Is DeepInfra DeepSeek V3.1 Terminus deprecated?

What kind of model is this?

Tags describe what DeepSeek V3.1 Terminus takes in, what it is built for and how you can get it. Modality, access and language tags follow DeepInfra's own documentation; tier and use-case tags are our reading of the line-up.

Modality

• Text

Use case

• Chat
• Coding
• Reasoning
• Agents & tool use

Tier

• Mid-tier

Access

• Hosted API
• Open weights

Specifications

Input price

unknown

Output price

unknown

Price band

unknown

Context window

163.8K tokens

Max output

unknown

Input

Text

Output

Text

Knowledge cutoff

unknown

Tool use

unknown

Structured output

unknown

Weights licence

MIT License

Model maker

DeepSeek

“unknown” means the figure has not been published, or we have not verified it yet — never that the answer is no. “not published” under the weights licence means this model is not offered with downloadable weights. The price band is ours: it bands the blended price (three parts input to one part output) as budget (≤ $0.50), standard (≤ $3), premium (≤ $12) or flagship.

Lifecycle

1. Released unknown
2. Deprecated not announced DeepInfra has not published the date this happened
3. Retired 17 August 2026

What is it good for?

No editorial profile for this model yet. The specifications above come from DeepInfra's own documentation and the suggestions below are derived from the data — shared tags, tier and price band — not written by hand.

What to use instead of DeepSeek V3.1 Terminus

• Kimi K2.6 Derived

  DeepInfra ● Active

  Same provider, same tier (mid-tier), also open weights; shares chat, coding, reasoning and agents.

  $0.75 in · $3.50 out / M tokens · 262.1K context

• Kimi K2.7 Code Derived

  DeepInfra ● Active

  Same provider, same tier (mid-tier), also open weights; shares chat, coding, reasoning and agents.

  $0.68 in · $3.40 out / M tokens · 262.1K context

• Kimi K3 Derived

  DeepInfra ● Active

  Same provider, same tier (mid-tier), also open weights; shares chat, coding, reasoning and agents.

  $2.85 in · $14.25 out / M tokens · 1M context

• GLM-4.7 Derived

  DeepInfra ● Active

  Same provider, same tier (mid-tier), also open weights; shares chat, coding, reasoning and agents.

  $0.40 in · $1.75 out / M tokens · 202.8K context

• Kimi K2 Thinking Derived

  Amazon Bedrock ● Active

  Alternative from Amazon Bedrock, same tier (mid-tier), also open weights; shares chat, coding, reasoning and agents.

  $0.60 in · $2.50 out / M tokens · 256K context

Derived suggestions are ranked from the data — shared tags, the same tier and a comparable price band — not from benchmark scores. Check the capability fit yourself: we track lifecycle, price and specifications.

Sources

• api.deepinfra.com ↗ https://api.deepinfra.com/models/list
• api.deepinfra.com ↗ https://api.deepinfra.com/v1/openai/models

Verified against the source on 10 September 2026. Dataset snapshot 10 September 2026. Providers can change a date without notice — the link above is always the final word.