ModelBench
DeepSeek logo
Models/DeepSeek

DeepSeek: DeepSeek Reasoner

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Source-linked deepseek-thinking Open weights Released 2025-12-01
API record Report
InputT
OutputT
Input price$0.147/M
Output price$0.295/M
Context1M
Max output384K
Providers6
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering DeepSeek Reasoner
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Cloudflare AI Gateway deepseek/deepseek-reasoner 1M 384K $0.14 $0.28 $0.003 ReasoningTools Docs ↗
DeepSeek deepseek-reasoner 1M 384K $0.14 $0.28 $0.003 ReasoningTools Docs ↗
OrcaRouter deepseek/deepseek-reasoner 1M 384K $0.147 $0.295 $0.028 ReasoningTools Docs ↗
Eden AI deepseek/deepseek-reasoner 131.072K 384K $0.28 $0.42 $0.028 ReasoningJSON Docs ↗
NanoGPT deepseek-reasoner 64K 65.536K $0.4 $1.7 $0.2 Not listed Docs ↗
Helicone deepseek-reasoner 128K 64K $0.56 $1.68 $0.07 Not listed Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.14/M

Across 6 priced providers

Median input $0.214/M

Midpoint of listed rates

Highest input $0.56/M

4.0× the lowest listed rate

Output range $0.28 – $1.7

Per million output tokens

Cloudflare AI Gateway $0.14/M
DeepSeek $0.14/M
OrcaRouter $0.147/M
Eden AI $0.28/M
NanoGPT $0.4/M
Helicone $0.56/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

2 providers list the identical $0.14 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 64K to 1M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
× Tool calling No
× Structured output No
✓ Attachments Yes
× Vision input No
✓ Open weights Yes
Creator
DeepSeek
Model family
deepseek-thinking
Knowledge cutoff
2025-09
License
Not documented
Release date
2025-12-01
Model ID
deepseek/deepseek-reasoner

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
Aider Polyglot percent correct · 2025-10-03 Source ↗
Aider Polyglot #5 of 31

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against Aider Polyglot, the benchmark with the widest published coverage that this model appears in.

0 47 93 $0.1 $1 $10 Qwen Max — $1.6/M, score 21.8 Qwen3 235B-A22B — $0.7/M, score 59.6 Qwen3 32B — $0.7/M, score 40.0 Claude Haiku 3.5 — $0.8/M, score 28.0 Claude Sonnet 3.7 — $3/M, score 64.9 Claude Opus 4 — $15/M, score 72.0 Claude Sonnet 4 (latest) — $2.898/M, score 61.3 Claude Sonnet 4 — $3/M, score 61.3 Command A — $2.5/M, score 12.0 DeepSeek Chat — $0.147/M, score 70.2 DeepSeek-R1 — $0.7/M, score 56.9 DeepSeek Reasoner — $0.147/M, score 74.2 Gemini 2.5 Flash — $0.3/M, score 55.1 Gemini 2.5 Pro — $1.25/M, score 83.1 Llama 4 Maverick 17B Instruct — $0.14/M, score 15.6 Codestral (latest) — $0.3/M, score 11.1 GPT-4.1 — $2/M, score 52.4 GPT-4.1 mini — $0.4/M, score 32.4 GPT-4.1 nano — $0.1/M, score 8.9 GPT-4o — $2.5/M, score 23.1 GPT-4o (2024-08-06) — $2.5/M, score 23.1 GPT-4o (2024-11-20) — $2.5/M, score 18.2 GPT-4o mini — $0.15/M, score 3.6 GPT-5 — $1.25/M, score 88.0 o1 — $15/M, score 61.7 o3 — $2/M, score 81.3 o3-mini — $1.1/M, score 60.4 o3-pro — $20/M, score 84.9 o4-mini — $1.1/M, score 72.0 DeepSeek Reasoner Input price per million tokens (log scale) Percent correct

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Price Completion1.7 → 0.295
Price Prompt0.4 → 0.147
Price Completion0.42 → 1.7
Price Prompt0.28 → 0.4
Price Completion0.28 → 0.42
Price Prompt0.14 → 0.28
Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology
Last verified
Sep 11, 2026
Status
Source-linked
Confidence
Medium
Catalog source
Models.dev
Models.devcatalog ↗Cloudflare AI Gateway documentationprovider documentation ↗DeepSeek documentationprovider documentation ↗OrcaRouter documentationprovider documentation ↗Eden AI documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗Helicone documentationprovider documentation ↗Aider Polyglotthird-party ↗
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/deepseek/deepseek-reasoner
curl
curl "https://model.kyssta.lol/api/v1/models/deepseek/deepseek-reasoner"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is DeepSeek Reasoner?

DeepSeek reasoning model for multi-step analysis, math, coding, and tools. It is published by DeepSeek and catalogued here from Models.dev.

How much does DeepSeek Reasoner cost?

Listed input pricing starts at $0.14 per million tokens from Cloudflare AI Gateway, rising to $0.56 across 6 listed providers.

What is the context length of DeepSeek Reasoner?

DeepSeek Reasoner accepts up to 1M tokens of context and returns up to 384K output tokens.

Which providers serve DeepSeek Reasoner?

6 providers list this model: Cloudflare AI Gateway, DeepSeek, OrcaRouter, Eden AI, NanoGPT, Helicone.

Are the weights for DeepSeek Reasoner open?

Yes. The weights are published and downloadable from Hugging Face.

When was DeepSeek Reasoner released?

The catalog records a release date of 2025-12-01, last verified Sep 11, 2026.

More models from DeepSeek

View all →
DeepSeek: DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

163.84K ctx $0.25/M in DeepSeek: R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

8.192K ctx $0.8/M in DeepSeek: R1 0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

163.84K ctx $0.5/M in DeepSeek: DeepSeek V3 0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

163.84K ctx $0.25/M in