← Model list
GLM-5.1
zhipuai·zhipuai/glm-5.1·Deprecated·Open weights·glm series
Strong GLM coding model for agentic engineering, terminals, and repository generation
At a glance
Official price$1.40 / $4.40 per 1M
Cache read $0.26 · Z.AI
Lowest paid$0.45 / $2.15
CrofAI Gateway · 3.9× spread
5 more $0 channels
Context200,000
⚠ Providers report 163,840–204,800; the table below is authoritative
Output limit131,072
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-04
Released / updated2026-04-07 / 2026-04-07
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning
Intelligence41
Value47
Coding55.8
Agentic30.6
Output speed83 tok/s
TTFT1.53 s
Cost per task$0.3042
Value formulaIQ 41 ÷ min blended $0.875 = 47
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 36.3 · 62 tok/s
ReasoningIQ 41 · 83 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 52 providers46 with public prices · 1 free · 4 subscription-covered
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Alibaba Token Plan | Gateway | Subscription | $0 | $0 | 202,752 ⚠ | 128,000 | ||
| Kenari glm-5-1 | Gateway | Free | — | — | 200,000 | 131,072 | ||
| Zhipu AI Coding Plan | Gateway | Subscription | $0 | $0 | 200,000 | 131,072 | ||
| SCNet Token Plan GLM-5.1 | Gateway | Subscription | $0 | — | 200,000 | 131,072 | ||
| Alibaba Token Plan (China) | Gateway | Subscription | $0 | $0 | 202,752 ⚠ | 128,000 | ||
| CrofAI | Gateway | $0.45 | $2.15 | $0.08 | $0 | 202,752 ⚠ | 202,752 | |
| HPC-AI | Cloud | $0.615 | $2.46 | $0.133 | — | 202,000 ⚠ | 202,000 | |
| NanoGPT | Gateway | $0.75 | $2.60 | $0.15 | — | 200,000 | 131,072 | |
| DevPass (LLM Gateway) | Gateway | $0.931 | $2.93 | $0.173 | $0 | 204,800 ⚠ | 131,072 | |
| EmpirioLabs AI glm-5-1 | Gateway | $0.825 tiered >32K: $1.10 | $3.30 | $0.165 | — | 202,000 ⚠ | 128,000 | |
| Z.AIOfficial | First-party | $1.40 | $4.40 | $0.26 | $0 | 200,000 | 131,072 | |
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
1CrofAI$153.10
2HPC-AI$188.16
3NanoGPT$208.00
4DevPass (LLM Gateway)$241.74
5OpenRouter$250.61
6EmpirioLabs AI$250.85
26Z.AI · Official$363.20
5 more channels offer $0 (Alibaba Token Plan, Kenari, Zhipu AI Coding Plan etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to CrofAI to save $210.10/mo (58%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark4 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Agent Index | harness: Claude Code | 52.7 | average pass@1 | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Claude Code | 73.2 | pass@1 | Source ↗ |
| SWE-Bench Pro | harness: Claude Code · dataset: hard-aa | 19.8 | pass@1 | Source ↗ |
| Terminal-Bench | harness: Claude Code · v2.1 | 65.1 | pass@1 | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
Toggle (on / off)effort = noneeffort = loweffort = mediumeffort = higheffort = minimaleffort = xhigheffort = maxbudget_tokens
18 / 52 providers expose no reasoning control (reasoning_options: []).
Related models
GLM Latestsame series$1.40 / $4.40Z.ai: GLM Latestsame series$1.40 / $4.40GLM 5.3 Preview Thinkingsame series$1.40 / $4.40DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28MiniMax-M2.7cheaper alternative$0.30 / $1.20DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44
Price historyone sample accumulated per data sync
Input listOutput listMin blended