Head to head · Open-weight models you run yourself · October 2026 research run
Inkling 2 Mini vs MiMo-V2.6-Flash-RL
Inkling 2 Mini and MiMo-V2.6-Flash-RL score within a point of each other on agent readiness, 61 (C) and 61 (C). MiMo-V2.6-Flash-RL leads on reach. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 6586 open weights comparisons
Which one, for what
Best for Developers with a 32 GB laptop or a single GPU who want a small open agent model with images in and a 1M context, and can run a runtime's pre-release build.
Ahead on
- Risk, 70 against 45
Watch for
No released version of vLLM, SGLang, Transformers, llama.cpp or Ollama runs it on 20 November 2026
Best for Teams with a GPU server, or a provider account, that want an open agent model with a very long context
Ahead on
- Reach, 65 against 60
Watch for
178 GB at 4 bits, so it needs about 200 GB of memory
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Risk Inkling 2 Mini +25
Inkling 2 Mini 70
File safety 25, safetensors only and no repository code to run. Provenance 15, the files are in the organisation Thinking Machines links to, with a SHA-256 on every LFS file. Safety evaluation 10, Thinking Machines' own evaluations and monitorability results, nothing an outside party published or a harness to rerun. Agent guidance 10, the card says what the safety work covered and names safeguards for agent use (a sandbox, confirmation before destructive actions), with nothing on prompt injection. Licence risk 5, 10 off for a use policy that reaches beyond the law and that can change at any time. Security 5, security.txt and a disclosure policy. 25 + 15 + 10 + 10 + 5 + 5 = 70.
MiMo-V2.6-Flash-RL 45
File safety 5, the weights are safetensors, but the dflash folder's mask_embedding.pt is a pickle beside them (15). Provenance 15, the files sit in the XiaomiMiMo organisation, which mimo.xiaomi.com links to per the Distill listing (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions only. Licence risk 15, MIT has no use policy, threshold or change clause. Security programme 5, Xiaomi runs a company security centre for reporting flaws, as read for the Distill listing (5). 5 + 15 + 0 + 5 + 15 + 5 = 45.
Reach MiMo-V2.6-Flash-RL +5
Inkling 2 Mini 60
Memory 25 of 30, ggml-org's IQ4_NL GGUF with its vision projector is 17.98 GB, about 21.6 GB with a fifth added. Runtimes 0, no released version of the six runs the looped architecture; vLLM and SGLang serve it from their own images and llama.cpp has it on master only. Builds 10, one checkpoint from the publisher in mixed NVFP4 and MXFP8. Terms 10, Apache 2.0 with a binding acceptable use policy on top, read as a custom licence. Download 10, no gate. Hosted 5, Thinking Machines' own Tinker samples from it. 25 + 0 + 10 + 10 + 10 + 5 = 60.
MiMo-V2.6-Flash-RL 65
Memory 5, the smallest build at 4 bits or better is ggml-org's MXFP4 GGUF, 168.93 GB with its projector, and 168.93 GB × 1.2 = 202.7 GB, within 256 GB. Xiaomi's own files are 177.74 GB. ggml-org's Q2_K is below 4 bits and isn't read. Runtimes 20, Released vLLM 0.33.0 and SGLang 0.5.23 have the mimo_v2 model and the mimo parsers, Transformers 5.22.2 has a mimo_v2_flash model, and llama.cpp b12242 has the architecture, with a GGUF from its own organisation. Builds 10, one precision from Xiaomi, the 4-bit files it releases. Terms 15, MIT in the card's metadata, an OSI licence. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, the card says it is on Xiaomi's MiMo Open Platform API and on OpenRouter, and Novita is live for it on Hugging Face. 5 + 20 + 10 + 15 + 10 + 5 = 65.
Score by category
| Category | Weight | Inkling 2 Mini | MiMo-V2.6-Flash-RL | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25% | 60 | 65 | MiMo-V2.6-Flash-RL +5 |
| Risk | 20% | 70 | 45 | Inkling 2 Mini +25 |
| Agent interface | 10% | 85 | 85 | even |
| Documentation and upkeep | 10% | 57 | 59 | MiMo-V2.6-Flash-RL +2 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | Inkling 2 Mini | MiMo-V2.6-Flash-RL |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Thinking Machines Lab | Xiaomi (MiMo team) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MIT (metadata only, no LICENSE file) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-11-20 | 2026-10-28 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
Verdicts
Inkling 2 Mini
Thinking Machines' small open model, a looped 26.4B mixture-of-experts with images in, several tool calls a turn and per-request thinking effort, in one 20 GB checkpoint that fits a 32 GB laptop. No released runtime runs it yet, so today it's vLLM's or SGLang's images, llama.cpp from master, or Tinker.
MiMo-V2.6-Flash-RL
A large agent model with an open licence: text, images, video and audio, a 1M context, tool calling it was trained for, and code in four released runtimes. It's a server model, 178 GB at 4 bits, and the card's commands run the repository's code. No safety results, little said about data, and few questions answered.
Before you call either
Inkling 2 Mini
- No released runtime runs it yet. Serve it from vLLM's vllm/vllm-openai:inkling-2-mini image with
--reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling, or from SGLang's lmsysorg/sglang:inkling-2-mini image, where the tool-call parser isinkling2 - On a laptop, ggml-org's GGUF runs in a llama.cpp built after b12591:
llama-server -hf ggml-org/Inkling-2-Mini-GGUF:IQ4_NL. The looped architecture isn't in a llama.cpp release yet - Pass
reasoning_effortas none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99. The minimum doesn't fully turn reasoning off - The card says it can get stuck re-checking its own work, so cap output tokens and agent turns
- Run it in a sandbox and confirm destructive actions: the card says it may delete or overwrite files without asking and misreport what it did
- Tool call arguments must reach the template as an object, not a JSON string, as for Inkling 2 Small
- Images should be 40 to 4096 px a side. It takes no audio, and the template raises an error for an audio part
- Use guided decoding or validate JSON yourself, since structured output isn't documented
- Without the hardware, sample from it on Tinker with the Tinker SDK; Tinker's OpenAI-compatible endpoint doesn't serve it yet
- Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal
MiMo-V2.6-Flash-RL
- Plan for a provider unless you have a multi-GPU server: Xiaomi's API platform, OpenRouter or Novita
- On SGLang or vLLM pass
--tool-call-parser mimo --reasoning-parser mimo - Use temperature 1.0 and top_p 0.95, as the card recommends
- The card's commands pass trust-remote-code. Read the repository's three Python files first, or use Transformers 5.22.2, which has the model built in
- Skip the dflash folder unless you need speculative decoding. Its mask_embedding.pt is a pickle
- The Use Restrictions section asks for human oversight of high-risk actions
Questions
Which is better for AI agents, Inkling 2 Mini or MiMo-V2.6-Flash-RL?
Inkling 2 Mini and MiMo-V2.6-Flash-RL score within a point of each other on agent readiness, 61 (C) and 61 (C). MiMo-V2.6-Flash-RL leads on reach.
Other comparisons with Inkling 2 Mini or MiMo-V2.6-Flash-RL
- Agents-A1-4B vs Inkling 2 Mini
- Agents-A1-4B vs MiMo-V2.6-Flash-RL
- Apertus v1.5 8B vs Inkling 2 Mini
- Apertus v1.5 8B vs MiMo-V2.6-Flash-RL
- Apodex-1.1-mini vs Inkling 2 Mini
- Apodex-1.1-mini vs MiMo-V2.6-Flash-RL
- Arete-27B vs Inkling 2 Mini
- Arete-27B vs MiMo-V2.6-Flash-RL
- BigBang-v1 vs Inkling 2 Mini
- BigBang-v1 vs MiMo-V2.6-Flash-RL
- Carbon-X vs Inkling 2 Mini
- Carbon-X vs MiMo-V2.6-Flash-RL
- Cola2 vs Inkling 2 Mini
- Cola2 vs MiMo-V2.6-Flash-RL
- Cosmos-Reason2-2B vs Inkling 2 Mini
- Cosmos-Reason2-2B vs MiMo-V2.6-Flash-RL
- Darwin-36B-Opus vs Inkling 2 Mini
- Darwin-36B-Opus vs MiMo-V2.6-Flash-RL
- DeepSeek-V3.2 vs Inkling 2 Mini
- DeepSeek-V3.2 vs MiMo-V2.6-Flash-RL
- DeepSeek V4.1 Flash vs Inkling 2 Mini
- DeepSeek V4.1 Flash vs MiMo-V2.6-Flash-RL
- DeepSeek-V4-Flash-0731 vs Inkling 2 Mini
- DeepSeek-V4-Flash-0731 vs MiMo-V2.6-Flash-RL
- Devstral Small 2 vs Inkling 2 Mini
- Devstral Small 2 vs MiMo-V2.6-Flash-RL
- DiffusionGemma 26B A4B IT vs Inkling 2 Mini
- DiffusionGemma 26B A4B IT vs MiMo-V2.6-Flash-RL
- EXAONE 4.5 33B vs Inkling 2 Mini
- EXAONE 4.5 33B vs MiMo-V2.6-Flash-RL
- Gemma 4 12B IT vs Inkling 2 Mini
- Gemma 4 12B IT vs MiMo-V2.6-Flash-RL
- Gemma 4 26B A4B IT vs Inkling 2 Mini
- Gemma 4 26B A4B IT vs MiMo-V2.6-Flash-RL
- Gemma 4 31B IT vs Inkling 2 Mini
- Gemma 4 31B IT vs MiMo-V2.6-Flash-RL
- Gemma 4 E2B IT vs Inkling 2 Mini
- Gemma 4 E2B IT vs MiMo-V2.6-Flash-RL
- Gemma 4 E4B IT vs Inkling 2 Mini
- Gemma 4 E4B IT vs MiMo-V2.6-Flash-RL
- GLM-4.5-Air vs Inkling 2 Mini
- GLM-4.5-Air vs MiMo-V2.6-Flash-RL
- GLM-4.7-Flash vs Inkling 2 Mini
- GLM-4.7-Flash vs MiMo-V2.6-Flash-RL
- GLM-5.3-Flash vs Inkling 2 Mini
- GLM-5.3-Flash vs MiMo-V2.6-Flash-RL
- GLM-5.3 vs Inkling 2 Mini
- GLM-5.3 vs MiMo-V2.6-Flash-RL
- gpt-oss-120b vs Inkling 2 Mini
- gpt-oss-120b vs MiMo-V2.6-Flash-RL
- gpt-oss-20b vs Inkling 2 Mini
- gpt-oss-20b vs MiMo-V2.6-Flash-RL
- Granite 4.2 30B vs Inkling 2 Mini
- Granite 4.2 30B vs MiMo-V2.6-Flash-RL
- Granite 4.2 3B vs Inkling 2 Mini
- Granite 4.2 3B vs MiMo-V2.6-Flash-RL
- Granite 4.2 8B vs Inkling 2 Mini
- Granite 4.2 8B vs MiMo-V2.6-Flash-RL
- Hy-Memory-30B-A3B vs Inkling 2 Mini
- Hy-Memory-30B-A3B vs MiMo-V2.6-Flash-RL
- Hy3 vs Inkling 2 Mini
- Hy3 vs MiMo-V2.6-Flash-RL
- Inkling 2 Mini vs Inkling 2 Small
- Inkling 2 Mini vs Inkling-Small
- Inkling 2 Mini vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Inkling 2 Mini vs Kimi K3
- Inkling 2 Mini vs Kimi K3.1 Pro
- Inkling 2 Mini vs Kolibri-1
- Inkling 2 Mini vs Kronos
- Inkling 2 Mini vs Laguna M.1
- Inkling 2 Mini vs Laguna S 2.1
- Inkling 2 Mini vs Laguna XS 2.1
- Inkling 2 Mini vs LBS-27B
- Inkling 2 Mini vs LFM2.5-2.6B
- Inkling 2 Mini vs LFM3-1.7B
- Inkling 2 Mini vs LFM3-Audio-2B
- Inkling 2 Mini vs LFM3-Omni-2B
- Inkling 2 Mini vs LFM3-VL-2B
- Inkling 2 Mini vs Ling-3.0-tiny
- Inkling 2 Mini vs Ling-3.1-flash-1019
- Inkling 2 Mini vs LongCat-2.5
- Inkling 2 Mini vs MiMo-V2.6 Distill Qwen 9B
- Inkling 2 Mini vs MiniCPM-o 4.5
- Inkling 2 Mini vs MiniCPM-V 4.7 1B
- Inkling 2 Mini vs MiniCPM-V 4.7 35B-A3B
- Inkling 2 Mini vs MiniCPM5-2B
- Inkling 2 Mini vs MiniMax-M2.5
- Inkling 2 Mini vs MiniMax-M2.7
- Inkling 2 Mini vs MiniMax-M3.1-Flash
- Inkling 2 Mini vs Mistral Large 4
- Inkling 2 Mini vs Muse Glimmer 30B
- Inkling 2 Mini vs Nanbeige4.2-3B
- Inkling 2 Mini vs Nanbeige4.3-33B
- Inkling 2 Mini vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Inkling 2 Mini vs Nemotron 3.5 Lightning 30B A3B
- Inkling 2 Mini vs Nemotron 3 Nano 30B A3B
- Inkling 2 Mini vs Nemotron 3 Nano 4B
- Inkling 2 Mini vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Inkling 2 Mini vs Nemotron 3 Super 120B A12B
- Inkling 2 Mini vs Nemotron 3 Ultra 550B A55B
- Inkling 2 Mini vs North Mini Code 1.0
- Inkling 2 Mini vs occamy-1.0
- Inkling 2 Mini vs Olmo 3 7B Think
- Inkling 2 Mini vs Ornith-1.5-122B
- Inkling 2 Mini vs Ornith-1.5-35B-A3B
- Inkling 2 Mini vs Ornith-1.5-397B
- Inkling 2 Mini vs Ornith-1.5-9B
- Inkling 2 Mini vs OTel-2.0-LLM-31B-IT
- Inkling 2 Mini vs Qwen-AgentWorld-35B-A3B
- Inkling 2 Mini vs Qwen3-30B-A3B-Instruct-2507
- Inkling 2 Mini vs Qwen3-4B-Instruct-2507
- Inkling 2 Mini vs Qwen3.5-0.8B
- Inkling 2 Mini vs Qwen3.5-122B-A10B
- Inkling 2 Mini vs Qwen3.5-2B
- Inkling 2 Mini vs Qwen3.5-397B-A17B
- Inkling 2 Mini vs Qwen3.5-4B
- Inkling 2 Mini vs Qwen3.5-9B
- Inkling 2 Mini vs Qwen3.6-27B
- Inkling 2 Mini vs Qwen3.6-35B-A3B
- Inkling 2 Mini vs Qwen3.8-27B
- Inkling 2 Mini vs Qwen3.8-Flash-Next
- Inkling 2 Mini vs Qwen3-Coder-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-Coder-Next
- Inkling 2 Mini vs Qwen3-Omni-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-VL-2B-Instruct
- Inkling 2 Mini vs Qwen3-VL-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-VL-32B-Instruct
- Inkling 2 Mini vs Qwen3-VL-4B-Instruct
- Inkling 2 Mini vs Qwen3-VL-8B-Instruct
- Inkling 2 Mini vs Qwopus3.8-27B-Flash-V2
- Inkling 2 Mini vs Recursive Flint
- Inkling 2 Mini vs Ripple-65B Preview
- Inkling 2 Mini vs SenseNova-Loop-9B-Preview
- Inkling 2 Mini vs SmolLM3-3B
- Inkling 2 Mini vs Spark-X2.6-4B
- Inkling 2 Mini vs Step 3.7 Flash
- Inkling 2 Mini vs Swift 1.5 Qwen3.8-27B
- Inkling 2 Mini vs Swift 1.5 Qwen3.8-Flash-Next
- Inkling 2 Mini vs ThinkingCap (Qwen3.8 27B)
- Inkling 2 Mini vs Baidu Unlimited-OCR-2
- Inkling 2 Mini vs WeVisOne-VL-2B
- Inkling 2 Mini vs WeVisOne-VL-4B
- Inkling 2 Mini vs ZAYA1-8B
- Inkling 2 Small vs MiMo-V2.6-Flash-RL
- Inkling-Small vs MiMo-V2.6-Flash-RL
- Inkling vs Inkling 2 Mini
- Inkling vs MiMo-V2.6-Flash-RL
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiMo-V2.6-Flash-RL
- Kimi K3.1 Pro vs MiMo-V2.6-Flash-RL
- Kimi K3 vs MiMo-V2.6-Flash-RL
- Kolibri-1 vs MiMo-V2.6-Flash-RL
- Kronos vs MiMo-V2.6-Flash-RL
- Laguna M.1 vs MiMo-V2.6-Flash-RL
- Laguna S 2.1 vs MiMo-V2.6-Flash-RL
- Laguna XS 2.1 vs MiMo-V2.6-Flash-RL
- LBS-27B vs MiMo-V2.6-Flash-RL
- LFM2.5-2.6B vs MiMo-V2.6-Flash-RL
- LFM3-1.7B vs MiMo-V2.6-Flash-RL
- LFM3-Audio-2B vs MiMo-V2.6-Flash-RL
- LFM3-Omni-2B vs MiMo-V2.6-Flash-RL
- LFM3-VL-2B vs MiMo-V2.6-Flash-RL
- Ling-3.0-tiny vs MiMo-V2.6-Flash-RL
- Ling-3.1-flash-1019 vs MiMo-V2.6-Flash-RL
- LongCat-2.5 vs MiMo-V2.6-Flash-RL
- MiMo-V2.6 Distill Qwen 9B vs MiMo-V2.6-Flash-RL
- MiMo-V2.6-Flash-RL vs MiniCPM-o 4.5
- MiMo-V2.6-Flash-RL vs MiniCPM-V 4.7 1B
- MiMo-V2.6-Flash-RL vs MiniCPM-V 4.7 35B-A3B
- MiMo-V2.6-Flash-RL vs MiniCPM5-2B
- MiMo-V2.6-Flash-RL vs MiniMax-M2.5
- MiMo-V2.6-Flash-RL vs MiniMax-M2.7
- MiMo-V2.6-Flash-RL vs MiniMax-M3.1-Flash
- MiMo-V2.6-Flash-RL vs Mistral Large 4
- MiMo-V2.6-Flash-RL vs Muse Glimmer 30B
- MiMo-V2.6-Flash-RL vs Nanbeige4.2-3B
- MiMo-V2.6-Flash-RL vs Nanbeige4.3-33B
- MiMo-V2.6-Flash-RL vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- MiMo-V2.6-Flash-RL vs Nemotron 3.5 Lightning 30B A3B
- MiMo-V2.6-Flash-RL vs Nemotron 3 Nano 30B A3B
- MiMo-V2.6-Flash-RL vs Nemotron 3 Nano 4B
- MiMo-V2.6-Flash-RL vs Nemotron 3 Nano Omni 30B A3B Reasoning
- MiMo-V2.6-Flash-RL vs Nemotron 3 Super 120B A12B
- MiMo-V2.6-Flash-RL vs Nemotron 3 Ultra 550B A55B
- MiMo-V2.6-Flash-RL vs North Mini Code 1.0
- MiMo-V2.6-Flash-RL vs occamy-1.0
- MiMo-V2.6-Flash-RL vs Olmo 3 7B Think
- MiMo-V2.6-Flash-RL vs Ornith-1.5-122B
- MiMo-V2.6-Flash-RL vs Ornith-1.5-35B-A3B
- MiMo-V2.6-Flash-RL vs Ornith-1.5-397B
- MiMo-V2.6-Flash-RL vs Ornith-1.5-9B
- MiMo-V2.6-Flash-RL vs OTel-2.0-LLM-31B-IT
- MiMo-V2.6-Flash-RL vs Qwen-AgentWorld-35B-A3B
- MiMo-V2.6-Flash-RL vs Qwen3-30B-A3B-Instruct-2507
- MiMo-V2.6-Flash-RL vs Qwen3-4B-Instruct-2507
- MiMo-V2.6-Flash-RL vs Qwen3.5-0.8B
- MiMo-V2.6-Flash-RL vs Qwen3.5-122B-A10B
- MiMo-V2.6-Flash-RL vs Qwen3.5-2B
- MiMo-V2.6-Flash-RL vs Qwen3.5-397B-A17B
- MiMo-V2.6-Flash-RL vs Qwen3.5-4B
- MiMo-V2.6-Flash-RL vs Qwen3.5-9B
- MiMo-V2.6-Flash-RL vs Qwen3.6-27B
- MiMo-V2.6-Flash-RL vs Qwen3.6-35B-A3B
- MiMo-V2.6-Flash-RL vs Qwen3.8-27B
- MiMo-V2.6-Flash-RL vs Qwen3.8-Flash-Next
- MiMo-V2.6-Flash-RL vs Qwen3-Coder-30B-A3B-Instruct
- MiMo-V2.6-Flash-RL vs Qwen3-Coder-Next
- MiMo-V2.6-Flash-RL vs Qwen3-Omni-30B-A3B-Instruct
- MiMo-V2.6-Flash-RL vs Qwen3-VL-2B-Instruct
- MiMo-V2.6-Flash-RL vs Qwen3-VL-30B-A3B-Instruct
- MiMo-V2.6-Flash-RL vs Qwen3-VL-32B-Instruct
- MiMo-V2.6-Flash-RL vs Qwen3-VL-4B-Instruct
- MiMo-V2.6-Flash-RL vs Qwen3-VL-8B-Instruct
- MiMo-V2.6-Flash-RL vs Qwopus3.8-27B-Flash-V2
- MiMo-V2.6-Flash-RL vs Recursive Flint
- MiMo-V2.6-Flash-RL vs Ripple-65B Preview
- MiMo-V2.6-Flash-RL vs SenseNova-Loop-9B-Preview
- MiMo-V2.6-Flash-RL vs SmolLM3-3B
- MiMo-V2.6-Flash-RL vs Spark-X2.6-4B
- MiMo-V2.6-Flash-RL vs Step 3.7 Flash
- MiMo-V2.6-Flash-RL vs Swift 1.5 Qwen3.8-27B
- MiMo-V2.6-Flash-RL vs Swift 1.5 Qwen3.8-Flash-Next
- MiMo-V2.6-Flash-RL vs ThinkingCap (Qwen3.8 27B)
- MiMo-V2.6-Flash-RL vs Baidu Unlimited-OCR-2
- MiMo-V2.6-Flash-RL vs WeVisOne-VL-2B
- MiMo-V2.6-Flash-RL vs WeVisOne-VL-4B
- MiMo-V2.6-Flash-RL vs ZAYA1-8B
Machine-readable
- This page as Markdown
/compare/inkling-2-mini-vs-mimo-v2-6-flash-rl.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/inkling-2-mini.json·/api/v1/tools/mimo-v2-6-flash-rl.json - From a terminal
anchor compare inkling-2-mini mimo-v2-6-flash-rl(the CLI) - Over MCP
compare_tools {"a": "inkling-2-mini", "b": "mimo-v2-6-flash-rl"}at/mcp, no key