Grok 4.20 0309 Non Reasoning API
xAI's Grok 4.20 0309 Non Reasoning costs $1.250 per million input tokens and $2.499 per million output tokens from 1 independent provider. Each request through the OpenAI-compatible API goes to the offer with the lowest estimated charge that meets your rules.
- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send grok-4.20-0309-non-reasoning as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.
About Grok 4.20 0309 Non Reasoning
Grok 4.20 0309 Non Reasoning is a language model from xAI. Its release date is 9 March 2026. Grok model for agentic tool use, reasoning, coding, and live assistance. Its weights are not public. It takes text and images and gives text. The largest offer takes 200,000 input tokens. 1 independent provider quotes it on this exchange now.
Description, release date and licence: models.dev (https://models.dev/)
Facts
- Model name
- grok-4.20-0309-non-reasoning
- Maker
- xAI
- Context window
- 200K tokens
- Input price
- $1.250 per million tokens
- Output price
- $2.499 per million tokens
- Providers
- 1 independent provider
- Regions
- us
Providers
- Architect: us, $1.250 input and $2.499 output per million tokens, $0.200 cache read per million tokens, 200K tokens of context
Scores
- HLE: 24.5, #139 of 465
- GPQA: 78.5, #173 of 432
- AA-LCR: 25.3, #342 of 409
- Terminal-Bench Hard: 22.0, #153 of 311
- τ²-Bench: 69.6, #133 of 313
- IFBench: 47.8, #150 of 321
Scores: Artificial Analysis (https://artificialanalysis.ai/)
Request
curl https://router.inference.ai.exchange/v1/chat/completions \
-H "Authorization: Bearer $LIQUID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-4.20-0309-non-reasoning",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is Grok 4.20 0309 Non Reasoning?
- Grok 4.20 0309 Non Reasoning is a language model from xAI. Its release date is 9 March 2026. Grok model for agentic tool use, reasoning, coding, and live assistance. Its weights are not public.
- How much does Grok 4.20 0309 Non Reasoning cost?
- Offers now ask $1.250 per million input tokens and $2.499 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
- What is the context length of Grok 4.20 0309 Non Reasoning?
- The largest offer takes 200,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can Grok 4.20 0309 Non Reasoning do?
- Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does Grok 4.20 0309 Non Reasoning support?
- Text · Images → Text.
- Which providers serve Grok 4.20 0309 Non Reasoning?
- 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
- How do I call Grok 4.20 0309 Non Reasoning?
- Send "grok-4.20-0309-non-reasoning" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was Grok 4.20 0309 Non Reasoning released?
- Its creator released it on 9 March 2026.
- When was Grok 4.20 0309 Non Reasoning listed?
- The exchange first listed it on 10/10/2026. This is not its release date.
Related pages
- Grok 4 Fast
- Grok 3 Mini Latest
- Grok 4.1 Fast
- Grok 4.1 Fast Reasoning Latest
- Grok 4 Fast Non Reasoning
- Grok 4.1 Fast Non Reasoning Latest
- Set up a client
- All models
- Providers
- Discover the best model for your budget
- Quickstart
- llms.txt: the index of every page, as Markdown
- llms-full.txt: every page in one file
- This page as Markdown