPoint base_url at Inferway
https://api.inferway.ai/v1Run the streaming smoke test
stream=trueFree use: 8/sec burst · 60/min · 300/hour · 1,000/day
Long outputs require stream=true
Streaming
curl https://api.inferway.ai/v1/chat/completions \
-H "Authorization: Bearer $INFERWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "inferway/mimo-v2.6-flash",
"stream": true,
"messages": [{"role": "user", "content": "Say hello in one short sentence."}]
}'Copy setup for your AI assistant
Paste into Claude Code or Cursor. Key stays in your .env, never in the prompt.Questions
No. Content is never written to disk — inference runs entirely in memory and is destroyed on completion. We retain request metadata only (token counts, timestamps, latency, routing, HTTP status) for up to 90 days, for billing and reliability.
Input tokens that hit the cache are billed at the cache rate rather than the normal input rate, so long shared system prompts and retrieval contexts benefit most. All three rates are the ones shown above, published for the market you are being served. The cache matches whole blocks of tokens, so a short prompt may not hit at all and then bills entirely at the input rate.
Non-streaming requests pass through a CDN with roughly a 100-second first-byte timeout. A long output returns no first byte until generation finishes, so it hits that timeout. With stream=true, bytes start arriving with the first token. Non-streaming is fine for short completions.
You pay per token, metered from request metadata, never from your request content. Pricing and context limits are published on the model catalog and generated from a single catalog source.
Longer answers: Docs · Privacy · Transparency