GLM-5.3

Z.ai's latest flagship reasoning model with a 1M-token context window and controllable thinking length.

Input price: $0.07–$2.10list $1.40-95%
Output price: $0.22–$6.60list $4.40-95%
Context: 1M
Max output: 131K
Modalities: InputTextOutputText
Capability: 156 (#28 of 89)
Human preference: 1474
30-day uptime: —
Released: 2026-08-14
Knowledge cutoff: —

Providers

Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.

AutoInput$0.07–$2.10-95%Output$0.22–$6.60-95%Cache read$0.013–$0.39-95%Context1MMax output131KWe send each request to the best-priced healthy provider. You pay that provider’s price.Cloudflare Workers AICheapestInput$0.07-95%Output$0.22-95%Cache read$0.013-95%GlobalNo trainingNo retentionTencent Cloud TokenHubInput$0.7008-40%Output$2.4528-40%Cache read$0.1752-40%ChinaNo trainingFireworks AIInput$1.40Output$4.40Cache read$0.26Context1MMax output131KUnited StatesNo trainingNo retentionFireworks AIInput$2.10Output$6.60Cache read$0.39Context1MMax output131KUnited StatesNo trainingNo retention

Pricing

Prices vary by provider. Showing Cloudflare Workers AI, the lowest. Pick a provider above to see its prices.

Input: $0.07list $1.40-95%; per 1M tokens
Output: $0.22list $4.40-95%; per 1M tokens
Cache read: $0.013list $0.26-95%; per 1M tokens

Make a request

Set your provider preferences, then copy the request. It reads your API key from OHMYGPT_API_KEY.

Keep conversations on one provider

Later turns reuse the provider’s prompt cache, which can lower cost and latency.

Providers

Fireworks AI

Tencent Cloud TokenHub

Cloudflare Workers AI

curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/glm-5.3",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Similar models

Other models with the same output types at a similar price.

Better value: more capable, lower price
Pareto frontier
This model
Similar models

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-02), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

GLM-5.3This model

Capability: 156
Input: $0.07–$2.10
Output: $0.22–$6.60

DeepSeek V4.1 Flash

Capability: 156
Input: $0.073–$0.283
Output: $0.292–$1.131

Tencent Hy-MT2-Plus

Capability: —
Input: $0.073
Output: $0.292

Nova Lite

Capability: —
Input: $0.066
Output: $0.264

NVIDIA Nemotron Nano 3 30B

Capability: —
Input: $0.066
Output: $0.264

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-10-28): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text