New API offers an API service for accessing GLM big models. The platform is designed and developed by New API, with the website hosted at open.glmbigmodel.me. It provides endpoints for interacting with large language models, suitable for applications requiring AI-powered text generation and processing.
A third-party API relay providing access to GLM/ChatGLM models through OpenAI-compatible endpoints.
- Models
- 140 models
- From
- $0.0083/M
- Speed
- 52 tok/s
- Updated
- 7/10/2026
- Latency
- 0.00 s
- Created At
- 12/7/2025
- Recharge Rate
- ¥1.00 per $1 quota
Features
DrawingTaskData Export
Login Methods
GitHubLinuxDO
API Endpoints
- Endpoint 1Historical / Unverified
https://api.985100.xyz - Cloudflare Optimized Route
https://api.galaxy-grocery.comPreferred route
- EdgeOne Route
https://open.glmbigmodel.meBackup route
- Direct Connection
https://image.galaxy-grocery.comUse for image requests and other long-lived connections
- Cloudflare Optimized Route
https://api.glmbigmodel.meWill be decommissioned in September
- Direct Connection
https://image.glmbigmodel.meWill be decommissioned in September
Claim this provider
Verify ownership to unlock provider management features:
- Edit provider name, content, and links
- Get featured with priority traffic and visibility boost
- Display a verified badge to build user trust
Leaderboard Rankings
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
About GLM BigModel Relay
Health Check
100%Recent availability
History (72 pts)
PastNow
API Benchmarks & Pricing
Compare 80 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
xai/grok-4other | $1.25/M | $6.25/M |
xai/grok-4-fastother | $0.083/M | $0.208/M |
xai/grok-4.1-thinkingother | $1.25/M | $6.25/M |
gpt-image-2other | $0.050/request | - |
gpt-image-2image | $0.100/request | - |
| $0.200/request | - | |
| $0.200/request | - | |
glm-5.2other | $0.208/M | $0.917/M |
agnes-video-v2.0other | $0.050/request | - |
agnes-image-2.1-flashother | $0.0100/request | - |
agnes-image-2.0-flashother | $0.0083/request | - |
MiniMax-M3other | $0.250/M | $1.000/M |
qwen/qwen3.7-maxother | $1.04/M | $3.12/M |
grok-4.3-fastother | $0.521/M | $1.04/M |
grok-4.3-lowother | $0.521/M | $1.04/M |
mimo-v2-omniother | $0.167/M | $0.833/M |
mimo-v2-proother | $0.417/M | $1.25/M |
qwen/qwen3.5-plusother | $0.333/M | $2.00/M |
deepseek-v4-proother | $0.725/M | $1.45/M |
mimo-v2.5-proother | $0.417/M | $1.25/M |
mimo-v2.5other | $0.167/M | $0.833/M |
qwen/qwen3.6-plus-image-editother | $0.0100/request | - |
qwen/qwen3.6-videoother | $0.100/request | - |
qwen/qwen3.6-35b-a3bother | $0.104/M | $0.542/M |
qwen/qwen3.6-plus-imageother | $0.0100/request | - |
Showing 25 of 80 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Feb 18, 09:26 AM | claude-opus-4-5-20251101 | 52.45 tok/s | 5.33s |
Similar API Provider Alternatives to Compare
Compare GLM BigModel Relay alternatives against 6 nearby API providers using 548 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| GLM BigModel Relay glm-bigmodel-relay A third-party API relay providing access to GLM/ChatGLM models through OpenAI-compatible endpoints. | Current provider baseline | 140 | 0 | $0.0083/M | 52 tok/s | 9970% |
| 阿里云百炼 DashScope dashscope Alibaba Cloud DashScope provides AI model APIs including Qwen LLMs, vision, audio, and embedding models. |
| 296 | 0 | N/A | 77 tok/s | 7720% |
| 百度千帆 baidu-qianfan Baidu Qianfan is Baidu Intelligent Clouds enterprise AI platform, providing access to ERNIE series models and other LLM capabilities through developer APIs. |
| 184 | 0 | N/A | 81 tok/s | 4810% |
| Mistral AI mistral-ai-api Mistral AI API provides access to frontier AI models including Mistral Large, Medium, Small, and Codestral for chat, code, and embeddings. |
| 11 | 0 | N/A | 132 tok/s | 9980% |
| DeepSeek deepseek DeepSeek provides API access to its latest large language models for text generation and coding tasks. |
| 6 | 0 | N/A | 75 tok/s | 9980% |
| 火山引擎 Ark volcengine-ark Volcengine Ark is ByteDance's enterprise AI platform, offering Doubao series models and third-party LLMs via OpenAI-compatible API. |
| 163 | 0 | N/A | 41 tok/s | 9960% |
| 智谱 AI zhipu-ai Zhipu AI provides the GLM series of large language models including GLM-4, ChatGLM, and CodeGeeX for text, code, and multimodal tasks. |
| 34 | 0 | N/A | 68 tok/s | 9970% |
Announcements
default7/26/2026
The gpt-image2 model is now available again.
default7/9/2026
The gpt-image-2 model is currently unstable for image generation, with issues such as timeouts.
ongoing5/29/2026
Since the Xianyu account is banned from replying, you can join the QQ group for communication: 497909697
ongoing5/17/2026
Recharge on this site can be done via WeChat through Wallet Management. The Xianyu link is inaccessible because it was taken down by Xianyu; a new link will be provided later.
default5/14/2026
This site's domain will gradually migrate to api.galaxy-grocery.com. The original domain will expire and be taken offline in September 2026, but will remain accessible until then.
default4/26/2026
gpt-image-2 model price reduced to 0.05 yuan per call via the other group.
default3/5/2026
New jimeng-4.6 model launched, supports 2k resolution, priced at 0.01 yuan per call.
default3/4/2026
jimeng series and nanobanana models temporarily delisted due to parameter changes in Jimeng interface; will be relisted after re-adaptation.
default2/12/2026
Added support for glm-5 model.
default2/6/2026
Added gpt-5.3-codex model.
Notes
- Health checks: Scope: the 72-hour chart and recent availability measure API connectivity only. Each bar summarizes one hour of checks. Targets: LMSpeed tries the configured health check URL and provider status URL first, then API endpoints derived from known API hosts and recent speed-test base URLs. A website host is considered only when it looks like an API endpoint. Probe steps: each candidate goes through DNS lookup, TCP connection, TLS handshake for HTTPS, and an HTTP HEAD request with redirects followed. Probing stops after the first reachable candidate. Reachable criteria: every required network step must succeed. An HTTP response below 500 is treated as reachable, including 401 because it confirms that an authenticated API endpoint responded, except for statuses classified as blocked. Blocked results: HTTP 403, 429, 521, 525, and 530, plus detected WAF or Cloudflare challenges, are shown as blocked and excluded from availability calculations because LMSpeed cannot determine whether the API itself is down. Model availability: when a dedicated test key is configured, LMSpeed sends an authenticated GET request to a derived /models endpoint and compares returned model IDs with this provider's listed models. These per-model results appear in Models & Pricing and are not included in the provider connectivity percentage. Timeouts: TCP connection, TLS handshake, HTTP connectivity, and model requests each use a 20-second timeout. A full run can take longer when several candidates are tried. Frequency: a background worker checks all providers every 5 minutes by default. The 72-hour chart combines those samples into hourly bars, and the schedule may be changed by the service operator. Limit: automated samples are not an SLA and do not guarantee account quota, every model, every region, or successful completion requests. Check the provider's own status page before making operational decisions.
- Domain Rating data is sourced from Ahrefs. It is a 0–100 backlink-based domain strength signal and does not measure API speed or reliability.
- Announcements and FAQ are read from this provider's NewAPI status snapshot when available. LMSpeed stores the original content and optional English translations from the provider status source, then shows the localized fields on this page.