Qwen3.5 397B A17B
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
Updated 2 h ago · first seen 11 Sept 2026
model_01M294WW52DV38H37AY2B8FNDD
- Context
- 262.1K tokens
- T2 · 4 h ago
- Released
- 16 Feb 2026
- T2 · 4 h ago
Specification
- Release date
- 16 Feb 2026
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Openness
- open-weights
Source:Artificial AnalysisT2observed 2 h agomedium
- Context window
- 262.1K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Max output
- 235.9K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Modalities
- image, text, video
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Input modalities
- image, text, video
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Tokenizer
- Qwen3
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Hugging Face repo
- Qwen/Qwen3.5-397B-A17B
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Aa median output tokens per second
- 79
Source:Artificial AnalysisT2observed 2 h agomedium
- Openrouter id
- qwen/qwen3.5-397b-a17b
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
17
Source tiers
T217
Freshest observation
2 h ago
Conflicts
None
Modalities
- Modalities
- imagetextvideo
- Input
- imagetextvideo
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 262.1K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Max output
- 235.9K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Tokenizer
- Qwen3
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 95.61% | pass^1 | aa_slug=qwen3-5-397b-a17b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 19.11 | index | aa_slug=qwen3-5-397b-a17b · version=4.3 · estimated=false | — | artificialanalysis.aiT2 |
| GPQA | 89.29% | accuracy | aa_slug=qwen3-5-397b-a17b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 28.96% | accuracy | aa_slug=qwen3-5-397b-a17b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 78.78% | accuracy | aa_slug=qwen3-5-397b-a17b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| MMMU-Pro | 77.28% | accuracy | aa_slug=qwen3-5-397b-a17b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SciCode | 44.79% | accuracy | aa_slug=qwen3-5-397b-a17b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 0% | accuracy | aa_slug=qwen3-5-397b-a17b · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 51.31% | accuracy | aa_slug=qwen3-5-397b-a17b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 40.91% | accuracy | aa_slug=qwen3-5-397b-a17b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterqwen/qwen3.5-397b-a17b | $0.55 | $3.5 | $0.225 | — | 262.1K | 49 min ago | openrouter.aiT2 |
| Together AIqwen3-5-397b-a17b | $0.60 | $3.6 | $0.35 | — | — | 2 h ago | together.aiT1 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 2
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
- Together AI
No hardware estimate available
Ancestors 0
None recorded.
This model
Qwen3.5 397B A17B
Quantizations 2
Descendants 0
None recorded.
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
Release daterelease_date1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 16 Feb 2026 | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Opennessopenness1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| open-weights | → current | current | Artificial AnalysisT2 | medium | deterministic |
Context windowcontext_length1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 262.1K tokens | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Max outputmax_output_tokens1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 235.9K tokens | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Modalitiesmodalities1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image, text, video | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Input modalitiesmodalities_input1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image, text, video | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Output modalitiesmodalities_output1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Tokenizertokenizer1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Qwen3 | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Hugging Face repohf_repo1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Qwen/Qwen3.5-397B-A17B | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Descriptiondescription1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers... | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Aa median output tokens per secondmetric.aa_median_output_tokens_per_second1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 79 | → current | current | Artificial AnalysisT2 | medium | deterministic |
Openrouter idopenrouter_id1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| qwen/qwen3.5-397b-a17b | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Reasoningreasoning1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Structured outputstructured_output1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Supported parameterssupported_parameters1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Tool callingtool_calling1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Visionvision1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Qwen3.5 397B A17B scores 40.91% on Terminal-Bench
artificial_analysisQwen3.5 397B A17B scores 51.31% on Terminal-Bench
artificial_analysisQwen3.5 397B A17B scores 0% on Terminal-Bench
artificial_analysisQwen3.5 397B A17B scores 95.61% on τ²-bench
artificial_analysisQwen3.5 397B A17B scores 77.28% on MMMU-Pro
artificial_analysisQwen3.5 397B A17B scores 78.78% on IFBench
artificial_analysisQwen3.5 397B A17B scores 44.79% on SciCode
artificial_analysisQwen3.5 397B A17B scores 28.96% on Humanity's Last Exam
artificial_analysisQwen3.5 397B A17B scores 89.29% on GPQA
artificial_analysisQwen3.5 397B A17B scores 19.11 on Artificial Analysis Intelligence Index
artificial_analysisTogether AI lists Qwen3.5 397B A17B at $0.6 in / $3.6 out per 1M tokens
together_pricingOpenRouter lists Qwen3.5 397B A17B at $0.55 in / $3.5 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Together AI — pricing | together.ai/pricing | pricing | T1· Official | 2 h ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 49 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/Intel/Qwen3.5-397B-A17B-int4-AutoRound | model_page | T2· Quality secondary | 2 h ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/amd/Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2 | model_page | T2· Quality secondary | 2 h ago | 3 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 2 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.