impulse

DeepSeek R1 Turbo

Open weights
API id deepseek-r1-turbo
Input / 1M
$0.70
at Novita AI
Output / 1M
$2.50
at Novita AI
Context window
64K
tokens
Max output
16K
tokens per reply
Hosts
2
3 listings
Released
-
date not published

Pricing

List prices at Novita AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.70$2.50

What it costs a month

At Novita AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$398
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$426
  • Coding agent1,000 requests a day, 40K in / 2K out$990
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,280
Use your own numbers

Where to run it

2 hosts serve DeepSeek R1 Turbo. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Novita AIInference
deepseek-r1-turbo
$0.70 / $2.50
DeepInfraInference
DeepSeek-R1-Turbo
$1.00 / $3.00
+30% vs headline
Show 1 more listings: regions, snapshots and variants
DeepInfra
0528
DeepSeek-R1-0528-Turbo
$1.00 / $3.00
+30% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Parallel tool calls
Open weights
License: DeepSeek License (MIT code)
Runtimes: SGLang, TGI, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Novita AI.

Smaller DeepSeek models

No cheaper DeepSeek model keeps its key capabilities.

Other frontier labs

  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    26% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    60% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    83% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    83% less

Open-weight picks

  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    25% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    31% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    40% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    45% less

Call it

Using Novita AI's API.

Python
from litellm import completion

response = completion(
    model="novita/deepseek-r1-turbo",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does DeepSeek R1 Turbo cost?

On Novita AI, DeepSeek R1 Turbo costs $0.70 per million input tokens and $2.50 per million output tokens.

Which APIs offer DeepSeek R1 Turbo?

DeepSeek R1 Turbo runs on 2 APIs: Novita AI and DeepInfra.

What is DeepSeek R1 Turbo's context window?

64K tokens, with up to 16K tokens in one reply.

Is DeepSeek R1 Turbo being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to DeepSeek R1 Turbo?

Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (26% less), GPT-5.4 Nano on OpenAI (60% less) and GLM 5.3 on CLF AI Gateway (25% less). Savings are on a mix of 3 input tokens to 1 output token.

What is DeepSeek R1 Turbo's API model id?

Use deepseek-r1-turbo with Novita AI. Other hosts use their own ids: DeepSeek-R1-Turbo on DeepInfra.

Sources

Raw catalog entry for deepseek-r1-turbo on Novita AI
{
  "litellm_provider": "novita",
  "mode": "chat",
  "input_cost_per_token": 7e-7,
  "output_cost_per_token": 0.0000025,
  "max_input_tokens": 64000,
  "max_output_tokens": 16000,
  "supports_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_tool_choice": true,
  "supports_system_messages": true,
  "supports_reasoning": true,
  "supports_response_schema": true
}