ModelClock
Together AI · Together AI platform · LLM

deepseek-ai/DeepSeek-V4.1-Flash

Capability changeCapability change announced Oct 2, 2026
Read official noticeAdd deadlines to calendarRSS for this model

2 notices

Capability change

Capability change announced Oct 2, 2026

Together AI documents a capability change: “​ New provisioned throughput models The following models are now available on provisioned throughput : deepseek-ai/DeepSeek-V4.1-Flash.”

Hosting route
Together AI platform
Affected scope
provisioned throughput
Announced
Oct 2, 2026
First seen by ModelClock
Oct 8, 2026

What the provider published

docs.together.ai ↗

​ New provisioned throughput models

The following models are now available on provisioned throughput :

  • deepseek-ai/DeepSeek-V4.1-Flash.

Read from the provider's text; the quote is the provider's exact lines.

Revision history

Loading…
Raw history JSON
API availability

Available in the API since Sep 11, 2026

Together AI announced API availability for this model on 2026-09-11. serverless

This date applies to API availability. Rollouts in consumer products or other hosting routes can happen on different dates.

Hosting route
Together AI platform
Affected scope
serverless
Announced
Sep 11, 2026
First seen by ModelClock
Oct 8, 2026

What the provider published

docs.together.ai ↗

​ New serverless models

The following models are now available on serverless :

  • deepseek-ai/DeepSeek-V4.1-Flash: 1,000,000 context length, FP8 quantization, function calling, and structured outputs. Pricing: $0.30 input / $1.20 output / $0.006 cached input (per 1M tokens).

Read from the provider's text; the quote is the provider's exact lines.

Revision history

Loading…
Raw history JSON