jishie

GLM 5.3 Flash

umans-ai-coding-plan/umans-glm-5.3-flash · family glm-flash · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
free
Cache read $/1M
#143 of 7,381
Cheapest rank
Provider
Umans AI Coding Plan (umans-ai-coding-plan)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
131,071 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“GLM 5.3 Flash” is offered by 12 providers — cheapest-effective first. This one (Umans AI Coding Plan) is the cheapest.

ProviderInputOutputBlendedContext
Umans AI Coding Plan (this)freefree$0.001M
NanoGPT$0.075$0.25$0.121M
EmpirioLabs AI$0.075$0.25$0.121M
Cloudflare Workers AI$0.15$0.5$0.241.3M
Baseten$0.15$0.5$0.241M
Vercel AI Gateway$0.15$0.5$0.241M
CoreWeave$0.15$0.5$0.241M
Venice AI$0.15$0.5$0.241M
Fireworks AI$0.15$0.5$0.241M
Umans AI$0.15$0.5$0.241M
above.dev$0.165$0.55$0.261M
Modal$0.45$1.5$0.711M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Umans AI Coding Plan and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"umans-glm-5.3-flash","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Umans AI Coding Plan models · model index · JSON