ModelsAtlas
Explore
Atlas / Models / DeepSeek / DeepSeek Reasoner (legacy id)

DeepSeek Reasoner (legacy id)

deepseek/deepseek-reasoner
Text LLM by DeepSeek · DeepSeek V4 family · Released Unknown
⇄ Compare📄 Official docs ↗Vendor API ↗

Legacy compatibility id mapping to DeepSeek V4 Flash thinking mode (per DeepSeek pricing notes).

Input price
Custom /1M
Output price
Custom /1M
Context
1M
Modalities
text
Released
Unknown
Tool calling
—
Atlas signal
86/100
01

Overview

Legacy compatibility id mapping to DeepSeek V4 Flash thinking mode (per DeepSeek pricing notes).

Access: available through the official DeepSeek API. Context window: 1M.

Vendor-native catalog entry, sourced from official documentation.Last refreshed Aug 29, 2026
02

Specifications

API identifierdeepseek/deepseek-reasoner
ProviderDeepSeek
Model typeText LLM
Context window1M catalog
Input modalitiestext
Output modalitiestext
ReleasedUnknown
Architecture modalitytext->text
Source: provider documentation + catalog feedMethodology →
03

Pricing

Vendor-native listing — token prices may need to come from DeepSeek pricing pages until a host feed is linked.

Custom
Input /1M
Custom
Output /1M
—
Per request
—
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokensN/ACustom / 1MPer input token
Completion tokensN/ACustom / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

VariableCalculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool CallingNot advertisedSupports tools / function calling
Self-Hosting✓ SupportedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

DeepSeek Reasoner (legacy id)
MMLU Signal (Reasoning)
89signal
Coding Signal (HumanEval proxy)
83signal
Math Signal (GSM8K proxy)
83signal
Science Signal (GPQA proxy)
87signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call DeepSeek Reasoner (legacy id) through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-reasoner",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
API reference ↗Status page ↗
08

Alternatives

Closest models by context window from a different provider.

ModelProviderContextInput /1MActions
Claude Opus 4.6Anthropic1MCustomView →
Claude Opus 4.7Anthropic1MCustomView →
See all DeepSeek Reasoner (legacy id) alternatives →Browse all 38 models →All comparisons →

Head-to-head comparisons

Side-by-side breakdowns of DeepSeek Reasoner (legacy id) against other frontier models.

vs Claude Opus 4.6vs Claude Opus 4.7vs Claude Sonnet 4.6vs Claude Haiku 4.5vs Claude Opus 4vs Claude Opus 4.1vs Claude Opus 4.5vs Claude Sonnet 4vs Claude Sonnet 4.5vs Gemini 1.5 Flashvs Gemini 1.5 Provs Claude 3 Opusvs Claude 3.5 Sonnetvs Claude 3.7 Sonnetvs o1vs o3-minivs GPT-4ovs GPT-4o minivs DeepSeek Chat (legacy id)vs DeepSeek V4 Flashvs DeepSeek V4 Provs Gemini 2.0 Flashvs DeepSeek R1vs DeepSeek V3vs Qwen2.5 72B Instructvs Qwen2.5 Coder 32Bvs Jamba 1.5 Largevs Jamba 1.5 Minivs Command Rvs Command R+vs Llama 3.3 70B Versatilevs Llama 3.1 405B Instructvs Llama 3.1 70B Instructvs Llama 3.1 8B Instructvs Mistral Largevs Mistral Smallvs Mixtral 8x7B Instruct
09

Sources & attribution

Vendor-native listing: confirm the exact model id with your provider before wiring it up.

DeepSeek — Models & pricingOfficial ↗
Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does DeepSeek Reasoner (legacy id) cost?

Pricing is not publicly listed by the provider. Check DeepSeek directly for current rates.

What is the context window of DeepSeek Reasoner (legacy id)?

DeepSeek Reasoner (legacy id) supports up to 1M tokens of context.

Does DeepSeek Reasoner (legacy id) support tool / function calling?

DeepSeek Reasoner (legacy id) does not advertise first-class tool/function calling. Check vendor docs for the latest capabilities.

How do I access DeepSeek Reasoner (legacy id)?

Use the official DeepSeek API with the model id `deepseek/deepseek-reasoner`. See the Quick start section above for code examples.