This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
China Mobile has launched a newer release, JT-4.1 Flash 236B A21B. We suggest considering it instead.
JT-4.1 Flash 236B A21B 0709: Intelligence, Performance & Price Analysis
Model summary
Performance
Verbosity
JT-4.1 Flash 236B A21B 0709 (Reasoning) supports text and image input, outputs text, and has a 262k tokens context window.
| Input modality | Supports: text and image |
|---|---|
| Output modality | Supports: text |
| Context window | 262k ~393 A4 pages of size 12 Arial font |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Time per Task
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Evaluations
Agentic knowledge work, Elo
Agentic SaaS workflows
Professional document reasoning, All-pass
Agentic coding & terminal use
Agentic real-world work tasks, Elo
Visual reasoning
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| JT-4.1 Flash 236B A21B 0709 (Reasoning) | - | 236B 21B active at inference time | 262k | - | - | - | Not available | - | |
| JT-4.1 Flash 236B A21B 0709 (Non-reasoning) | - | 236B 21B active at inference time | 262k | - | - | - | Not available | - |
More from China Mobile
Frequently Asked Questions
Common questions about JT-4.1 Flash 236B A21B 0709
JT-4.1 Flash 236B A21B 0709 was released on July 9, 2026.
JT-4.1 Flash 236B A21B 0709 was created by China Mobile.
Yes, JT-4.1 Flash 236B A21B 0709 (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer. No, JT-4.1 Flash 236B A21B 0709 (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
JT-4.1 Flash 236B A21B 0709 supports text and image input.
JT-4.1 Flash 236B A21B 0709 supports text output.
Yes, JT-4.1 Flash 236B A21B 0709 supports image input and can analyze, describe, and answer questions about images.
Yes, JT-4.1 Flash 236B A21B 0709 is multimodal. It can process text and image input and generate text output.
JT-4.1 Flash 236B A21B 0709 has a context window of 262k tokens. This determines how much text and conversation history the model can process in a single request.
No, JT-4.1 Flash 236B A21B 0709 is proprietary. The model weights are not publicly available.
JT-4.1 Flash 236B A21B 0709 has 236B parameters.
Check the providers page for current API availability. View providers
Visit the providers page to see availability. Compare providers
