Z.ai · Released Jan 19, 2026
GLM 4.7 Flash
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...
- Released
- Jan 19 2026
- Context window
- 200K 118K out
- Input / 1M tokens
- $0.061 from Free
- Output / 1M tokens
- $0.40 from Free
Where to run it
27 providers compared
Free to try on Zhipu AI, Pendra, AIHubMix, ZenMux, Tempr Gateway +4 more — free endpoints are often limited-time and rate-limited. Cheapest: LLM Gateway, DevPass (LLM Gateway), Deep Infra at $0.06 / $0.40 per 1M input / output tokens — 52% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Zhipu AIfree · may be limited-time | Free | Free | Free | 200K | 131K | — | Free |
| Pendrafree · may be limited-time | Free | Free | — | 200K | 131K | — | Free |
| AIHubMixfree · may be limited-time | Free | Free | — | 200K | 131K | — | Free |
| ZenMuxfree · may be limited-time | Free | Free | Free | 200K | 128K | — | Free |
| Tempr Gatewayfree · may be limited-time | Free | Free | Free | 200K | 131K | — | Free |
| Hugging Facefree · may be limited-time | Free | Free | — | 200K | 128K | — | Free |
| EmpirioLabs AIfree · may be limited-time | Free | Free | — | 200K | 131K | — | Free |
| Z.AIfree · may be limited-time | Free | Free | Free | 200K | 131K | — | Free |
| Kenarifree · may be limited-time | Free | Free | — | 200K | 131K | — | Free |
| LLM Gateway | $0.06 | $0.40 | $0.01 | 200K | 131K | — | Cheapest |
| DevPass (LLM Gateway) | $0.06 | $0.40 | $0.01 | 200K | 131K | — | Cheapest |
| Deep Infra | $0.06 | $0.40 | $0.01 | 203K | 16K | — | Cheapest |
| Cloudflare | $0.061 | $0.40 | — | 131K | 118K | 99.9%24h | +1% |
| Kilo Gateway | $0.061 | $0.40 | — | 131K | 118K | — | +1% |
| Cloudflare Workers AI | $0.061 | $0.40 | — | 131K | 131K | — | +1% |
| NovitaBF16 | $0.07 | $0.40 | $0.01 | 200K | 128K | 17.6%24h | +5% |
| NanoGPT | $0.07 | $0.40 | $0.01 | 200K | 128K | — | +5% |
| Vercel AI Gateway | $0.07 | $0.40 | — | 200K | 131K | — | +5% |
| Novita AI | $0.07 | $0.40 | $0.01 | 200K | 128K | — | +5% |
| Amazon Bedrock | $0.07 | $0.40 | — | 203K | 131K | — | +5% |
| Jiekou.AI | $0.07 | $0.40 | $0.01 | 200K | 128K | — | +5% |
| Merge Gateway | $0.07 | $0.40 | — | 200K | 128K | — | +5% |
| Eden AI | $0.07 | $0.40 | — | 203K | 131K | — | +5% |
| Poe | $0.071 | $0.40 | — | 200K | 66K | — | +6% |
| Cortecs | $0.08 | $0.48 | — | 203K | 203K | — | +24% |
| Synthetic | $0.10 | $0.50 | $0.02 | 197K | 66K | — | +38% |
| AI/ML API | $0.17 | $0.69 | $0.014 | 203K | 16K | — | +108% |
Value
Price vs. performance
GLM 4.7 Flash Other Z.ai Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
2 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions | 60.5% | #94of 122 | Gemini 4 Argon96.4% |
| OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 | 58.3% | #92of 120 | Gemini 4 Argon100.0% |
Specs
Details
- Model ID
z-ai/glm-4.7-flash- Developer
- Z.ai
- Release date
- Jan 19, 2026 ·
- Context window
- 200,000 tokens
- Max output
- 117,964 tokens
- API price
- $0.061 / $0.40 per 1M input / output tokens
- Providers
- 27
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.