Macaron V1 Venti
Macaron-V1-Venti is the flagship model of Mind AI's Macaron-V1 family, built on GLM-5.2 with four specialist LoRA adapters for chat, personal-agent, coding and generative UI tasks.
- Input / output price
- $0.825 / $2.475 per 1M
- Context
- 1M tokens
- Released
- Jul 21, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Novita novita/macaron-v1-venti | $0.825/M | $2.475/M |
Pricing
USD per 1M tokens on Novita, after gateway discounts.
- Input
- $0.825 per 1M
- Output
- $2.475 per 1M
- Cache read
- $0.165 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better12tokens/sacross providers
Response latency
Lower is better3.7sacross providers
Benchmarks
8 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Terminal-Bench 2.1huggingface.co | 87.6% | huggingface.co | Nov 15, 2026 |
| SWE-bench Verifiedhuggingface.co | 85.6% | huggingface.co | Nov 15, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| ClawGymhuggingface.co | 77.7% | huggingface.co | Nov 15, 2026 |
| tau3-benchhuggingface.co | 69.3% | huggingface.co | Nov 15, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| PinchBenchhuggingface.co | 94% | huggingface.co | Nov 15, 2026 |
| UI4A-Benchhuggingface.co | 87.8% | huggingface.co | Nov 15, 2026 |
| Macaron LivingBenchhuggingface.co | 64% | huggingface.co | Nov 15, 2026 |
| Macaron ChatBenchhuggingface.co | 58.3% | huggingface.co | Nov 15, 2026 |
Apps
Use Macaron V1 Venti in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Macaron V1 Venti FAQ
Short answers, built from the data on this page.
Macaron V1 Venti is a model from Mind Lab, released on Jul 21, 2026. Macaron-V1-Venti is the flagship model of Mind AI's Macaron-V1 family, built on GLM-5.2 with four specialist LoRA adapters for chat, personal-agent, coding and generative UI tasks.
On the Respan gateway, Macaron V1 Venti costs $0.825 per 1M input tokens and $2.475 per 1M output tokens on Novita, after gateway discounts.
Macaron V1 Venti is served by Novita.
Macaron V1 Venti accepts up to 1M tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "macaron-v1-venti". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Macaron V1 Venti has 8 published benchmark scores, including Terminal-Bench 2.1 87.6%, ClawGym 77.7%, and PinchBench 94%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.