Qwen3.6 35B Flex
neuralwatt/qwen3-6-35b-flexمن neuralwatt · العائلة: qwen · أُصدِر 2026-04-17
⚠ هذا نموذج مُحسَّن من المجتمع أو مشتق — وليس إصدارًا رسميًا من المزود.
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
القدرات
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding73
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)2/20
- Provider availability1/10
Agents91
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability1/10
JSON / structured output98
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume18/20
Cost efficiency68
- Headline price (log-scaled)63/95
- Has prompt-cache pricing5/5
Long context46
- Context window (100K → 2M)36/90
- Has published price for full window10/10
Vision78
- Accepts image input50/50
- Context window (10K → 1M)17/30
- Has published price10/10
- Provider availability1/10
Production-readiness50
- Number of independent providers5/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers10/10
- Official model (not derivative)0/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $1.32 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $2.63 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.75 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $2.26 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $2.71 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
تفاصيل التسعير
السعر المُوصى به من neuralwatt · qwen3.6-35b-flex
متاح لدى 1 مزود
| المزود | معرف نموذج المزود | إدخال / 1M | إخراج / 1M | السياق | تاريخ الإصدار |
|---|---|---|---|---|---|
| Neuralwatt neuralwatt | qwen3.6-35b-flex | $0.189 | $0.748 | 131K | 2026-04-17 |
Frequently asked questions
How much does Qwen3.6 35B Flex cost?
Qwen3.6 35B Flex costs $0.189 per 1M input tokens and $0.748 per 1M output tokens, sourced from neuralwatt. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Qwen3.6 35B Flex?
Qwen3.6 35B Flex has a context window of 131K tokens, with a max output of 131K tokens per reply. This is the total combined size of prompt + completion.
Does Qwen3.6 35B Flex support tool calling?
Yes. Qwen3.6 35B Flex supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Qwen3.6 35B Flex support structured output / JSON mode?
Yes. Qwen3.6 35B Flex supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can Qwen3.6 35B Flex accept image input?
Yes. Qwen3.6 35B Flex accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check neuralwatt's docs for the exact rule.
Is Qwen3.6 35B Flex open-weight?
Yes. Qwen3.6 35B Flex's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
آخر تحديث:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.