Express API
Home Console Models Pricing Docs

49 Models & Growing

OpenAI-compatible API at gptapi.net.cn/v1. Sourced from China’s top AI labs. All specs from official vendor documentation.

Model IDCapabilities & Specs
DeepSeek · 2 models
deepseek-v4-flash284B MoE (13B active) · 1M context, 384K max output. Thinking mode, JSON output, tool calls, FIM. Fast & efficient.
deepseek-v4-pro1.6T MoE (49B active) · 1M context, 384K max output. Thinking mode, JSON output, tool calls, FIM, context caching. Flag.
Alibaba / Qwen · 9 models
qwen-image-2.0-pro-2026-06-22Professional image generation · Infographics, photorealism · ~$0.07/image · Contact support for access.
qwen3.6-35b-a3b35B (3B active) MoE · 256K context · Cost-efficient. $0.25/$1.50 per 1M.
qwen3.6-flash1M context · Fast tier · High throughput. $0.17/$1.00 per 1M.
qwen3.6-plus1M context · Strong generalist · Balanced cost-performance. $0.28/$1.67 per 1M (tiered ≥256K).
qwen3.7-max1M context · Qwen flagship, agent-centric · Coding, office productivity, tool orchestration. $1.67/$5.00 per 1M (official, currently 50% off).
qwen3.7-max-2026-06-081M context · Qwen flagship latest iteration. Continuous improvements.
qwen3.7-plus1M context · Cost-effective Qwen 3.7 · Text+image input. $0.28/$1.11 per 1M (official, 20% off).
qwen3.7-plus-2026-05-261M context · Qwen 3.7 Plus updated.
qwen3.7-text-embedding32K input · Embedding model · 1024-dim vectors. $0.07/1M.
Moonshot / Kimi · 12 models
kimi-k2.5256K context · Open-source SoTA · ⚠️ Deprecated, shutting down Aug 31, 2026. Available until then.
kimi-k2.6256K context · Multimodal · Thinking + non-thinking modes · Vision, tool calls, streaming.
kimi-k2.7-code256K context · Code-specialized · Thinking-only · Text+image+video input · Tool calls, structured output.
kimi-k2.7-code-highspeed256K context · ~5-6x faster than K2.7 Code · Optimized for low-latency code completion & agent IDEs.
kimi-k32.8T params · 1M context · Vision input · Always-on reasoning (low/high/max) · Tool calls, web search, JSON Mode, context caching. Kimi's strongest.
moonshot-v1-128k128K context. ⚠️ Deprecated, shutdown Aug 31.
moonshot-v1-128k-vision-preview128K context, vision. ⚠️ Deprecated, shutdown Aug 31.
moonshot-v1-32k32K context. ⚠️ Deprecated, shutdown Aug 31.
moonshot-v1-32k-vision-preview32K context, vision. ⚠️ Deprecated, shutdown Aug 31.
moonshot-v1-8k8K context. ⚠️ Deprecated, shutdown Aug 31. Legacy foundation model.
moonshot-v1-8k-vision-preview8K context, vision. ⚠️ Deprecated, shutdown Aug 31.
moonshot-v1-autoAuto routing · ⚠️ Not an official Kimi model. Third-party alias.
Zhipu / GLM · 10 models
glm-4.5355B MoE (32B active) · 128K context · ⚠️ Deprecated in favor of 4.7.
glm-4.5-air106B (12B active) MoE · 128K context · Most affordable GLM. High-volume workloads.
glm-4.5vVision-language · ⚠️ Deprecated. Still available with pricing.
glm-4.6355B MoE (32B active) · 200K context · Stable general-purpose · Supports thinking mode.
glm-4.6v106B · 128K context · Vision model · Image understanding, visual reasoning.
glm-4.7128K context · Latest 4.x · Enhanced coding, creative writing, role-play. ⚠️ Deprecating 4.6.
glm-51M context · Strong general reasoning & agent capabilities.
glm-5-turboSpeed-optimized GLM 5 · High RPM for production throughput.
glm-5.11M context · Tiered pricing (≤32K / >32K) · Deep reasoning, agentic workflows.
glm-5.21M context · Zhipu flagship · Long-horizon agents, software engineering, deep reasoning · Tool calls, structured output.
ByteDance / Doubao · 5 models
doubao-embedding-text-240715Doubao Embedding · 2560-dim vectors · Semantic search & RAG.
doubao-lite-128k-240428Doubao Lite · 128K context · Cost-effective long-text processing.
doubao-lite-32k-240628Doubao Lite · 32K context · Fast, affordable Chinese model.
doubao-pro-128k-240628Doubao Pro · 128K context · Top Chinese language performance · Ultra-long context.
doubao-pro-32k-240615Doubao Pro · 32K context · Strong Chinese NLP · Function calling.
MiniMax · 3 models
MiniMax-M2.7Strong general-purpose dialogue · Stable production performance · Context caching.
MiniMax-M2.7-highspeedHigh-speed variant · Real-time, low-latency applications.
MiniMax-M31M context · Multimodal (text+image+video) · Long-horizon agents, coding, creative writing · Tool calls.
Baidu / ERNIE · 2 models
ernie-4.5-turbo-128kBaidu ERNIE 4.5 Turbo · 128K context · Fast inference for long documents.
ernie-5.1Baidu ERNIE 5.1 · Deep Chinese language understanding · Enterprise-grade · Function calling, structured output.
Tencent / Hunyuan · 2 models
hy3Tencent HY3 · 295B MoE (21B active), 192 experts · 128K context · Reasoning, agentic, production-grade.
hy3-previewTencent HY3 Preview · Early access · Configurable thinking depth.
StepFun · 2 models
step-3.5-flashEntry model · Fastest response, minimal cost per token.
step-3.7-flashFast model · General-purpose, competitive performance at low cost.
Xiaomi / MiMo · 2 models
mimo-v2.5Xiaomi MiMo V2.5 · 128K context · Natural Chinese fluency · General-purpose.
mimo-v2.5-proXiaomi MiMo V2.5 Pro · 128K context · Strong coding & agentic capabilities · Benchmark leader.
Express API · gptapi.net.cn