Model Catalog › together

DeepSeek-R1

deepseek-ai/DeepSeek-R1

CHAT High tier Reasoning Open-weight

DeepSeek-R1 (deepseek-ai/DeepSeek-R1) is a chat model from together with a 128K-token context window; open-weight; capabilities tools, reasoning; input text; output text.

128KContext
20.5KMax output
$3$ / 1M in

Pricing

Input
$3 / 1M tokens
Output
$7 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.

Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.

Specifications

Context window
128,000 tokens (128K)
Max output
20,480 tokens
Weights
Open-weight
Input modalities
text
Output modalities
text
Knowledge cutoff
2024-07
Release date
2025-01-20

Capabilities

tools reasoning

Provenance

committedmodels-devoverrides
Last verified: 2026-10-30

Related models

DeepSeek-V3
deepseek-ai/DeepSeek-V3
together · CHAT · 65.5K ctx
Qwen3 235B A22B Instruct
Qwen/Qwen3-235B-A22B-Instruct-2507-tput
together · CHAT · 262K ctx
Qwen3 Coder 480B
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
together · CHAT · 256K ctx
Llama 3.3 70B Instruct Turbo
meta-llama/Llama-3.3-70B-Instruct-Turbo
together · CHAT · 131.1K ctx
Llama 4 Maverick 17B
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
together · CHAT