Model Catalog › zai
GLM-4.6
glm-4.6
CHAT
Mid tier
Reasoning
Open-weight
GLM-4.6 (glm-4.6) is a chat model from zai with a 200K-token context window; open-weight; capabilities tools, reasoning; input text; output text.
200KContext
128KMax output
$0.6$ / 1M in
23Intelligence
69.954tok / s
Pricing
- Input
- $0.6 / 1M tokens
- Output
- $2.2 / 1M tokens
- Currency
- USD
- Note
- Indicative US list price — verify with the vendor.
Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.
Benchmarks
- Intelligence index
- 23
- Math
- 44.3
Cited from a public third-party leaderboard — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-24.
Performance
- Throughput
- 69.954 tokens/s
- Latency (TTFT)
- 0.893 s
Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-22.
Specifications
- Context window
- 200,000 tokens (200K)
- Max output
- 128,000 tokens
- Weights
- Open-weight
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- 2025-04
- Release date
- 2025-09-30
Capabilities
tools reasoning
Provenance
committedlitellmmodels-devoverrides
Last verified: 2026-10-30
Markdown · Vendor JSON · Full catalog · All zai models