Together AI · Together AI platform · LLMzai-org/GLM-5.2
Capability changeCapability change announced Aug 25, 2026
4 notices
Capability change
Capability change announced Aug 25, 2026
Together AI documents a capability change: “ Longer context for GLM-5.2 zai-org/GLM-5.2 on serverless now accepts a 1,000,000-token context length, up from 512,000.”
- Hosting route
- Together AI platform
- Affected scope
- Not stated in the notice
- Announced
- Aug 25, 2026
- First seen by ModelClock
- Oct 7, 2026
Longer context for GLM-5.2
zai-org/GLM-5.2 on serverless now accepts a 1,000,000-token context length, up from 512,000. Pricing is unchanged. See the GLM-5.2 quickstart .
Read from the provider's text; the quote is the provider's exact lines.
Capability change
Capability change announced Aug 13, 2026
Together AI documents a capability change: “ New models available for fine-tuning You can now fine-tune the following models: zai-org/GLM-5.2.”
- Hosting route
- Together AI platform
- Affected scope
- Not stated in the notice
- Announced
- Aug 13, 2026
- First seen by ModelClock
- Oct 7, 2026
New models available for fine-tuning
You can now fine-tune the following models:
Read from the provider's text; the quote is the provider's exact lines.
Capability change
Capability change announced Aug 8, 2026
Together AI documents a capability change: “ Longer context for GLM-5.2 zai-org/GLM-5.2 on serverless now accepts a 512,000-token context length, up from 262,144.”
- Hosting route
- Together AI platform
- Affected scope
- serverless
- Announced
- Aug 8, 2026
- First seen by ModelClock
- Oct 7, 2026
Longer context for GLM-5.2
zai-org/GLM-5.2 on serverless now accepts a 512,000-token context length, up from 262,144. Pricing is unchanged. See the GLM-5.2 quickstart .
Read from the provider's text; the quote is the provider's exact lines.
Capability change
Capability change announced Jul 8, 2026
Together AI documents a capability change: “ Provisioned throughput Provisioned throughput is now available, allowing you to reserve inference capacity for frontier open models.”
- Hosting route
- Together AI platform
- Affected scope
- provisioned throughput
- Announced
- Jul 8, 2026
- First seen by ModelClock
- Oct 7, 2026
Provisioned throughput
Provisioned throughput is now available, allowing you to reserve inference capacity for frontier open models. Commit to a one-month-or-longer term, and Together commits to throughput and reliability targets for traffic within your purchased capacity. At launch, provisioned throughput is available for MiniMaxAI/MiniMax-M3 and zai-org/GLM-5.2.
Read from the provider's text; the quote is the provider's exact lines.
Same model elsewhere
Each provider and hosting route sets its own dates.
ModelClock