Kimi K3 vs GLM-5.2
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Moonshot
|
by Z.AI
3 providers:
Fireworks $1.40/$4.40
Together $1.40/$4.40
Z.AI $1.40/$4.40
|
|---|---|---|
| Overview | ||
| Status | Current flagship Open weights | Current flagship Open weights |
| Released | Jul 16, 2026 | Jun 13, 2026 |
| Pricing per million tokens | ||
| Input | $3.00/Mtok | $1.40/Mtok |
| Output | $15.00/Mtok | $4.40/Mtok |
| Blended avg | $6.00/Mtok | $2.15/Mtok |
| Cached input | $0.300/Mtok | $0.260/Mtok |
| Specifications | ||
| Context window | 1M tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
text
|
| Benchmarks source: Vellum LLM Leaderboard | ||
| Avg benchmark score | 83.3 | 76 |
| Perf / dollar | 13.9 | 35.3 |
| GPQA Diamond | 93.5 | 91.2 |
| SWE-Bench Verified | 93.4 | 45 vendor |
| Terminal-Bench 2.1 | 88.3 | 81 |
| MCP Atlas | 84.2 | 77 |
| Humanity's Last Exam | 56 | 54.7 |
| HumanEval | 76.8 | 84 vendor |
| BrowseComp | 91.2 | — |
| ARC-AGI 2 | — | 30 vendor |
| AIME 2025 | — | 70 vendor |
| MMMLU | — | 80 vendor |
| BFCL | — | 70 vendor |
| MATH 500 | — | 76 vendor |
| AIME 2026 | — | 99.2 |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 59.7 | 52.6 |
| AA Agentic Index | 54.3 | 45.7 |
| AA-Omniscience Index (−100–100) | 19.7 | 4.4 |
| GDPval-AA v2 | 1668 ELO | 1505.2 ELO |
| LMSYS Chatbot Arena | 1485.3 ELO | 1469.4 ELO |
| Providers | ||
| Available from |
Moonshot — $3.00/$15.00/Mtok
|
Fireworks — $1.40/$4.40/Mtok
Together — $1.40/$4.40/Mtok
Z.AI — $1.40/$4.40/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Kimi K3 | GLM-5.2 | Savings |
|---|---|---|---|
| 1M tokens | $6 | $2.15 | $3.85 (64.2%) |
| 10M tokens | $60 | $21.5 | $38.5 (64.2%) |
| 100M tokens | $600 | $215 | $385 (64.2%) |
| 1000M tokens | $6000 | $2150 | $3850 (64.2%) |
When to pick which
distilled from the pricing and spec data above- your workload re-reads context (agents, RAG, long chats): cached input costs $0.300/Mtok — 90% off its list input price
- raw capability matters more than price: 83.3 vs 76 average benchmark score
- cost dominates: $2.15/Mtok blended vs $6.00 — 64.2% less on the same 50/50 token mix
- provider flexibility: available from 3 providers, so you can price-shop hosts or fail over
The cheaper option here — GLM-5.2 costs $2.15/Mtok blended on Z.AI.
Summary
Kimi K3 by Moonshot costs $3.00/Mtok input and $15.00/Mtok output, with a 1M-token context window. It supports text, image input.
GLM-5.2 by Z.AI costs $1.40/Mtok input and $4.40/Mtok output, with a 1M-token context window. It supports text input and is available from 3 providers.
On a blended cost basis, GLM-5.2 is 64.2% cheaper than Kimi K3.
On benchmarks, Kimi K3 scores higher (83.3 vs 76) on average. In terms of value, GLM-5.2 has better performance per dollar (35.3 vs 13.9).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.