Grok 4.5
xAI released 2026-07-08 proprietary
Gemini 3.7 Flash is both better and cheaper.
It scores +0.2 higher and costs 75% less ($0.750/M against $3.00/M) on this workload — and it does everything this model does.
GLM 5.3 is cheaper still (28% less) but drops no image, file input.
Every price dimension
| Input | $2.00/M |
|---|---|
| Output | $6.00/M |
| Cached input | $0.300/M |
| Web search | $0.005/call |
Past 200,000 tokens the price changes. Input goes to $4.00/M (2×) and output to $12.00/M. The headline rate does not apply to a long-context workload.
Independent scores
| Intelligence | 55.8 |
|---|---|
| Coding | 72.4 |
| Agentic | 48.9 |
| LMArena Elo | 1452.3default |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Best rankings by task
- godotgamedev #3of 43 1270
- androidnative #5of 54 1266
- agenticgamedev #6of 34 1220
- htmlslides #6of 34 1216
- asciiart #7of 83 1294
- mobileapps #7of 56 1260
- python-pptxslides #8of 35 1249
- fullstack #9of 59 1277
Capability
| Context window | 500K |
|---|---|
| Input modes | text, image, file |
| Tool use | yes |
| Reasoning | always on |
| Open weights | no |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
| Cross-checked | vendor page |
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.