Gemini 3 Flash Preview vs GLM-5.2
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Google
|
by Z.AI
3 providers:
Fireworks $1.40/$4.40
Together $1.40/$4.40
Z.AI $1.40/$4.40
|
|---|---|---|
| Overview | ||
| Status | Preview flagship | Current flagship Open weights |
| Released | Dec 17, 2025 | Jun 13, 2026 |
| Pricing per million tokens | ||
| Input | $0.500/Mtok | $1.40/Mtok |
| Output | $3.00/Mtok | $4.40/Mtok |
| Blended avg | $1.13/Mtok | $2.15/Mtok |
| Cached input | $0.050/Mtok | $0.260/Mtok |
| Specifications | ||
| Context window | 1M tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimageaudiovideo
|
text
|
| Benchmarks sources: Artificial Analysis, Google model card, Google model card (no tools) / Vellum LLM Leaderboard | ||
| GPQA Diamond | 90.4 vendor | 91.2 |
| SWE-Bench Verified | 78 vendor | 45 vendor |
| Humanity's Last Exam | 33.7 vendor | 54.7 |
| Avg benchmark score | — | 76 |
| Perf / dollar | — | 35.3 |
| Terminal-Bench 2.1 | — | 81 |
| MCP Atlas | — | 77 |
| ARC-AGI 2 | — | 30 vendor |
| AIME 2025 | — | 70 vendor |
| MMMLU | — | 80 vendor |
| BFCL | — | 70 vendor |
| HumanEval | — | 84 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 | 27 | 52.6 |
| LMSYS Chatbot Arena | 1472.8 ELO | 1469.4 ELO |
| AA Agentic Index | — | 45.7 |
| AA-Omniscience Index (−100–100) | — | 4.4 |
| GDPval-AA v2 | — | 1505.2 ELO |
| Providers | ||
| Available from |
Google — $0.500/$3.00/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 | Gemini 3 Flash Preview | GLM-5.2 | Savings |
|---|---|---|---|
| 1M tokens | $1.13 | $2.15 | $1.02 (47.4%) |
| 10M tokens | $11.25 | $21.5 | $10.25 (47.7%) |
| 100M tokens | $112.5 | $215 | $102.5 (47.7%) |
| 1000M tokens | $1125 | $2150 | $1025 (47.7%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $1.13/Mtok blended vs $2.15 — 47.7% less on the same 50/50 token mix
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.050/Mtok — 90% off its list input price
- you want open weights — self-host it, fine-tune it, or exit the API entirely; Gemini 3 Flash Preview is closed
- provider flexibility: available from 3 providers, so you can price-shop hosts or fail over
The cheaper option here — Gemini 3 Flash Preview costs $1.13/Mtok blended on Google.
Summary
Gemini 3 Flash Preview by Google costs $0.500/Mtok input and $3.00/Mtok output, with a 1M-token context window. It supports text, image, audio, video 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, Gemini 3 Flash Preview is 47.7% cheaper than GLM-5.2.It also has a larger context window.
The two aren't directly comparable on average benchmark score: GLM-5.2 has published per-benchmark results, while Gemini 3 Flash Preview does not yet — it is measured today on independent composites (see the table above).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.