Alibaba · Chat
Qwen 3.8 27B
Qwen 3.8 27B is a 27-billion-parameter instruction-tuned language model from Alibaba's Qwen family, designed for vision, efficient general-purpose text generation and agentic workloads.
- llminfo IQ
- 129.4
- Maker's price
- $1.125 blended / 1M
- Max context
- 1.1M
- Listings
- 238
Evidence and sources
International storefront (alibabacloud.com) is Singapore-incorporated; mainland operating entity 杭州阿里云智能科技有限公司 (Hangzhou).
Advantages and trade-offs
Compared with 10 chat models, picked mainly by popularity and IQ
Advantages
More provider options
Open weights available
The weights are public. 1 of the 9 peers that say either way has open weights.
Input & output
as stated by the model's providersCapabilities
Supported operations and provider-stated features
Listings
| —Not published by the provider | $0.50 | $3.00 | — | — | |
| 262K | $0.00 | $0.00 | — | — | |
| —Not published by the provider | $0.105cache read $0.0525 | $0.63 | — | — | |
| 131K | $0.12 | $1.70 | — | — | |
| 262K | $0.125 | $1.50 | — | — | |
| 262K | $0.125 | $1.50 | — | — | |
| 262K | $0.15cache read $0.0375 | $1.875 | — | — | |
| 262K | $0.15cache read $0.0375 | $1.875 | 23 | 705ms | |
| 262K | $0.15cache read $0.075 | $0.65 | — | — | |
| 262K | $0.15cache read $0.05 | $2.00 | — | — |
Showing 10 of 216: the maker's own listing first, then the cheapest per 1M input tokens from each provider. 47 listings with suspiciously low prices are in the full list only.
Also sold by Adaption, Aiand, Aihubmix, Aimlapi, Akash, Ambient, Apertus, Atlascloud, Berget AI, Cedarllm, Cerebras, Chutes, Cloudflare Workers AI, Commandcode, Core42, Cortecs AI, Crusoe, Darkbloom, DeepInfra, Doubleword, Eden AI, Empiriolabs, Engy, Entrim, Eurouter, Evroc, Featherless AI, Flexai, Fortytwo, Geodd, Gmicloud, Graphn, Groq, Hyper, Ionet, Keln, Kilo, Klavo, Kosmik, Liquid, Llmgateway, Llmgateway Providers, Lyceum, Meganova, Melious, Merge Gateway, Munito, Munito Eu, Near AI, Nebius AI Studio, Neosantara, Neuralwatt, Nous Portal, Novita AI, Obscurify, Ofox, Opper, Orcarouter, OVHcloud, Parasail, Phala, Powerspring, Ppio, Prime, Redpill, Regolo, Runinfra, Scaleway, Siliconflow Cn, Sokkan, Standardcompute, Stepping Stone, Streamlake, Synthetic, T Systems, Tensorix, Tensorx, Thinking Machines, Venice, Vercel, Vultr, Wafer, Wavespeed, Weights & Biases, Zenmux.
22 listings without a price are hidden.
Via subscription
Included in a provider's subscription rather than sold per token. See the plan for what it includes.
Included in plans
Benchmarks
Named effort levels run from lowest to highest. Select a result to see its source details.
Multilingual
| Benchmark | Score |
|---|---|
| AISG SEA-HELM | |
| (Burmese) | |
| (English) | |
| (Filipino) |
Show 5 more benchmarksHide 5 benchmarks
| Benchmark | Score |
|---|---|
| (Indonesian) | |
| (Malay) | |
| (Tamil) | |
| (Thai) | |
| (Vietnamese) |
Show 34 more resultsHide 34 results
Human preference
| Benchmark | Score |
|---|---|
| Arena ELO | |
| Chinese | |
| Creative Writing | |
| English |
Show 53 more benchmarksHide 53 benchmarks
Agentic
Show results from 25 providers and OpenRouter's automatic routingHide results from 25 providers and OpenRouter's automatic routing
- SiliconFlow
- PrimeIntellect
- Near AI
- DekaLLM
- ModelRun
- DeepInfra
- OpenRouter's automatic routing
- Nebius
- AkashML
- Cloudflare
- Chutes
- Reka
- Parasail
- Mancer 2
- Io Net
- Novita
- Ionstream
- Cerebras
- CoreWeave
- Darkbloom
- Modal
- Alibaba
- Wafer
- Phala
- Venice
- Tenstorrent
| Benchmark | Score |
|---|---|
| Tax Agent Bench | |
| Finance Agent (v2) | |
| Harvey's Legal Agent Benchmark v1 | |
| Terminal-Bench 2.1 |
Show 1 more benchmarkHide 1 benchmark
| Benchmark | Score |
|---|---|
| Terminal-Bench-Science |
Coding
Science
Show results from 28 providers and OpenRouter's automatic routingHide results from 28 providers and OpenRouter's automatic routing
- Morph
- Cloudflare
- StreamLake
- Modal
- DekaLLM
- DeepInfra
- SiliconFlow
- Alibaba
- Cerebras
- PrimeIntellect
- Parasail
- Wafer
- Ionstream
- AkashML
- Novita
- CoreWeave
- Chutes
- Nebius
- OpenRouter's automatic routing
- GMICloud
- Mancer 2
- Darkbloom
- Tenstorrent
- Near AI
- Io Net
- ModelRun
- Venice
- Reka
- Phala
Reasoning
General
| Benchmark | Score |
|---|---|
| typos | |
| AMPS_Hard | |
| connections | |
| consecutive_events |
Show 15 more benchmarksHide 15 benchmarks
| Benchmark | Score |
|---|---|
| integrals_with_game | |
| javascript | |
| logic_with_navigation | |
| olympiad | |
| paraphrase | |
| plot_unscrambling | |
| python | |
| simplify | |
| spatial | |
| story_generation | |
| summarize | |
| tablejoin | |
| tablereformat | |
| theory_of_mind | |
| typescript |
Long context
Vision
Math
Instruction following
Knowledge
OCR
Other
| Benchmark | Score |
|---|---|
| Cyber Index | |
| Economics Index | |
| Engineering Index | |
| Finance And Accounting Index |
Show 5 more benchmarksHide 5 benchmarks
| Benchmark | Score |
|---|---|
| Healthcare And Medical Index | |
| Intelligence Index | |
| Legal Index | |
| Openness Index | |
| Strategy And Ops Index |
Show 9 more resultsHide 9 results
Show 2 more resultsHide 2 results
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Bangla LLM Bench, Md Deluair Hossen. Source tasks: Hendrycks et al. 2021 (MMLU), OpenAI MMMLU, Bandarkar et al. 2024 (Belebele), Shi et al. 2023 (MGSM), Nahin et al. 2025 (TituLLMs). Public numeric community results; results licence not separately stated. · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · IdrockBench, IDROCK AI Excellence Center, New Uzbekistan University. Public numeric results; no results licence stated (code MIT and dataset licences not borrowed). · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Outback Yak Research, NepNewsBench v2 research draft. Public numerical aggregates from a candidate preview that the publisher says is not evidence of publication; no release licence assigned and none asserted here. · SWE-bench-Live (Microsoft and contributors), swe-bench-live.github.io. Resolve rates computed from the published report counts. · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted.
Also known as: @cf/qwen/qwen3.8-27b, alibaba/qwen3.8-27b, bailian/qwen3.8-27b, cerebras/qwen-3.8-27b, deepinfra/qwen/qwen3.8-27b, e2ee-qwen-3.8-27b, empiriolabs/qwen3-8-27b, gmi/qwen/qwen3.8-27b, groq/qwen/qwen3.8-27b, hf:qwen/qwen3.8-27b, nebius/qwen/qwen3.8-27b, novita/qwen3.8-27b, parasail-qwen38-27b, phala/qwen3.8-27b, qwen 3.8 27b, qwen-3-8-27b, qwen-3.8-27b, qwen-3.8-27b-flex, qwen-3.8-27b-nvfp4, qwen/qwen3.8-27b, qwen/qwen3.8-27b-fp8, qwen/qwen3.8-27b-tee, qwen/qwen3.8-27b:batch, qwen/qwen3.8-27b:free, qwen/qwen3.8-27b:thinking, qwen3-8-27b, qwen3.8-27b-4bit-mtp, qwen3.8-27b-fast, qwen3.8-27b-fp8, qwen38-27b, streamlake/qwen3.8-27b, tee/qwen3.8-27b, wandb/qwen/qwen3.8-27b
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works