Free DeepSeek model via API
Updated:
Free endpoints for V4 Flash, V4 Pro, R1, and DeepSeek coding variants. The catalog shows where the model is served at a zero token price.
Read more
Reasoning routes burn quota faster than instruct. Confirm the selected provider's cap before production use.
6 models found
| № | Model | Power | Provider | Parameters | Context | Limit | |
|---|---|---|---|---|---|---|---|
| 📌 |
OpenCode GO
|
$60 in monthly API credits for $10, covering DeepSeek, Qwen, GLM, and other models. Introductory first-month offer available. |
Open | ||||
| 1 |
DeepSeek R1 Distill Qwen 7B
|
⚡ | Together AI | 7B | 131K | Fair Use (По мере нагрузки серверов) | Open |
| 2 |
Deepseek OCR 2
|
⚖️ | Together AI | ? | 8K | Fair Use (По мере нагрузки серверов) | Open |
| 3 |
DeepSeek: DeepSeek V4 Flash (Free)
|
🚀 | OrcaRouter | ? | ? | Free tier | Open |
| 4 |
Deepseek Coder 6.7b Instruct
|
⚡ | NVIDIA Build | 6.7B | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 5 |
Deepseek V4.1 Flash
|
🚀 | NVIDIA Build | ? | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 6 |
Deepseek R1 Distill QWEN 32b
|
⚖️ | UnoRouter | 32B | 80K | No-card free models use shared capacity and per-model limits; availability can change. | Open |