xAI's fastest model with 2M token context window. Optimized for speed without reasoning overhead, supporting text and image inputs with function calling and structured outputs.
Grok 4.1 Fast is TheRouter's compatibility page for xai/grok-4-1-fast-non-reasoning, a fast xAI chat route with text+image input, tool calling, structured outputs, and a 2-million-token context window in TheRouter's catalog. The crucial disclosure is lifecycle status: xAI's May 15, 2026 migration guide lists the upstream grok-4-1-fast-non-reasoning slug as retired and redirected to grok-4.3.
Treat this route as a legacy compatibility surface, not a fresh recommendation for new deployments. Existing applications pinned to the TheRouter model id can use the page to compare route shape, pricing, latency expectations, and migration risk before moving to xai/grok-4.3 or a pinned 2M-context alternative such as xai/grok-4.20-non-reasoning.
The non-reasoning label matters operationally. Unlike xai/grok-4-1-fast-reasoning, this row does not expose TheRouter's reasoning parameter and is best understood as the speed-oriented sibling for extraction, classification, and tool-dispatch steps where the orchestrator handles deeper reasoning elsewhere.
xai/grok-4-1-fast-non-reasoning that need a stable model id while validating successor behaviorxai/grok-4.3 before choosing a retired 4.1 fast slugxAI retired the upstream grok-4-1-fast-non-reasoning slug on May 15, 2026 and redirects it to grok-4.3; the vendor does not present it as a current standalone model with a separate model card.
TheRouter still exposes xai/grok-4-1-fast-non-reasoning as a listed compatibility model id with TheRouter catalog pricing, 2M context, text+image input, tools, and structured outputs. Customers should validate behavior before treating it as equivalent to the successor.
| Type | Rate |
|---|---|
| Input | $0.324 / 1M tokens |
| Output | $0.810 / 1M tokens |
| TheRouter model ID | xai/grok-4-1-fast-non-reasoning | verified |
| Upstream slug status | Retired by xAI on May 15, 2026 and redirected to grok-4.3docs.x.ai ↗ | verified |
| Context window | 2,000,000 tokens on TheRouter | verified |
| Input modalities | Text, image | verified |
| Output modalities | Text | verified |
| Reasoning parameter | Not exposed on this non-reasoning TheRouter model row | verified |
| Structured outputs | Supported through response_format on TheRouter | verified |
| TheRouter pricing | $0.30 input / $0.75 output per 1M tokens on TheRouter | verified |
| Training cutoff | Not publicly disclosed for this retired slug | unknown |
| License | Proprietary | verified |
| Benchmark | Distribution | Score | Source |
|---|---|---|---|
Exact retired slug benchmarks xAI documents the slug retirement and redirect but does not publish standalone benchmark scores for Grok 4.1 Fast non-reasoning. | — | Not publicly disclosed | — |
Successor comparison guidance The upstream redirect target is `grok-4.3`; current benchmark comparisons should be made against the successor page, not copied onto this retired alias. | — | Not publicly disclosed | — |
TheRouter route shape Vendor docs confirm xAI capability concepts, while TheRouter's catalog supplies this active model row. No paid live verification was run in this scheduled pass. | — | Not publicly disclosed | — |
Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.
curl https://api.therouter.ai/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer $THE_ROUTER_API_KEY" -d '{
"model": "xai/grok-4-1-fast-non-reasoning",
"messages": [
{"role": "user", "content": "Summarize the key points from this input."}
]
}'Use the OpenAI-compatible chat completions endpoint with the TheRouter model id. Keep this snippet for compatibility tests; prefer current xAI successors for new builds.
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xai/grok-4-1-fast-non-reasoning",
"messages": [
{"role": "system", "content": "Be concise and flag uncertainty."},
{"role": "user", "content": "Summarize the migration risks in this plan."}
]
}'The May migration guide lists grok-4-1-fast-non-reasoning among retired API model names. For TheRouter users, that makes this page a compatibility and migration reference rather than a fresh-model launch page.
Not as an upstream xAI slug. xAI's migration guide says the original grok-4-1-fast-non-reasoning name was retired and redirects to grok-4.3. TheRouter still lists its own compatibility model id, so validate behavior before assuming exact equivalence.
Choose it when latency and simple execution matter more than deep reasoning: extraction, classification, formatting, or tool dispatch controlled by a separate planner. For hard analysis or explicit reasoning controls, use xai/grok-4-1-fast-reasoning, xai/grok-4.20-reasoning, or the current successor xai/grok-4.3.
Because the exact upstream slug is documented as retired and xAI does not publish a standalone benchmark table for it. Copying Grok 4.3 scores onto the retired alias would mislead readers, so this page records the evidence gap instead.
| source | URL | retrieved | |
|---|---|---|---|
| TheRouter model ID | — | — | verified |
| Upstream slug status | docs.x.ai ↗ | 2026-08-11 | verified |
| Context window | — | — | verified |
| Input modalities | — | — | verified |
| Output modalities | — | — | verified |
| Reasoning parameter | — | — | verified |
| Structured outputs | — | — | verified |
| TheRouter pricing | — | — | verified |
| Training cutoff | — | — | unknown |
| License | — | — | verified |
| Exact retired slug benchmarks | docs.x.ai ↗ | 2026-08-11 | unknown |
| Successor comparison guidance | docs.x.ai ↗ | 2026-08-11 | unknown |
| TheRouter route shape | docs.x.ai ↗ | 2026-08-11 | unknown |
| xAI retires Grok 4.1 fast slugs and redirects them to Grok 4.3 | docs.x.ai ↗ | 2026-08-11 | verified |
| Is xai/grok-4-1-fast-non-reasoning still a current xAI model? | docs.x.ai ↗ | 2026-08-11 | to verify |
| Why are there no exact benchmark scores on this page? | docs.x.ai ↗ | 2026-08-11 | to verify |