DeepSeek V3 with Jev
DeepSeek V3 is a model from DeepSeek, released 2024-12-26. It costs $0.257 per million input tokens and $1.03 per million output tokens, reads up to 164K tokens of context, and writes up to 16,000 tokens in one reply. Through llm11, set model to deepseek/deepseek-chat.
- Input price
- $0.257 / 1M
- Output price
- $1.03 / 1M
- Context window
- 164K tokens
- Max output
- 16K tokens
- Released
- 2024-12-26
- Accepts
- text
Read from the live catalogue and refreshed daily. At blended list price, 62% of the 332 priced models we can call cost more.
Using DeepSeek V3 with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. DeepSeek V3 does the answering when Jev sends it work, or when you name it yourself. DeepSeek V3 falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
Jev is new, so we have not published results for DeepSeek V3 with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00033 | $0.334 |
| Question over retrieved documents | 4,000 / 500 | $0.00154 | $1.54 |
| Long document summary | 30,000 / 1,000 | $0.00875 | $8.75 |
Cheaper models to try
The catalogue has no benchmark score for DeepSeek V3, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| OpenAI GPT-5.6 Luna | $0.200 | $1.20 | 1.05M | |
| OpenAI GPT-5.6 Luna Pro | $0.200 | $1.20 | 1.05M | |
| Mistral Codestral 2508 | $0.300 | $0.900 | 256K | |
| Qwen Qwen3.5-35B-A3B | $0.163 | $1.30 | 262K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="deepseek/deepseek-chat",
messages=[{"role": "user", "content": "Hello"}],
)More from DeepSeek
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.300 | $1.20 | 1.05M | |
| DeepSeek V4 Flash Vision Exp | $0.216 | $0.647 | 1.05M | |
| DeepSeek V4 Pro 0813 | $0.480 | $4.20 | 1.05M | |
| DeepSeek V4 Flash 0731 | $0.018 | $0.320 | 1.31M | |
| DeepSeek V4 Flash 0423 | $0.140 | $0.280 | 1.05M | |
| DeepSeek V4 Pro 0423 | $0.955 | $1.91 | 1.05M |
Questions
- What is DeepSeek V3 with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. DeepSeek V3 does the answering when Jev sends it work, or when you name it yourself. DeepSeek V3 falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is DeepSeek V3 a System One model?
- No. DeepSeek V3 answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does DeepSeek V3 cost?
- $0.257 per million input tokens and $1.03 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00154, so a thousand of them is about $1.54. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the DeepSeek V3 context window?
- 163,840 tokens, with up to 16,000 tokens in a single reply.
- Does DeepSeek V3 support tool calling and structured output?
- The catalogue lists tool calling and structured output, but it does not list reasoning controls.
- Can I use DeepSeek V3 through llm11?
- Yes. Set model to deepseek/deepseek-chat on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to DeepSeek V3?
- Routing decisions are made by Jev, TypeSafe AI's System One model. DeepSeek V3 falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
- What is a cheaper alternative to DeepSeek V3?
- Nearest in price and below it: OpenAI GPT-5.6 Luna at $0.200 in and $1.20 out, OpenAI GPT-5.6 Luna Pro at $0.200 in and $1.20 out and Mistral Codestral 2508 at $0.300 in and $0.900 out. The catalogue has no benchmark score for DeepSeek V3, so this is a price ordering. It does not claim these answer as well.