LLMdeepseek

DeepSeek: DeepSeek V3

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

Anyone in the Space can @-mention DeepSeek: DeepSeek V3 with the team's shared context — pooled credits, one chat, one memory.

All models

Starter is free forever — 1 Space, 100 credits/month, 1 MCP. No card.

Specifications

Provider: deepseek
Category: llm
Context length: 163,840 tokens
Max output: 16,384 tokens
Modalities: text
License: proprietary
Released: 2024-12-26

Pricing

Input: $0.32/Mtok
Output: $0.89/Mtok
Model ID: deepseek/deepseek-chat

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool — one plan, one balance for everyone.

Team cost calculator

Seats5 peopleMessages / seat / day80Avg turn size2 ktokOutput share30 %

Estimated monthly spend

$8.64

17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool — one plan, one balance for everyone.

Providers

Provider	Context	Input	Output	P50 latency	Throughput	30d uptime
deepseek	164k	$0.32/Mtok	$0.89/Mtok	—	—	—

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Spaces have used this model yet to share anonymised team stats. We wait for at least 50 distinct Spaces per week before publishing any aggregate.

Starter prompts

Starter prompts for this model will land here soon.