The best open-source LLMs in 2026
The best open-source LLMs right now are MiMo-V2.6-Pro, Qwen3.8-27B and Gemma 4, out of 35 we have reviewed. Each is ranked by our rating, with its price, our verdict and who it suits.
By Andrew Miller · Updated Oct 25, 2026 · How we review
How we ranked: by our rating out of 5, from reviews built on each product's own pricing, documentation and policies plus independent benchmarks where they exist, each checked on the date shown in the review. We take no affiliate commission. Models whose maker has retired the hosted API stay listed for their open weights and are marked.
- 1
Licence and data: Weights under MIT. Xiaomi's MiMo privacy policy says data is stored in Singapore and deleted or anonymised after its retention period; the Desktop app trains on inputs unless you opt out. Third-party gateways report that Xiaomi's API does not train on traffic, which Xiaomi's API terms should confirm.
Running it: $0.435/$0.87 per million tokens with a 99% cache discount and half-price batch. 1,000 agent tasks of 500K input and 30K output tokens cost about $244 uncached; Flash would be about $78.
Price: Open weights under MIT. Xiaomi API: Pro $0.435 input / $0.87 output per 1M tokens, cached input $0.004; Flash $0.14 / $0.28; Pro UltraSpeed $4.35 / $8.70; Batch API half price.
Read our MiMo-V2.6-Pro review4.5/5 - 2
Licence and data: Apache 2.0: commercial use with no revenue caps or acceptable-use annex. Qwen Cloud's listing publishes no retention or training terms, and its sample endpoint is in Singapore (ap-southeast-1).
Running it: Self-hosted: 4-bit 16.5 GB, 8-bit 29 GB, FP8 31 GB, BF16 about 56 GB of weights before KV cache. Hosted: Qwen Cloud $0.50/$3.00 per 1M tokens; OpenRouter providers range from about $0.04/$1.25 to $0.45/$3.20.
Price: Free weights under Apache 2.0. Qwen Cloud: $0.50 input / $3.00 output per 1M tokens ($0.10 cached). Third-party hosts on OpenRouter from about $0.04 / $1.25.
Read our Qwen3.8-27B review4.5/5 - 3
Licence and data: Self-hosted, so data stays where you run it. Apache 2.0 allows commercial use and fine-tuning with no revenue cap or acceptable-use addendum.
Running it: Weights are free. The 31B needs about 62 GB in BF16 (one 80 GB card) or 17.7 GB at 4-bit; 26B A4B is 14.4 GB, 12B 7.0 GB and E4B 5.2 GB at 4-bit. OpenRouter lists 31B at $0.20/$0.40 and 26B A4B at $0.08/$0.26 per 1M tokens.
Price: Free weights under Apache 2.0. Hosted on Google Cloud and third parties; OpenRouter lists 31B at $0.20/$0.40 and 26B A4B at about $0.08/$0.26 per 1M tokens.
Read our Gemma 4 review4.4/5 - 4
Licence and data: Z.ai's API is run from Singapore and its data processing terms say it processes customer data on the customer's behalf; a specific statement on training with API prompts is not published. Self-hosting keeps data in-house.
Running it: Z.ai lists $1.40/$4.40 per 1M tokens with cached input at $0.26 and cache storage free for a limited time. Artificial Analysis puts it at $2.01 per index task, against $0.72 for GPT-6.1 Sol. Self-hosting means about 753 GB of FP8 weights plus cache memory.
Price: Open weights under a modified MIT licence. Z.ai API: $1.40 input / $0.26 cached / $4.40 output per 1M tokens; GLM-5.3-Flash $0.15 / $0.50.
Read our GLM-5.3 review4.4/5 - 5
Licence and data: Open weights are MIT-licensed with no commercial or revenue restrictions. DeepSeek's privacy policy (February 2026) says data is stored in China, lists model training among its uses of user input, and offers opt-out only by emailing privacy@deepseek.com.
Running it: On the API, 1B input tokens a month at 70% cache hits plus 100M output tokens costs about $820 at peak rates or $410 off-peak. Self-hosting needs roughly 865 GB for weights alone, which by our arithmetic means at least an eight-GPU H200 server (1.1 TB of HBM) and more for full 1M-token contexts.
Price: Free MIT-licensed weights. DeepSeek API: $0.66 input / $1.98 output per 1M tokens off-peak, $1.32 / $3.96 at peak; cache hits from $0.022.
Read our DeepSeek-V4-Pro review4.3/5 - 6
Licence and data: Z.ai's API data terms say prompts and outputs are processed in real time and not stored, and customer data is generally processed in Singapore. The terms do not mention training either way, and no SOC 2 or ISO certification is published. Z.ai serves the model on Chinese-made accelerators.
Running it: On Z.ai, 2B input tokens (80% cached) and 200M output tokens a month cost about $208; GLM-5.3 would be about $1,856. Self-hosting means roughly 330 GB of FP8 weights plus KV cache, which is more than four 80 GB GPUs can hold, so plan on an eight-GPU node.
Price: Open weights under MIT. Z.ai API: $0.15 input / $0.50 output per 1M tokens ($0.03 cached); FlashX $0.37 / $1.25.
Read our GLM-5.3-Flash review4.3/5 - 7
Licence and data: Moonshot's privacy policy allows training on user content with no API exemption described, keeps data while the account is active and stores it in Singapore; no SOC 2 or ISO certification is named. The licence exempts internal use from its revenue and display clauses.
Running it: $3/$15 per million tokens, $0.30 cached, with extra charges for 5-minute or 1-hour cache writes. 1,000 agent tasks of 500K input and 30K output tokens cost about $1,950 uncached; Fireworks lists one endpoint at $2.10/$10.50.
Price: Open weights under a modified MIT licence. Kimi API: $3 input / $15 output per 1M tokens; cached input $0.30.
Read our Kimi K3 review4.3/5 - 8
Licence and data: Weights under MIT with no use restrictions. On DeepSeek's service, the privacy policy (updated 10 February 2026) says data is stored in China, kept while the account exists and may train models, with an opt-out on request; no separate API retention terms are published.
Running it: 10 billion input and 1 billion output tokens a month costs about $2,100 off-peak or $4,200 at peak on DeepSeek; cached input is $0.003 per million off-peak. Self-hosting needs over 765 GB of GPU memory for the weights alone.
Price: Free MIT-licensed weights. DeepSeek API: $0.15 input / $0.60 output per 1M tokens off-peak, $0.30 / $1.20 at weekday peak; cache hits $0.003 to $0.006.
Read our DeepSeek-V4.1-Flash review4.2/5 - 9
Licence and data: Weights under Apache 2.0 with no extra conditions. Tencent Cloud's China-site terms say it will not use inputs to improve its own models; retention is not stated publicly. Models from other labs on TokenHub follow their own terms.
Running it: $0.834/$2.501 per million tokens on TokenHub. 1,000 agent tasks of 500K input and 30K output tokens cost about $492 uncached. Self-hosting FP8 needs eight B300-class GPUs.
Price: Open weights under Apache 2.0. Tencent Cloud TokenHub: ¥6 input / ¥18 output per 1M tokens, or $0.834 / $2.501 internationally, cached input $0.042. OpenRouter from about $0.75 / $2.25. Hy3: $0.13 / $0.53.
Read our Hy4 preview review4.2/5 - 10
Licence and data: Qwen Community License 1.0: commercial use allowed; model name must be shown above 100 million monthly users or $20 million monthly revenue; separate licence for model-as-a-service and AI coding or office assistant businesses at any size. Qwen Cloud's retention and training terms are not stated on the model page.
Running it: Hosted: $0.15 input and $0.47 output per million tokens and $0.016 for cache hits; Batch is offered with no published discount. Self-hosted: roughly 360 GB of BF16 or 180 GB of FP8 weights, so a multi-GPU H100 or H200 server before KV cache.
Price: Open weights under the Qwen Community License 1.0 (separate licence for hosting and AI-assistant businesses). Qwen3.8-Flash API: $0.15 input / $0.47 output per 1M tokens; cache hits $0.016.
Read our Qwen3.8-Flash-Next review4.2/5 - 11
Licence and data: Licence allows commercial use; model name must be shown above 100 million monthly users or $20 million monthly revenue; separate licence for model-as-a-service or AI work assistant businesses above $50 million yearly revenue; internal use is exempt. Qwen Cloud's model page does not state retention or training use.
Running it: 10 million input and 2 million output tokens a day, a busy internal assistant, costs about $32 a day or roughly $960 a month at list price; explicit cache reads at $0.17 cut the cost of repeated context by over 90%.
Price: Open weights under the Qwen3.8-Max licence. Qwen Cloud API: $2 input / $6 output per 1M tokens; cache reads $0.17 (explicit) or $0.25 (implicit).
Read our Qwen3.8-Max review4.2/5 - 12
Licence and data: Weights under the StepFun Model License 1.0: display rule above 100M users or $20M monthly revenue, commercial licence for device makers and MaaS businesses over $20M a year, internal use exempt. StepFun's API terms allow training on Startup and early-access programme traffic; terms for other paid traffic are not explicit.
Running it: $1.00/$2.70 per million tokens with 90% off cached input. 1,000 agent tasks of 500K input and 30K output tokens cost about $581 uncached. Self-hosted FP8 needs four B300 or eight H200 GPUs; BF16 needs eight B300 or sixteen H200.
Price: Open weights under the StepFun Model License 1.0. StepFun API: $1.00 input / $2.70 output per 1M tokens, 90% off cached input; same price on OpenRouter and DeepInfra.
Read our Step 5 Preview review4.2/5 - 13
Licence and data: Apache 2.0 with no usage restrictions when self-hosted. On Mistral's API, free-tier inputs and outputs may be used for training unless you opt out; pay-as-you-go users can opt out.
Running it: $0.10 to $0.20 per million tokens on Mistral's API, with batch at half price. Self-hosted, the 14B in FP8 needs one 24 GB GPU; the 3B runs on phones and Jetson boards.
Price: Open weights under Apache 2.0. Mistral API: 14B $0.20, 8B $0.15, 3B $0.10 per 1M tokens, the same for input and output; batch half price.
Read our Ministral 3 (3B, 8B and 14B) review4.1/5 - 14
Licence and data: Apache 2.0 permits commercial use with no revenue cap. Run locally, nothing leaves the machine; on OpenRouter the hosting provider's terms apply. Meta's training data includes information from its own products and services.
Running it: Local: one 24GB card for the 17GB build, 32GB for the near-lossless build, 64GB for full precision. Hosted: $0.30/$1.20 per 1M tokens on DeepInfra, $0.35/$1.50 on Together, so 300M in and 60M out a month is about $162.
Price: Free weights under Apache 2.0; no Meta API. Hosted on OpenRouter from $0.30 per 1M input and $1.20 per 1M output tokens (DeepInfra).
Read our Muse Glimmer review4.1/5 - 15
Licence and data: OpenMDW-1.1 permits commercial use. Self-hosting keeps data in-house; hosted providers set their own retention terms, and OpenRouter does not offer EU in-region routing for this model.
Running it: On OpenRouter's $0.15/$0.50, 1M agent turns a month at 8K input and 1K output tokens comes to about $1,700, before its verbosity inflates output. Self-hosting at BF16 means four H100s per replica; NVFP4 fits a smaller Blackwell footprint.
Price: Free weights under OpenMDW-1.1. Hosted: OpenRouter from $0.15 input / $0.50 output per 1M tokens, plus a free variant; NVIDIA NIM and other providers priced separately.
Read our Nemotron 3.5 Super VL review4.1/5 - 16
Licence and data: Apache 2.0 with no usage restrictions in the licence. Self-hosted, prompts stay on your hardware; hosted, retention follows each provider's terms, and OpenRouter's EU-only routing needs a Business or Enterprise plan.
Running it: 1B input and 250M output tokens a month cost about $300 at $0.15/$0.60 per million; Bedrock batch halves its rate. Self-hosting needs one 80GB GPU for inference and an H100 node to fine-tune.
Price: Free weights under Apache 2.0; hosted prices vary by provider.
Read our gpt-oss-120b review4.0/5 - 17
Licence and data: Apache 2.0, open for commercial and research use with no field-of-use limits; self-hosted prompts stay on your hardware.
Running it: IBM's API charges $0.16 per million input and $0.65 per million output tokens, with a 75% discount on cache hits. Self-hosted, the 30B needs about 18GB at 4-bit or 31GB at 8-bit.
Price: Free weights under Apache 2.0; watsonx and third-party hosting billed separately.
Read our Granite 4.2 review4.0/5 - 18
Licence and data: Weights under MIT, with a public training-content summary. inclusionAI's API privacy and retention terms were not found on its model or OpenRouter pages; self-host for sensitive data.
Running it: At $0.30/$0.90, 1,000 agent tasks of 500K input and 30K output tokens cost about $177 uncached, before its above-average reasoning output. At OpenRouter's listed price, about a quarter of that.
Price: Open weights under MIT. inclusionAI API: $0.30 input / $0.90 output per 1M tokens, cached $0.06, per Artificial Analysis; OpenRouter lists $0.075 / $0.225.
Read our Ling-3.1-flash review4.0/5 - 19
Licence and data: Apache 2.0 for code and weights, with no revenue cap or acceptable-use addendum. Self-hosted only, so prompts stay on your hardware; no Hugging Face inference provider hosts it.
Running it: No hosted price exists, so cost is hardware: about 5 GB of BF16 weights, 2.68 GB at Q8_0 and 1.56 GB at Q4_K_M, which a single consumer GPU or a laptop holds with room for context. OpenBMB publishes no throughput figures to size a fleet.
Price: Free weights and training data under Apache 2.0.
Read our MiniCPM5-2B review4.0/5 - 20
Licence and data: Muse Model License: free use, modification, distillation and redistribution; attribution required in each product; model-as-a-service providers above $20M annual revenue need a separate agreement. Meta claims no ownership of outputs. Self-hosted, nothing leaves your infrastructure.
Running it: Self-hosting: NVFP4 (about 537GB) on one four-GPU Blackwell node, BF16 (about 1.65TB) on eight B300s, or two 512GB M5 Ultra Mac Studios. Hosted, a million support replies a month at 3,000 input and 500 output tokens is about $5,875 at OpenRouter rates.
Price: Free weights under the Muse Model License (attribution required; $20M revenue threshold for model-as-a-service). Hosted on OpenRouter at $1.25 input, $0.15 cached, $4.25 output per 1M tokens.
Read our Muse Spark Open review4.0/5 - 21
Licence and data: Run locally, nothing leaves the machine. The OpenRouter endpoint is served by Recursive; the card says hosted terms and data practices are separate from the weight licence, and we found no published retention terms.
Running it: Weights free. Locally, a Mac or GPU with 48 GB of memory for the 4-bit builds; on servers, one H200 or B300 per BF16 replica (about 80 GB). Hosted: free and rate-limited on OpenRouter; no paid per-token price published.
Price: Free open weights under Apache 2.0; free, rate-limited endpoint on OpenRouter. Paid Flint API for select partners, price not published.
Read our Flint review3.9/5 - 22
Licence and data: Licence: commercial use needs a "Built with MiniMax M3" credit and a notice to MiniMax; products over $20 million in annual revenue need prior written permission; no military use. MiniMax's API retention and training terms were not published on the pages we could read.
Running it: 1M support replies a month at 2,000 input and 300 output tokens each is about $960 on the standard tier, less with cached system prompts. Self-hosting at BF16 needs roughly 850 GB of GPU memory before KV cache: an eight-GPU H200 or B200 node, or more than one H100 node.
Price: Open weights under the MiniMax community licence. API per 1M tokens on prompts up to 512K: $0.30 input, $1.20 output, $0.06 cached; double above 512K; priority tier 1.5x.
Read our MiniMax-M3 review3.9/5 - 23
Licence and data: Self-hosted weights keep data in-house under Apache 2.0. Cohere's API platform is SOC 2 Type II with configurable retention and a training opt-out; private deployments run in your VPC, on-premises or in Model Vault, where Cohere says it has no access.
Running it: Self-hosting needs two H100s or one B200 in W4A4, four H100s in FP8 and eight in BF16. Hosted, 1M RAG answers a month at 8,000 input and 400 output tokens is about $3,000 at OpenRouter's $0.30/$1.50.
Price: Free weights under Apache 2.0. Cohere API rate not published; OpenRouter lists $0.30 input / $1.50 output per 1M tokens. Private deployment by quote.
Read our Command A+ review3.8/5 - 24
Licence and data: Self-hosted, so prompts stay local. Apache 2.0 allows commercial use and fine-tuning; the usage policy only requires compliance with applicable law.
Running it: Weights are free and fit a 16GB GPU. Hosted on OpenRouter from $0.018 input and $0.09 output per 1M tokens, so 1M short replies a month costs well under $100; Artificial Analysis puts it at about $0.01 per index task.
Price: Free weights under Apache 2.0. Hosted from $0.018 input / $0.09 output per 1M tokens on OpenRouter; Artificial Analysis lists $0.07 / $0.25.
Read our gpt-oss-20b review3.8/5 - 25
Licence and data: Modified MIT: usable only if your company's monthly revenue is under $20 million. On Mistral Studio, free-mode inputs and outputs may be used for training, pay-as-you-go customers can opt out, and Vibe trains by default except on Enterprise.
Running it: 1B input and 100M output tokens a month is about $2,250 at list, or about $1,125 with the 50% batch discount; the same load on Large 4 is about $1,778. Self-hosting means about 134 GB of mostly FP8 weights, so four 80 GB GPUs as a floor.
Price: Open weights under a modified MIT licence (no rights for companies above $20M monthly revenue). API: $1.50 per 1M input tokens, $7.50 per 1M output; batch 50% off.
Read our Mistral Medium 3.5 review3.8/5 - 26
Licence and data: Apache 2.0 allows commercial use with no attribution or revenue limits. On Mistral's API, free-tier inputs and outputs may be used for training unless you opt out; pay-as-you-go users can opt out at any time; thumbs-up and thumbs-down feedback is usable on every plan.
Running it: 1M chat replies a month at 1,500 input and 250 output tokens cost about $375 on the API and about $190 in batch. Self-hosting needs two to four H100-class GPUs per replica at FP8, or one DGX B200.
Price: Free weights under Apache 2.0. API: $0.15 input / $0.60 output per 1M tokens; batch 50% off; cached input up to 90% off.
Read our Mistral Small 4 review3.7/5 - 27
Licence and data: Falcon LLM licence: royalty-free, no revenue cap, mandatory attribution, and an acceptable use policy that TII may update and users must monitor.
Running it: Official GGUF files run from 4.6GB at Q4_K_M and 8.1GB at Q8_0 to 15.2GB at BF16, so one 24GB GPU handles production batches; there is no per-token hosted price to compare.
Price: Free weights under the Falcon LLM licence (royalty-free; attribution and acceptable use policy required). No public hosted API listed by Artificial Analysis.
Read our Falcon-H1R-7B review3.6/5 - 28
Licence and data: Self-hosted only, so data stays wherever you run it. There is no first-party API, and so no retention or training terms to review.
Running it: Weights free. BF16 is 250 GB (a multi-GPU node), FP8 133 GB (two 80 GB cards), and NVFP4 (77.7 GB) or Q4_K_M (75.8 GB) the only builds near one 80 GB card; Macs get a 68.7 GB MLX 4-bit build. No first-party hosted price published; NanoGPT lists $0.20 input and $0.80 output per million tokens but marks the model unavailable.
Price: Free open weights under MIT. You pay only for your own hardware or hosting.
Read our Ornith-1.5-122B review3.6/5 - 29
Licence and data: Apache 2.0 allows commercial use, fine-tuning and redistribution with no revenue or user limits. Self-hosting keeps prompts in-house; on OpenRouter it is not available through EU in-region routing, and each host sets its own retention.
Running it: OpenRouter hosts charge $0.39 to $0.75 input and $2.34 to $4.50 output per 1M tokens; hosted Qwen3.5-Plus is $0.30/$1.80. Self-hosting needs about 406 GB for FP8 (an eight-GPU 80 GB server), 214 GB at 4-bit or 180 GB at 3-bit.
Price: Free weights under Apache 2.0; Qwen3.5-Plus on Alibaba Cloud and third-party hosting billed separately.
Read our Qwen3.5-397B-A17B review3.6/5 - 30
Licence and data: Apache 2.0: commercial use and fine-tuning allowed with no revenue cap or acceptable-use addendum. Self-hosted, nothing leaves your servers; the OpenRouter endpoint is run by a third party, Phala, under its own terms.
Running it: BF16 weights are about 62GB (31.2B parameters including embeddings), one 80GB H100; FP8 halves that; a community GGUF build at 11.6GB fits a 16GB card. The only hosted option, OpenRouter's free endpoint, has daily request caps, so production traffic means self-hosting.
Price: Free weights under Apache 2.0. No first-party API; OpenRouter lists a free endpoint (hosted by Phala) under its free-model request caps.
Read our Xing4.0-29B-A4B review3.6/5 - 31
Licence and data: Apache 2.0 with no acceptable-use addendum; commercial use and redistribution allowed. Self-hosted only, so data stays on your device or server. The training data mixture is public, which makes provenance checks possible.
Running it: About 3.1B parameters, roughly 6GB in BF16, so a single consumer GPU, an Apple laptop or a 4-bit phone build. With no paid API listed, cost at volume is your own hardware.
Price: Free weights under Apache 2.0, with the training data recipe and checkpoints published. No hosted API on Hugging Face's own Inference Providers.
Read our SmolLM3-3B review3.5/5 - 32
Hosted API retired Mar 31, 2026; open weights still available
Licence and data: Apache 2.0 with no usage restrictions; self-hosted, so code never leaves your hardware unless you choose a third-party host.
Running it: No first-party API price exists any more; self-hosting means about 24GB of VRAM for the official FP8 weights, 19.3GB at Q6_K or 14.3GB at Q4_K_M, plus memory for the KV cache at long contexts.
Price: Free weights under Apache 2.0. Mistral's API version was retired on March 31, 2026, and Artificial Analysis lists no public API.
Read our Devstral Small 2 review3.4/5 - 33
Licence and data: MIT licence; self-hosting keeps images and prompts local, and Foundry hosting follows Azure's terms.
Running it: Self-hosting needs a GPU with well over 30GB, such as a 48GB A6000 or an 80GB A100; Foundry pricing is not published on the model card.
Price: Free weights under MIT; Microsoft Foundry hosting billed separately.
Read our Phi-4-Reasoning-Vision-15B review3.4/5 - 34
Licence and data: MIT licence with no revenue cap or separate use policy. Self-hosted, audio and images stay on your hardware; Azure's terms apply only if you use Microsoft's hosted endpoint.
Running it: At launch prices on Azure AI Foundry, audio input cost $4 per 1M tokens against $0.08 for text and images, so speech dominates any bill; output was $0.32 per 1M. Current Foundry pricing was not re-verified. Self-hosting needs one recent data-centre GPU.
Price: Free weights under MIT. Azure AI Foundry at launch: $0.08 input / $0.32 output per 1M text or image tokens; audio input $4 per 1M.
Read our Phi-4-multimodal review3.3/5 - 35
Hosted API retired Jul 31, 2026; open weights still available
Licence and data: Modified MIT: no rights for companies above $20M global monthly revenue in the previous month, including for derivatives, and an attribution notice is required. Self-hosted, code stays on your hardware.
Running it: Self-hosting needs about 125 GB for weights, so a four-GPU 80 GB node is the floor before KV cache. On Mistral's API, 1B input and 100M output tokens a month would have cost about $600 at list price.
Price: Open weights under a modified MIT licence (not for companies over $20M monthly revenue). Retired from Mistral's API on July 31, 2026.
Read our Devstral 2 review3.1/5
Sources
The main official source behind each ranked review; every review lists its full set.
- MiMo-V2.6-Pro: Hugging Face: XiaomiMiMo/MiMo-V2.6-Pro-RL model card
- Qwen3.8-27B: Hugging Face: Qwen/Qwen3.8-27B model card
- Gemma 4: Google: Gemma 4, byte for byte the most capable open models
- GLM-5.3: Hugging Face: zai-org/GLM-5.3 model card
- DeepSeek-V4-Pro: Hugging Face: DeepSeek-V4-Pro model card
- GLM-5.3-Flash: Hugging Face: zai-org/GLM-5.3-Flash model card
- Kimi K3: Kimi K3 tech blog: Open Frontier Intelligence
- DeepSeek-V4.1-Flash: Hugging Face: DeepSeek-V4.1-Flash model card
- Hy4 preview: Hugging Face: tencent/Hy4-preview model card
- Qwen3.8-Flash-Next: Hugging Face: Qwen/Qwen3.8-Flash-Next model card
- Qwen3.8-Max: Qwen Cloud: Qwen3.8-Max
- Step 5 Preview: Hugging Face: stepfun-ai/Step-5-Preview model card
- Ministral 3 (3B, 8B and 14B): Mistral AI: Introducing Mistral 3
- Muse Glimmer: Meta: Introducing Muse Glimmer
- Nemotron 3.5 Super VL: Hugging Face: NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 model card
- gpt-oss-120b: Hugging Face: openai/gpt-oss-120b model card
- Granite 4.2: IBM Research: Granite 4.2 brings native reasoning to enterprise agents
- Ling-3.1-flash: Hugging Face: inclusionAI/Ling-3.1-flash model card
- MiniCPM5-2B: Hugging Face: openbmb/MiniCPM5-2B model card
- Muse Spark Open: Meta AI Research: Introducing Muse Spark Open
- Flint: Flint model card (Hugging Face)
- MiniMax-M3: Hugging Face: MiniMaxAI/MiniMax-M3 model card
- Command A+: Cohere docs: Command A+
- gpt-oss-20b: Hugging Face: openai/gpt-oss-20b
- Mistral Medium 3.5: Mistral AI: Remote agents in Vibe, powered by Mistral Medium 3.5
- Mistral Small 4: Mistral AI: Introducing Mistral Small 4
- Falcon-H1R-7B: Hugging Face: tiiuae/Falcon-H1R-7B model card
- Ornith-1.5-122B: Ornith-1.5: From Self-Scaffolding to Self-Improvement
- Qwen3.5-397B-A17B: Hugging Face: Qwen/Qwen3.5-397B-A17B model card
- Xing4.0-29B-A4B: Hugging Face: XingChen-AGI/Xing4.0-29B-A4B model card
- SmolLM3-3B: Hugging Face: HuggingFaceTB/SmolLM3-3B model card
- Devstral Small 2: Hugging Face: mistralai/Devstral-Small-2-24B-Instruct-2512 model card
- Phi-4-Reasoning-Vision-15B: Hugging Face: microsoft/Phi-4-reasoning-vision-15B model card
- Phi-4-multimodal: Hugging Face: microsoft/Phi-4-multimodal-instruct model card
- Devstral 2: Hugging Face: mistralai/Devstral-2-123B-Instruct-2512 model card