Baichuan M2 32B
Baichuan M2 32B is a 32B medical reasoning model from Baichuan AI, built on Qwen2.5-32B and trained for clinical question answering and diagnostic reasoning.
- Input / output price
- $0.07 / $0.07 per 1M
- Context
- 131K tokens
- Released
- Aug 11, 2025
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/baichuan-m2-32b | $0.07/M | $0.07/M |
Pricing
USD per 1M tokens on Novita, after gateway discounts.
- Input
- $0.07 per 1M
- Output
- $0.07 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Benchmarks
8 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2024huggingface.co | 83.4% | huggingface.co | Sep 2, 2025 |
| AIME 2025huggingface.co | 72.9% | huggingface.co | Sep 2, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| HealthBench-Consensushuggingface.co | 91.5 | huggingface.co | Sep 2, 2025 |
| HealthBenchhuggingface.co | 60.1 | huggingface.co | Sep 2, 2025 |
| HealthBench-Hardhuggingface.co | 34.7 | huggingface.co | Sep 2, 2025 |
| WritingBenchhuggingface.co | 8.56 | huggingface.co | Sep 2, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Arena-Hard v2huggingface.co | 45.8% | huggingface.co | Sep 2, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| CFBenchhuggingface.co | 77.6 | huggingface.co | Sep 2, 2025 |
Apps
Use Baichuan M2 32B 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.
Baichuan M2 32B FAQ
Short answers, built from the data on this page.
Baichuan M2 32B is a model from Baichuan, released on Aug 11, 2025. Baichuan M2 32B is a 32B medical reasoning model from Baichuan AI, built on Qwen2.5-32B and trained for clinical question answering and diagnostic reasoning.
On the Respan gateway, Baichuan M2 32B costs $0.07 per 1M input tokens and $0.07 per 1M output tokens on Novita, after gateway discounts.
Baichuan M2 32B is served by Novita.
Baichuan M2 32B accepts up to 131K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "baichuan-m2-32b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Baichuan M2 32B has 8 published benchmark scores, including AIME 2024 83.4%, HealthBench-Consensus 91.5, and Arena-Hard v2 45.8%. 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.