G

GLM-5.3-Flash on Vidman AI

glm-5.3-flash

1M context128K max outputVisionVideoTool callingCachingalways reasoning

Pricing

₹ per 1M tokens · as of 3 November 2026
Input₹14
Output₹48
Cached input₹2.88

Flat rate: every request bills the same. Rupee prices convert at the platform exchange rate billing uses (₹96/USD today). Full catalog and comparisons on the pricing comparison page.

About this model

Z.ai's natively multimodal GLM-5 model, built for efficient coding and long-horizon agent tasks at low cost. Understands text, images and video.

Not sure? Vidman AI Adaptive routes to the best model per request, including this one.

Model specifications

API data
Modality
Text
Context
10,48,576 tokens
Maximum output
1,31,072 tokens
Reasoning
Always
Effort levels
low, high, max
Default effort
Provider default
Caching
Automatic
Cache minimum
None
Cache TTL
Provider managed
Route
Vidman AI managed

From the serverless catalog, fetched 3 November 2026.

Measured performance

API observations over 7d; not an SLA.

30,720 sampled requests
TTFT p50
6,000 ms
TTFT p95
12,000 ms
Throughput p50
100 tok/s
Throughput average
73.2 tok/s
Call it now: OpenAI-compatible
curl https://api.vidman.ai/v1/chat/completions \
  -H "x-api-key: $VIDMAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Existing OpenAI SDK code works by changing the base URL to https://api.vidman.ai/v1 and the key.

Model card

GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series from Z.ai. With 320B total parameters and just 18B active per token (320B-A18B), Z.ai reports that it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks.

GLM-5.3-Flash starts from a newly trained base model, with its architecture and training recipe redesigned around capability and efficiency. For the first time in the GLM series, it introduces a hybrid architecture combining sparse and linear attention, sharply reducing long-context serving costs while preserving precise long-context capabilities. The model also adopts Manifold-Constrained Hyper-Connections (mHC) to further improve scaling efficiency. Together with Z.ai's latest 30T-token multimodal pre-training corpus, these changes enable GLM-5.3-Flash to deliver more intelligence with less compute.

Architecture

GLM-5.3-Flash is a mixture-of-experts (MoE) model with a hybrid sparse/linear attention design and a native vision encoder. Published model configuration:

  • Scale: 320B total parameters with 18B active per token (320B-A18B). BF16 weights.
  • Context: a maximum position embedding of 1,048,576 tokens (1M context).
  • Language model: 45 hidden layers (the first 3 dense, the remainder sparse MoE), hidden size 4096, 288 routed experts with 8 routed experts active per token plus 1 shared expert, MoE intermediate size 2048, dense-layer intermediate size 12288, 64 attention heads, MLA-style attention with Q LoRA rank 1536 and KV LoRA rank 512, sigmoid expert scoring, vocabulary size 154,880.
  • Sparse attention indexer: 32 indexer heads (head dimension 128) selecting the top 2048 positions per query, with indexer sharing extended to the MTP iteration.
  • Hyper-connections: Manifold-Constrained Hyper-Connections (mHC) with an expansion factor of 4.
  • Speculative decoding: one multi-token-prediction (MTP) layer.
  • Vision encoder (native multimodal): a 24-layer vision transformer, hidden size 1024, patch size 14, base image size 448 with 2× spatial merge and a temporal patch size of 2 for video input. Images and videos are projected into the language model through a 4096-dimensional interface. The model accepts text, image and video inputs.

Thinking and Reasoning Effort

Per the official model card:

  • GLM-5.3-Flash supports controlling the thinking budget through the reasoning_effort parameter, which accepts three levels: low, high and max. It defaults to max if not passed (or if set to any other value). To use low or high, pass them explicitly.
  • For benchmark and leaderboard reproduction, Z.ai recommends keeping the default max.
  • In the model's chat template, clear_thinking defaults to false. Z.ai recommends explicitly passing clear_thinking=true for chat scenarios.

Performance

Z.ai's published claim for this release: GLM-5.3-Flash outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks. The full benchmark chart is published in the official model card. Evaluation methodology notes published alongside it include:

  • HLE w/ tools (full set): sampling temperature=1.0, top_p=0.95, maximum generation length 163,840 tokens, maximum context length 300,000 tokens with a context management strategy. GPT-5.6-luna (medium) as the judge model.
  • NL2Repo: temperature=1.0, top_p=1.0, max_new_tokens=64k under 1M context, with rule-based and LLM-based judgement to prevent malicious behaviors (e.g., unauthorized pip or curl operations).
  • DeepSWE: the mini-swe-agent harness with temperature=0.95, top_p=1.0, timeout=6h and 400K context.
  • Terminal-Bench 2.1: evaluated in Claude Code 2.1.207 with temperature=1.0, top_p=1, max_new_tokens=65536 and a 6-hour timeout.
  • Toolathlon Verified: results from the official evaluation service, pass@1 averaged over 3 independent runs.
  • AutomationBench: evaluated on v1.0.6, incorporating the fix for the null-type handling issue.
  • BabyVision: temperature=1.0, top_p=0.95, maximum context length 164K tokens, input images resized so the shorter side is at least 1.5K pixels.

License

GLM-5.3-Flash is released under the MIT license.

More from GLM

GLM 5.2₹134/₹326GLM-5.3₹134/₹422