glm-5.3
glm-5.3Availability100.0%
Available
Samples: 16
Latency1.6 s
Output speed99.8 tok/s
GLM 5.3 paid model.
- Input / 1M tokens
- $1.4
- Output / 1M tokens
- $4.4
- Context window
- 1,048,576
- Route
- Default
DefaultRoleplay
Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.
Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.
Creative Writing v3
GLM-5.3: 2,076.7
145 Models · 2026-10-25
LiveBench · Story constraint following
glm-5.3: 72.13
71 Models · 2026-10-25
LiveBench · Theory of mind
glm-5.3: 88.46
71 Models · 2026-10-25
8.9/ 10
Routes
Ability score divided by token cost, ranked across measured model routes. Cost uses equal input and output token counts; higher is better value.
| Use this model | ||||||
|---|---|---|---|---|---|---|
| devin | $0.7 | $2.2 | $0.13 | 8.9/10 | 7.7/10 | Plans and tiers |
| forge | $0.7 | $2.2 | $0.13 | 8.9/10 | 7.7/10 | Plans and tiers |
| Default | $1.4 | $4.4 | $0.26 | 8.9/10 | 5.7/10 | Use this model |
| opencode_plus | $1.4 | $4.4 | $0.26 | 8.9/10 | 5.7/10 | Plans and tiers |
| origin | $1.4 | $4.4 | $0.26 | 8.9/10 | 5.7/10 | Plans and tiers |
devin
opencode_plusQuick start
Access and billingcurl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
-H "Authorization: Bearer $TOKENREPLY_API_KEY" \
-H 'Content-Type: application/json' \
--data '{
"model": "glm-5.3",
"messages": [
{
"role": "user",
"content": "Reply with hello."
}
]
}'