Cogito v1 Preview Qwen-32B
Released
2025-04-08
Last refreshed
2026-10-07
Status
Researched 191d ago
Open weightsCommercial use: restrictedRAGAgentsLong contextClassificationJSON / Tool use
Deep Cogito releases · 1 in the last 12 monthsChangelog →
Specifications
- Family
- Cogito
- Released
- 2025-04-08
- Context
- 128K
- Parameters
- 32B
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open weights
- License
- Llama 3 CommunityRestricted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Created by
Building general superintelligence through advanced reasoning and iterative self-improvement.
San Francisco, California, United States
Founded 2024
WebsitePricing
Output / 1M
$0.900
Input / 1M
$0.900
Cheapest of 1 route · Fireworks AI
Providers(1)
Created by
Building general superintelligence through advanced reasoning and iterative self-improvement.
San Francisco, California, United States
Founded 2024
WebsitePricing
Output / 1M
$0.900
Input / 1M
$0.900
Cheapest of 1 route · Fireworks AI
Providers(1)
About
Cogito v1 Preview Qwen-32B is a hybrid reasoning model fine-tuned from Qwen 2.5 32B using Iterated Distillation and Amplification (IDA). Supports direct and extended-thinking modes, tool calling, and 30+ languages.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Fireworks AI | $0.900 | $0.900 | Serverless |
Available via routers & gateways(1)
Capabilities
ReasoningJSON / Tool useStructured Outputs
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.