← Model list
Grok 4.5
xai·xai/grok-4.5·GA·Closed·grok series·NEW
xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk
At a glance
Official price$2.00 / $6.00 per 1M
Cache read $0.30 · xAI
Lowest paid$1.80 / $5.40
Requesty Gateway · 1.3× spread
1 more $0 channels
Context500,000
⚠ Providers report 500,000–1,000,000; the table below is authoritative
Output limit500,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDF
Knowledge cutoff—
Released / updated2026-07-08 / 2026-07-08
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier high
Intelligence55.8
Value21
Coding72.4
Agentic48.9
Output speed50 tok/s
TTFT14.03 s
Cost per task$0.3601
Value formulaIQ 55.8 ÷ min blended $2.700 = 21
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 22 providers21 with public prices · 1 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kenari grok-4-5 | Gateway | Free | — | — | 500,000 | 500,000 | ||
| Requesty | Gateway | $1.80 tiered >200K: $3.60 | $5.40 | $0.45 | $1.80 | 500,000 | 500,000 | |
| NanoGPT | Gateway | $2.00 | $6.00 | $0.50 | — | 500,000 | 500,000 | |
| Impossibl | Gateway | $2.00 | $6.00 | $0.30 | — | 500,000 | 500,000 | |
| OpenRouter | Gateway | $2.00 tiered >200K: $4.00 | $6.00 | $0.30 | — | 500,000 | 500,000 | |
| DaoXE | Gateway | $2.00 | $6.00 | $0.50 | — | 500,000 | 500,000 | |
| CrossModel | Gateway | $2.00 tiered >200K: $4.00 | $6.00 | $0.30 | $2.00 | 500,000 | 500,000 | |
| OpenCode Go | Gateway | $2.00 tiered >200K: $4.00 | $6.00 | $0.50 | — | 500,000 | 500,000 | |
| xAIOfficial | First-party | $2.00 tiered >200K: $4.00 | $6.00 | $0.30 | — | 500,000 | 500,000 | |
| Merge Gateway | Gateway | $2.00 | $6.00 | $0.50 | — | 500,000 | 500,000 | |
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$468.00
2Impossibl$496.00
3OpenRouter$496.00
4CrossModel$496.00
5xAI · Official$496.00
6Ofox$496.00
1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to Requesty to save $28.00/mo (6%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark6 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | — | 64.7 | resolve rate | Source ↗ |
| SWE-Bench Multilingual | — | 78 | resolve rate | Source ↗ |
| Terminal-Bench | v2.1 | 83.3 | success rate | Source ↗ |
| DeepSWE | v1.0 | 62 | resolve rate | Source ↗ |
| DeepSWE | harness: mini-swe-agent · v1.1 | 53 | resolve rate | Source ↗ |
| SWE Marathon | — | 29 | pass@1 | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = loweffort = mediumeffort = higheffort = noneeffort = maxbudget_tokens
3 / 22 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 / $6.00Kimi K2.6cheaper alternative$0.95 / $4.00DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28Kimi K2.7 Codecheaper alternative$0.95 / $4.00
Price historyone sample accumulated per data sync
Input listOutput listMin blended