← Model list
Grok 4.3
xai·xai/grok-4.3·GA·Closed·grok series
xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk
At a glance
Official price$1.25 / $2.50 per 1M
Cache read $0.20 · xAI
Lowest paid$1.13 / $2.25
Requesty Gateway · 1.3× spread
Context1,000,000
Output limit30,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDFVideo
Knowledge cutoff2024-11
Released / updated2026-04-17 / 2026-04-17
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier high
Intelligence37.9
Value27
Coding42.2
Agentic24.2
Output speed118 tok/s
TTFT20.48 s
Cost per task$0.1454
Value formulaIQ 37.9 ÷ min blended $1.406 = 27
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 25 · 98 tok/s
lowIQ 36.3 · 100 tok/s
mediumIQ 36.9 · 113 tok/s
highIQ 37.9 · 118 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 23 providers22 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Requesty | Gateway | $1.13 tiered >200K: $2.25 | $2.25 | $0.18 | $1.13 | 1,000,000 | 1,000,000 | |
| OrcaRouter | Gateway | $1.25 tiered >200K: $2.50 | $2.50 | $0.20 | — | 1,000,000 | 30,000 | |
| NanoGPT | Gateway | $1.25 | $2.50 | $0.20 | — | 1,000,000 | 1,000,000 | |
| Impossibl | Gateway | $1.25 | $2.50 | $0.20 | — | 1,000,000 | 30,000 | |
| OpenRouter | Gateway | $1.25 tiered >200K: $2.50 | $2.50 | $0.20 | — | 1,000,000 | 1,000,000 | |
| Auriko | Gateway | $1.25 tiered >200K: $2.50 | $2.50 | $0.20 | — | 1,000,000 | 30,000 | |
| DaoXE | Gateway | $1.25 | $2.50 | $0.20 | — | 1,000,000 | 30,000 | |
| CrossModel | Gateway | $1.25 tiered >200K: $2.50 | $2.50 | $0.20 | $1.25 | 1,000,000 | 1,000,000 | |
| Amazon Bedrock xai.grok-4.3 | Cloud | $1.25 | $2.50 | $0.20 | — | 1,000,000 | 131,072 | |
| xAIOfficial | First-party | $1.25 tiered >200K: $2.50 | $2.50 | $0.20 | — | 1,000,000 | 30,000 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1Requesty$224.10
2OrcaRouter$249.00
3NanoGPT$249.00
4Impossibl$249.00
5OpenRouter$249.00
6Auriko$249.00
10xAI · Official$249.00
Switch to Requesty to save $24.90/mo (10%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark4 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index | v4.0 | 53 | index score | Source ↗ |
| GDPval-AA | — | 1500 | Elo | Source ↗ |
| τ²-Bench Telecom | — | 98 | success rate | Source ↗ |
| IFBench | — | 81 | accuracy | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokensToggle (on / off)
5 / 23 providers expose no reasoning control (reasoning_options: []).
Related models
Grok 4.6same series$2.00 / $6.00Grok 4.6 (xAI)same series$2.00 / $6.00Grok 4.6 (AWS Bedrock)same series$2.00 / $6.00DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44MiniMax-M3cheaper alternative$0.30 / $1.20
Price historyone sample accumulated per data sync
Input listOutput listMin blended