SylphxModels

Qwen

35B A3b family · v3.6

Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b

Qwen3.6 35B A3B on Sylphx AI · 262K of context. One Responses contract, with list prices published per million tokens.

Released
Apr 27, 2026 · 171 days old
Context
262,144 tokens
Get an API keySee a request sampleRead the docs
Input $0.248 / MOutput $1.485 / MCached input $0.05775 / MFull rate sheet
Context window262,144tokens per request
Max output65,536tokens per response
Input$0.248 / Mper million tokens
Output$1.485 / Mper million tokens
Cached input$0.05775 / M77% off input
ReleasedApr 27, 2026171 days old

Pricing

USD per million tokens
Input
$0.248
Output
$1.485
Cached input
$0.05775

$0.56 for 750,000 input and 250,000 output tokens.

Assumption: one batch of 750,000 input plus 250,000 output tokens at the published list prices — recompute for your own mix. Blended $0.5573 per million at a 3:1 mix.

Chat replies · 3:1 input:output
$0.5573 / M
Long documents · 9:1 input:output
$0.3717 / M
Heavy output · 1:1 input:output
$0.8665 / M
Cache write
$0.248 / M
Currency and unit
USD / million tokens

Cached input reads cost 77% less than fresh input tokens.

Full rate sheet and billing rules.

Specification

Context window
262,144 tokens
Max output
65,536 tokens
Input modalities
Not published
Output modalities
Not published
Family
35B A3b
Version
v3.6
Provider
Alibaba (Qwen)
Released
Apr 27, 2026 · 171 days old
Model id
qwen/qwen3.6-35b-a3b

Data posture

Standard

By default, prompts and outputs sent to this model are not used to train models. Training-discount lanes only with opt-in (x-sylphx-zdr: optional).

Training on what you send · default
No
Zero Data Retention · default
Not available
Training-discount options
Opt-in only · x-sylphx-zdr: optional
curl https://api.sylphx.ai/v1/responses \
  -H "Authorization: Bearer $SYLPHX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.6-35b-a3b",
    "input": "Summarise this incident report in three bullets.",
    "stream": false
  }'

How to call it

Send the official Responses document to the base URL above with your Sylphx API key and this exact model id. Streaming arrives as ordered events with one terminal event.

  • Retries: send an Idempotency-Key and a retry replays the original response instead of billing twice.
  • Errors: typed envelopes tell you whether to retry, wait, or fix the request.
  • Keys: create and revoke Sylphx API keys in the Sylphx console.

Independent evaluation

We do not publish benchmark scores for this model — we have not verified any. These external leaderboards run their own tests, so check them against your own workload.

Not our numbers