GLM 5.2 Fast is live on Chutes.
Z.ai's GLM 5.2, for chat and agents where the reply is on the clock. 1M-token context, 128K max output.
Here's what GLM 5.2 is good at, on Z.ai's published scores: 81.0 on Terminal-Bench 2.1, four points behind Opus 4.8 at 85.0, and 62.1 on SWE-bench Pro, up from GLM 5.1's 58.4. Z.ai built it for long-horizon tasks.
Base URL llm.chutes.ai/v1, model zai-org/GLM-5.2-Fast, same key as every other model ofc.
$2.45 per million input tokens, $7.70 out.
Linkz.aiZ.aiFull post on TaosisOpen on X ↗
The settings and chat.z.ai/'s scores on one card.
Model page and pricing: chutes.ai/app/chute/chutes-zai-org-glm-5-2-fast
Linkchat.z.aichat.z.ai/Full post on TaosisOpen on X ↗
Bittensor subnet @chutes_ai has partnered with Tencent Cloud.
Chutes is a launch partner for @TencentHunyuan’s new flagship AI model, Hy4, now available through its API.
Day-one access to leading AI models is business as usual on Bittensor.
Quoting @chutes_ai
Tencent Hy4 is live on Chutes
We’re a launch partner with @TencentHunyuan.
It’s Tencent’s new flagship, and the first Hy model that can see. It reads screenshots and charts, and it can drive a terminal or a desktop app for you.
0.525$ per million tokens in, 1.5625$ out.
Already on Chutes? Just Change the model name to start using it
Try now: chutes.ai/app/chute/chutes-tencent-hy4
Full post on TaosisOpen on X ↗
Taosis newsletters
Taosis News: the week’s articles from the subnet teams, the press and community newsletters, every Friday. Taosis Weekly: the week’s movers, best yields and chain events, with dollar values, every Monday. Past issues
@TencentHunyuan On launch day, @arena put Hy4 on Agent Arena’s cost/performance frontier across 8.5K+ real agent sessions.
It’s within about a point of Kimi K3.1 Pro (Max) and costs roughly 62% less per task.
Tencent says open weights are coming.
Full post on TaosisOpen on X ↗
Tencent Hy4 is live on Chutes
We’re a launch partner with @TencentHunyuan.
It’s Tencent’s new flagship, and the first Hy model that can see. It reads screenshots and charts, and it can drive a terminal or a desktop app for you.
0.525$ per million tokens in, 1.5625$ out.
Already on Chutes? Just Change the model name to start using it
Try now: chutes.ai/app/chute/chutes-tencent-hy4
Linkchutes.aichutes.ai/app/chute/chutes-tencent-hy4Full post on TaosisOpen on X ↗
Last Week in Chutes, week 24. Two weeks of news:
→ Seven new models on Chutes: DeepSeek V4 Pro, DeepSeek V4.1 Flash, Qwen3.8 Max, Qwen3.8 2.4T A95B, GLM 5.3, GLM 5.2 Fast and Kimi K2.7 Code. Same API key, same credits, just a new model id
→ Chutes is now pay as you go. Plus and Pro are gone, and you pay for what you use with credits. Plans you’ve already paid for keep working until the period ends
→ Timon’s essay on why we’re doing this: a pipeline that’s open all the way down, building models efficient enough to run on hardware you own
→ Parallax: dataset prep for the next pretraining run is almost finished. Around 10T tokens of high-quality data. Apple M5 and DGX Spark support are locked in
→ Chutes is live on SayGM, and Tencent Hy4 is on its way
Full write-up below 👇
Quoting @chutes_ai
x.com/i/article/2118353716243996672
Full post on TaosisRead the thread on X →Open on X ↗
Qwen3.8 2.4T A95B is live on Chutes.
It's the open-weights model behind Qwen3.8 Max, and the first Max-class model Qwen has released openly. 2.4T parameters in total with 95B active per token. 262K context, with always on thinking
Qwen publishes its scores under the Qwen3.8 Max name, the API version built on these weights:
- 86.6 on Terminal-Bench 2.1, ahead of Opus 4.8 at 84.6
- 81.9 on WideSearch, ahead of Fable 5 at 81.2 and Opus 4.8 at 72.9
Here's how Qwen describes the difference from Max: text only, with thinking always on and a 262K context against Max's 1M by default. Same price on Chutes for both
$2 per million input tokens, $6 out.
Full post on TaosisOpen on X ↗
Qwen's published scores for Qwen3.8 Max, the API version built on these weights.
Try it here: chutes.ai/app/chute/chutes-qwen-qwen3-8-2-4t-a9…
Linkchutes.aichutes.ai/app/chute/chutes-qwen-qwen3-8-2-4t-a95bFull post on TaosisOpen on X ↗
We’re expanding our model catalog with GLM, DeepSeek, Qwen, and Kimi
We’ve added seven models from Z.ai, DeepSeek, Alibaba’s Qwen team, and Moonshot AI to our catalog. The lineup includes GLM-5.3, DeepSeek V4.1 Flash 1017, and Kimi K2.7 Code, all accessible through our OpenAI-compatible API with an existing key and account credits. You can compare models for coding, research, and agent workflows without setting up a separate provider integration. Regular input prices start at $0.30 per million tokens, with the full lineup and rates below. TL;DR * Seven addit
SN64 Chutes blogsource ↗
We’re expanding our model catalog with GLM, DeepSeek, Qwen, and Kimi
We’ve added seven models from Z.ai, DeepSeek, Alibaba’s Qwen team, and Moonshot AI to our catalog. The lineup includes GLM-5.3, DeepSeek V4.1 Flash 1017, and Kimi K2.7 Code, all accessible through our OpenAI-compatible API with an existing key and account credits. You can compare models for coding, research, and agent workflows without setting up a separate provider integration. Regular input prices start at $0.30 per million tokens, with the full lineup and rates below. TL;DR * Seven addit
SN64 Chutes blogsource ↗
DeepSeek V4.1 Flash is live on Chutes.
Pair it with V4 Pro: route the routine calls to Flash and the hard ones to Pro. Same key, different model id.
Flash is the lighter of the two: 552B parameters, with 8B active per token while it reads and 16B while it writes, against Pro's 1.6T. With the same 1M-token context window
On agent work it holds its own. On DeepSWE v1.1, DeepSeek's published score is 77.0, ahead of Opus 5 at 74.0, and on Agents' Last Exam it tops DeepSeek's table at 35.4. It trails Opus 5 on Terminal-Bench 4.0 (42.3 against 51.8) though, so keep Pro for the longest terminal sessions
$0.30 per million input tokens, $1.20 out.
V4 Pro is $0.85 and $2.65.
Full post on TaosisOpen on X ↗
The pairing on one card. Model page and pricing: chutes.ai/app/chute/chutes-deepseek-ai-deepseek…
Linkchutes.aichutes.ai/app/chute/chutes-deepseek-ai-deepseek-v4-1-flash-1017Full post on TaosisOpen on X ↗
Tencent Hy4 is coming to Chutes 🪂
We're partnering with Tencent Cloud to bring it to the same Chutes API you already use.
Same key, new model ID
More soon 👀
Quoting @TencentHunyuan
4 Real Productivity
Full post on TaosisOpen on X ↗
chat.z.ai/'s published scores, where it leads and where it trails. Try it here: chutes.ai/app/chute/chutes-zai-org-glm-5-3
Linkchat.z.aichat.z.ai/Full post on TaosisOpen on X ↗
GLM 5.3 is live on Chutes.
It's Z.ai's flagship, built on the same base as GLM 5.2 and retrained for complex coding and long agent runs. 1M-token context, open weights.
Here's what to use it for:
- security review: on CyberGym, Z.ai's published score is 84.5, ahead of Fable 5 at 83.8 and Opus 4.8 at 78.1
- coding agents in a terminal: 88.2 on Terminal-Bench 2.1, ahead of Opus 4.8 at 85.0
Over GLM 5.2: 81.0 to 88.2 on Terminal-Bench 2.1, 46.2 to 66.9 on DeepSWE v1.1.
It does trail from Fable 5 and GPT-5.6 Sol on the longest software-engineering runs (66.9 on DeepSWE v1.1 against 69.7 and 72.7) though, so test it on your own repo first.
$1.225 per million input tokens, $3.85 out.
Z.ai's own API lists $1.40 and $4.40.
Linkz.aiZ.aiFull post on TaosisOpen on X ↗
The whole setup on one card. Model page and pricing: chutes.ai/app/chute/chutes-moonshotai-kimi-k2-7…
Linkchutes.aichutes.ai/app/chute/chutes-moonshotai-kimi-k2-7-codeFull post on TaosisOpen on X ↗
Kimi K2.7 Code is live on Chutes.
Base URL llm.chutes.ai/v1
Model moonshotai/Kimi-K2.7-Code
Works with any OpenAI-compatible client, same Chutes key.
Moonshot built it on K2.6 for coding agents: 1T parameters with 32B active per token, a 256K context and open weights. Moonshot says it uses about 30 percent fewer thinking tokens than K2.6, so a job takes fewer tokens.. making it more efficient
$0.83 per million input tokens, $3.50 out.
If you’re looking for a solid coding model at a reasonable price then you should give this one a shot.
Linkllm.chutes.aillm.chutes.ai/v1Full post on TaosisOpen on X ↗
Qwen3.8 Max is live on Chutes.
It's Qwen's 2.4T-parameter flagship, with a 1M-token context, built for coding and long agent tasks.
Here's what to use it for:
- reproducing a paper: on PaperBench, Qwen's published score is 93.0, ahead of GPT 5.6 Sol at 90.5 and Fable 5 at 88.8
- coding agents in a terminal: 86.6 on Terminal-Bench 2.1, ahead of Opus 4.8 at 84.6 in Qwen's table
The 1M-token context takes a big slice of a repo, or a few papers, in one request.
It trails on long software-engineering runs though (56.6 on DeepSWE 1.1 against Fable 5's 70.0), so try it on your own tasks before trusting it with those.
$2 per million input tokens, $6 out. Same rate at any hour.
Full post on TaosisOpen on X ↗
Qwen's published scores, where it leads and where it trails.
Try it here: chutes.ai/app/chute/chutes-qwen-qwen3-8-max-0902
Linkchutes.aichutes.ai/app/chute/chutes-qwen-qwen3-8-max-0902Full post on TaosisOpen on X ↗
Cheap inference gets expensive when it fails.
@OpenRouter has begun routing more traffic toward fast, reliable inference pushing providers to compete on quality.
As a provider, we welcome the competition.
Quoting @OpenRouter
We just shipped our biggest improvement to our provider router since the founding of OpenRouter.
Before, we prioritized mostly based on price. The new router now rewards the best quality inference for the actual cost of a request, so requests stay cheap but are also fast and reliable.
Providers that deliver more value automatically win more traffic, so every provider has a reason to keep improving. And every time a provider gets better, so does your inference on OpenRouter.
Full post on TaosisOpen on X ↗
An open model now sits a tenth of a point behind Fable 5 at coding in a terminal.
That's DeepSeek V4 Pro on Terminal-Bench 2.1: 87.9 against Fable 5's 88.0, with Opus 4.8 at 85.0 (DeepSeek's published scores).
What to use it for:
- a coding agent that runs commands, reads the errors and fixes what broke
- security review, where it tops DeepSeek's Cybergym table at 83.3
Its 1M-token context lets you hand it a big slice of your repo at once, so the agent sees how the pieces connect instead of guessing file by file.
It's weaker on long, multi-step projects (62.7 on DeepSWE against Fable 5's 70.0), so try it on your own tasks before trusting it with those.
On Chutes it's $0.85 in and $2.65 out per million tokens, at any hour.
Model page and pricing: chutes.ai/app/chute/chutes-deepseek-ai-deepseek…
Linkchutes.aichutes.ai/app/chute/chutes-deepseek-ai-deepseek-v4-pro-0813Full post on TaosisOpen on X ↗
DeepSeek V4 Pro is live on Chutes.
It's the big one from DeepSeek's V4 family, with 1.6T parameters and a 1M-token context window. Open weights, MIT licence.
It's strong on agent work. DeepSeek's published score on Terminal-Bench 2.1 is 87.9, ahead of Opus 4.8 at 85.0.
$0.85 per million input tokens, $2.65 out.
Try it here: chutes.ai/app/chute/chutes-deepseek-ai-deepseek…
Linkchutes.aichutes.ai/app/chute/chutes-deepseek-ai-deepseek-v4-pro-0813Full post on TaosisOpen on X ↗
Validator Astrid (5ELR…qwVh) scheduled a child-key change on 18 subnets
Validator hotkey 5ELREhApbCahM7FyGLM1V9WDsnnjCRmMCJTmtQD51oAEqwVh announced new child keys on SN6, SN12, SN13, SN20, SN24, SN31, SN38, SN44, SN50, SN54, SN60, SN62 and 6 more, applying at block 9,393,652 (~24h). Stake delegated to it there routes through its children after that.
ValidatorAstridSubnetsSN6, SN12, SN13, SN20, SN24, SN31, SN38, SN44, SN50, SN54, SN60, SN62, … (18 subnets) Between blocks 9,386,394 and 9,386,452
Chutes is very excited to be working with METANOVA LABS as they develop their Hit-to-Lead optimization agent! We fully intend to assist and support to this project in any way we can as it develops.
Quoting @metanova_labs
NOVA Hit-to-Lead Optimization Agent
In collaboration with @chutes_ai and @onepot_ai
We're developing a Hit-to-Lead optimization agent that integrates an algorithm developed by a NOVA Blueprint winner, extending NOVA's capabilities beyond hit discovery and into the iterative optimization of small molecules.
The system combines a domain-specialized AI agent with proprietary combinatorial chemical databases supplied by our partner Onepot AI, spanning billions of possible compounds, that are delivered within 5-7 business days.
Researchers will be able to guide the agent in developing, comparing and refining optimization strategies, exploring chemical modifications and prioritizing candidates based on predicted affinity, selectivity, physicochemical properties and specific binding interactions.
Confidentiality is a central design requirement. Pharmaceutical R&D involves valuable intellectual property, including compound structures, targets, emerging chemical series and optimization stra
Full post on TaosisOpen on X ↗
Chutes@chutes_ai
