Qwen: Qwen3.8-Flash-Next
qwen/qwen3.8-flash-nextHugging FaceChatVisionmoereasoningtoolsabliterated
Versions
Every served version of this family. Each has its own providers and prices.
- Qwen: Qwen3.8 Flash Nextqwen/qwen3.8-flash-nextbase$0.015 in$0.035 out1M1 endpoint
- Qwen: Qwen3.8 Flash Next Abliterated (DealignAI)qwen/qwen3.8-flash-next-abliterated$0.015 in$0.035 out1M1 endpoint
Providers
Live endpoints for this model, cheapest first. TTFT is time to first token, measured on streamed requests; response is request to last byte, measured on every request; throughput covers the last day; uptime is measured over the last day and week.
| Provider | Context | Max out | Input | Output | Cache read | TTFT | Response | Throughput | Capacity | Uptime 1d | Uptime 7d | Tools | Reasoning | Health | Data |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ImpCCint490% offbaseUS | 1M | 66K | $0.015 | $0.035 | $0.01 | 463ms30m | 6.42s30m | 20 tok/s | 5/6 free | 95.4% | 73.0% | Verified | Effort | Healthy | ZDR |
| ImpCCnvfp490% offqwen3.8-flash-next-abliteratedUS | 1M | 66K | $0.015 | $0.035 | $0.01 | 4.11s30m | 9.22s30m | 26 tok/s | 6/6 free | 99.1% | 79.9% | Verified | Effort | Healthy | ZDR |
Pricing
USD per million tokens.
| Provider | Input | Output | Cache read |
|---|---|---|---|
| ImpCCint490% offbase | $0.015 | $0.035 | $0.01 |
| ImpCCnvfp490% offqwen3.8-flash-next-abliterated | $0.015 | $0.035 | $0.01 |
Price history
Input price · USD per million tokens
Output price · USD per million tokens
Performance
Timing percentiles cover the labelled window: the last 30 minutes when it has enough samples, otherwise the last day. TTFT is the seconds to the first token, measured only on streamed requests; response is the seconds from request to last byte, measured on every request, streamed or not. Throughput is output tokens per second over the last day, counted only over streamed generations long enough to have a rate — a buffered answer has no generation phase, and a two-token one times the scheduler rather than the model. Tool calls is the share of the last day of tool requests this endpoint answered with a tool call, published once the day holds twenty of them; under that the cell is blank rather than a rate nothing measured.
| Provider | TTFT p50 | p75 | p90 | p99 | Response p50 | p75 | p90 | p99 | Throughput p50 | p75 | p90 | p99 | Tool calls 1d | Runaways 1d |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ImpCCint4base | 463ms30m | 1.26s | 1.80s | 2.42s | 6.42s30m | 21.4s | 22.0s | 627.2s | 20 tok/s | 31 tok/s | 40 tok/s | 45 tok/s | — | 0.0% |
| ImpCCnvfp4qwen3.8-flash-next-abliterated | 4.11s30m | 4.82s | 6.15s | 23.5s | 9.22s30m | 15.1s | 28.8s | 842.0s | 26 tok/s | 37 tok/s | 42 tok/s | 46 tok/s | — | 0.0% |
Time to first token by hour · last 7 days
Hourly median per provider. The line spans hours with no streamed traffic; where samples are sparse, a dot marks each hour actually timed.
Throughput by hour · last 7 days
Hourly median output tokens per second per provider, over generations long enough to have a rate. The line spans hours with no answer long enough to measure; where samples are sparse, a dot marks each hour actually measured.
Uptime
Share of successful requests and probes over the last day and week.
- ImpCCint4base1d 95.4%7d 73.0%Healthy
- ImpCCnvfp4qwen3.8-flash-next-abliterated1d 99.1%7d 79.9%Healthy
Availability by hour · last 7 days
Share of successful requests and probes per hour and provider. The line spans hours with nothing to measure; where samples are sparse, a dot marks each hour actually measured.
Activity
Prompt tokens and completion tokens per UTC day over the last 30 days. Every billed request counts, the platform's own paid probe traffic included.
curl https://api-staging.heimdallm.com/api/v1/chat/completions \ -H "Authorization: Bearer $HEIMDALL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "qwen/qwen3.8-flash-next", "messages": [{ "role": "user", "content": "Hello" }] }'Set HEIMDALL_API_KEY to a key from your account. See the quickstart for routing suffixes and provider preferences.
About
- Author
- Qwen
- Family id
- qwen/qwen3.8-flash-next
- Weights
- Qwen/Qwen3.8-Flash-Next
Qwen: Qwen3.8 Flash NextReleased Aug 27, 2026
Qwen3.8 Flash Next with INT4 weights, text, image and video understanding, preserved reasoning, tool calling and JSON schema output. The shared context window is 1,000,000 tokens using YaRN, with at most 65,536 output tokens per request. One aggregated eight-GPU engine serves it with native prefix caching.
- Parameters
- chat_template_kwargs (object), frequency_penalty (-2–2), guided_choice (list), guided_grammar (text), guided_json (any value), guided_regex (text), ignore_eos (true/false), logprobs (true/false), max_completion_tokens (1–65536), max_tokens (1–65536), min_tokens (0–65536), n (1–4), parallel_tool_calls (true/false), presence_penalty (-2–2), reasoning (object), reasoning_effort (none, low, medium, xhigh), repetition_penalty (>0, ≤2), response_format (object), seed (integer), stop (text or list), structured_outputs (true/false), temperature (0–2), tool_call_dispatch (true/false), tool_choice (none, auto, required or object), tools (list), top_k (-1–2147483647), top_logprobs (0–20; requires logprobs=true), top_p (>0, ≤1)
- Licence
- —
- Size
- 180B parameters, I32 weights
- Tokenizer
- —
- Available until
- —
Qwen: Qwen3.8 Flash Next Abliterated (DealignAI)Released Aug 28, 2026
DealignAI's abliterated Qwen3.8 Flash Next supports text, images and video, reasoning, tool use, and structured JSON. Requests share model cache capacity with a 1,000,000-token context limit per request and up to 65,536 output tokens.
- Parameters
- chat_template_kwargs (object), frequency_penalty (-2–2), guided_choice (list), guided_grammar (text), guided_json (any value), guided_regex (text), ignore_eos (true/false), logprobs (true/false), max_completion_tokens (1–65536), max_tokens (1–65536), min_tokens (0–65536), n (1–4), parallel_tool_calls (true/false), presence_penalty (-2–2), reasoning (object), reasoning_effort (none, low, medium, xhigh), repetition_penalty (>0, ≤2), response_format (object), seed (integer), stop (text or list), structured_outputs (true/false), temperature (0–2), tool_call_dispatch (true/false), tool_choice (none, auto, required or object), tools (list), top_k (-1–2147483647), top_logprobs (0–20; requires logprobs=true), top_p (>0, ≤1)
- Licence
- qwen-community-license-1.0
- Size
- 119.6B parameters, U8 weights
- Tokenizer
- —
- Available until
- —