← Model list
GLM-4.6
zhipuai·zhipuai/glm-4.6-2·Deprecated·Open weights·glm series
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
At a glance
Official price$0.60 / $2.20 per 1M
Cache read $0.11 · Z.AI
Lowest paid$0.286 / $1.14
302.AI Gateway · 2.1× spread
2 more $0 channels
Context204,800
⚠ Providers report 198,000–204,800; 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 / updated2025-09-30 / 2025-09-30
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning
Intelligence29.3
Value59
Coding45.8
Agentic18.6
Output speed50 tok/s
TTFT2.47 s
Cost per task$0.3046
Value formulaIQ 29.3 ÷ min blended $0.500 = 59
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 23.4 · 55 tok/s
ReasoningIQ 29.3 · 50 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 25 providers22 with public prices · 2 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| iFlow glm-4.6 | Gateway | Free | — | — | 200,000 ⚠ | 128,000 | ||
| ModelScope ZhipuAI/GLM-4.6 | Cloud | Free | — | — | 202,752 ⚠ | 98,304 | ||
| 302.AI glm-4.6 | Gateway | $0.286 | $1.14 | — | — | 204,800 | 131,072 | |
| NanoGPT z-ai/glm-4.6 | Gateway | $0.35 | $1.40 | $0.175 | — | 200,000 ⚠ | 65,535 | |
| ZenMux z-ai/glm-4.6 | Gateway | $0.35 | $1.54 | $0.07 | — | 200,000 ⚠ | 64,000 | |
| IO.NET zai-org/GLM-4.6 | Cloud | $0.40 | $1.75 | $0.20 | $0.80 | 200,000 ⚠ | 4,096 | |
| Venice AI zai-org-glm-4.6 | Gateway | $0.43 | $1.75 | $0.08 | — | 198,000 ⚠ | 16,384 | |
| Ofox z-ai/glm-4.6 | Gateway | $0.40 | $1.90 | $0.11 | — | 204,800 | 131,072 | |
| Meganova zai-org/GLM-4.6 | Gateway | $0.45 | $1.90 | — | — | 202,752 ⚠ | 131,072 | |
| Deep Infra zai-org/GLM-4.6 | Cloud | $0.50 | $2.00 | $0.10 | — | 202,752 ⚠ | 131,072 | |
| Z.AIOfficial glm-4.6 | First-party | $0.60 | $2.20 | $0.11 | $0 | 204,800 | 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
1ZenMux$113.40
2302.AI$114.30
3NanoGPT$119.00
4Venice AI$131.50
5Ofox$140.20
6IO.NET$143.50
15Z.AI · Official$171.20
2 more channels offer $0 (iFlow, ModelScope); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to ZenMux to save $57.80/mo (34%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark4 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 29.5 | index | Source ↗ |
| SciCode | — | 38.4 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 25 | success rate | Source ↗ |
| SWE-Bench Pro | dataset: public | 9.67 | resolve rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
Toggle (on / off)effort = loweffort = mediumeffort = higheffort = none
8 / 25 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 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20
Price historyone sample accumulated per data sync
Input listOutput listMin blended