Grok 4.20 with Jev
Grok 4.20 is a model from SpaceXAI, released 2026-03-31. It costs $1.25 per million input tokens and $2.50 per million output tokens, reads up to 2M tokens of context, and writes up to 1,800,000 tokens in one reply. Through llm11, set model to x-ai/grok-4.20.
- Input price
- $1.25 / 1M
- Output price
- $2.50 / 1M
- Context window
- 2M tokens
- Max output
- 1.8M tokens
- Cached input
- $0.200 / 1M
- Released
- 2026-03-31
- Accepts
- text, image, file
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 30% of the 332 priced models we can call cost more.
Using Grok 4.20 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. Grok 4.20 does the answering when Jev sends it work, or when you name it yourself. Grok 4.20 falls in the llm11-balanced 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 Grok 4.20 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 | $0.00113 | $1.13 |
| Question over retrieved documents | 4,000 / 500 | $0.00625 | $6.25 |
| Long document summary | 30,000 / 1,000 | $0.040 | $40.00 |
Cheaper models to try
The catalogue has no benchmark score for Grok 4.20, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen Qwen3 Max ThinkingRetires 2026-10-09 | $0.780 | $3.90 | 262K | |
| Qwen Qwen3 MaxRetires 2026-10-09 | $0.780 | $3.90 | 262K | |
| Google Gemini 3.8 Flash | $0.750 | $3.75 | 1.05M | |
| Google Gemini 3.7 Flash | $0.750 | $3.75 | 1.05M |
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="x-ai/grok-4.20",
messages=[{"role": "user", "content": "Hello"}],
)More from SpaceXAI
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Grok 4.7 | $2.00 | $6.00 | 500K | |
| Grok 4.6 | $2.00 | $6.00 | 500K | |
| Grok 4.5 | $2.00 | $6.00 | 500K | |
| Grok Build 0.1 | $1.00 | $2.00 | 256K | |
| Grok 4.3 | $1.25 | $2.50 | 1M | |
| Grok 4.20 Multi-Agent | $1.25 | $2.50 | 2M |
Questions
- What is Grok 4.20 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. Grok 4.20 does the answering when Jev sends it work, or when you name it yourself. Grok 4.20 falls in the llm11-balanced 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 Grok 4.20 a System One model?
- No. Grok 4.20 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 Grok 4.20 cost?
- $1.25 per million input tokens and $2.50 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00625, so a thousand of them is about $6.25. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Grok 4.20 context window?
- 2,000,000 tokens, with up to 1,800,000 tokens in a single reply.
- Does Grok 4.20 support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Grok 4.20 through llm11?
- Yes. Set model to x-ai/grok-4.20 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Grok 4.20?
- Routing decisions are made by Jev, TypeSafe AI's System One model. Grok 4.20 falls in the llm11-balanced 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 Grok 4.20?
- Nearest in price and below it: Qwen Qwen3 Max Thinking at $0.780 in and $3.90 out, Qwen Qwen3 Max at $0.780 in and $3.90 out and Google Gemini 3.8 Flash at $0.750 in and $3.75 out. The catalogue has no benchmark score for Grok 4.20, so this is a price ordering. It does not claim these answer as well.