Qwen3.8 Flash
inferway/qwen3.8-flashQwen's efficiency-focused Flash model.
- Model input
- TextImage
- Model output
- Text
Zero data retention
Private and affordable Model APIs
Your prompts stay yours. Your bill stays small.
Already have an account?Sign in
POST /v1/chat/completionsbase_urlhttps://api.inferway.ai/v1stream true
01Privacy
Private by construction.
Prompts and completions stay in memory and never touch disk. Request metadata is kept for up to 90 days.
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
Not kept
Content never hits disk; only metadata remains.
02Model & pricing
Curated models, honest prices.
MiMo-V2.6 Flash
Live384K ctxFP8max out 131,072Zero retentionFree · 1,000 req/day
Per token, metered from metadata. No seats, no minimums.
MiniMax H3 768P
Live768pINT8Audio7-day retention
Per second of video ordered. 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…
04Integrate
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 · 90/min · 500/hour · 1,000/day
Use stream=true for long outputs
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
Not for text inference: prompts and completions are processed in memory and never written to disk. Generated videos are kept for 7 days and media you upload for up to 48 hours, so you can use them. We retain request metadata (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.
Docs · Privacy · Transparency