Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. DeepSeek

DeepSeek V4 Flash 0731 (Thinking)

DeepSeek V4 Flash 0731 Thinking enables reasoning by default on the re-post-trained Mixture-of-Experts model with a 1M-token context window, built for coding, reasoning, and agent workflows.

  • Reasoning
  • Tool Calling
  • Structured Output

Added Aug 1, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.05
Output
$0.16
Cache read
$0.013
Compare provider prices

Specifications

Context window
1M
Max output
131.1K
Parameters
284B / 13B
Total / active
Avg output (7d)
1.3K tokens
Longer than 78% of models

Benchmarks

No public benchmark scores for this model yet.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.05$0.16$0.013N/AN/A
Auto
Auto (Anonymized)
$0.05$0.16$0.013N/AN/A
Munito
Munito
67% off
FP8
EU
$0.116$0.0381$0.294$0.097$0.0231$0.00762N/AN/A
EngyAI
EngyAI
GLB
$0.0473$0.0945$0.00945N/AN/A
Reka
Reka
UNK
$0.0493$0.0998$0.0389N/AN/A
Hyperfusion
Hyperfusion
FP8
AE
$0.0525$0.168N/AN/AN/A
Gonka24
Gonka24
GLB
$0.0536$0.109N/AN/AN/A
Baidu
Baidu
86% off
FP8
CN
$0.462$0.0628$1.39$0.188$0.0147$0.00201s89 tps
DeepInfra
DeepInfra
FP8
US
$0.063$0.189$0.01580.5s45 tps
Relace
Relace
FP4
UNK
$0.0735$0.147$0.01470.8s50 tps
BaseTen
BaseTen
FP8
US
$0.136$0.273$0.02940.4s102 tps
CoreWeave
CoreWeave
FP8
US
$0.136$0.284$0.05250.6s73 tps
Inceptron
Inceptron
FP4
EU
$0.136$0.52$0.02841s36 tps
Venice
Venice
US
$0.136$0.273$0.02940.6s66 tps
StreamLake
StreamLake
70% off
FP8
CN
$0.462$0.139$1.39$0.416$0.0147$0.00442.3s39 tps
NeuralWatt
NeuralWatt
US
$0.147$0.294$0.0294N/AN/A
Parasail
Parasail
FP8
US
$0.147$0.294$0.05250.8s47 tps
Wafer
Wafer
NVFP4
US
$0.147$0.242$0.1420.3s75 tps
Mancer
Mancer
FP8
$0.157$0.525$0.07871s46 tps
Sail Research (Standard)
Sail Research (Standard)
FP4
GLB
$0.157$0.315$0.04411.9s32.5 tps
TensorX
TensorX
FP4
EU
$0.157$0.315$0.0394N/AN/A
Alibaba
Alibaba
27% off
SG
$0.254$0.185$0.762$0.554$0.0254$0.01851.9s80 tps
Uomi
Uomi
BF16
GLB
$0.211$0.589N/AN/AN/A
SiliconFlow
SiliconFlow
FP8
SG
$0.231$0.693$0.02941.2s52 tps
GMICloud
GMICloud
FP8
US
$0.30$0.901$0.009562.1s60 tps
RunAnywhere (Wally)
RunAnywhere (Wally)
FP8
US
$0.308$0.924$0.00977N/AN/A
Phala
Phala
30% off
US
$0.462$0.323$1.39$0.97$0.0294$0.02062s57 tps
Novita
Novita
FP8
US
$0.43$1.29$0.02731s60 tps
AtlasCloud
AtlasCloud
FP4
US
$0.462$1.39$0.02943.4s51 tps
Chutes
Chutes
FP8
US
$0.462$1.39$0.04622s38 tps
Cloudflare
Cloudflare
US
$0.462$1.39$0.01471s65 tps
Ollama
Ollama
UNK
$0.462$1.39$0.0147N/AN/A
PrimeIntellect
PrimeIntellect
FP4
UNK
$0.462$1.39$0.01470.5s236 tps
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclearRetains prompts, training unclearBest latency and throughput are highlighted.
Batch API
ProviderInputOutputCached input
Auto
Autodeepseek/deepseek-v4-flash-0731:thinking
$0.05/M$0.16/M$0.013/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare DeepSeek V4 Flash 0731 (Thinking) with similar models from the same provider or model family.

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is a re-post-trained Mixture-of-Experts model with a 1M-token context window, built for coding, reasoning, and agent workflows.

DeepSeek V4.1 Flash 0910 Uncensored

deepseek/deepseek-v4.1-flash-0910-uncensored

Uncensored DeepSeek V4.1 Flash with text and image input, optional reasoning, and tool calling. The date label is retained for compatibility. Served only by its own checkpoint; it may be unavailable while that host is down.

DeepSeek V4.1 Flash 0910 Uncensored Thinking

deepseek/deepseek-v4.1-flash-0910-uncensored:thinking

Uncensored DeepSeek V4.1 Flash with text and image input, optional reasoning, and tool calling. The date label is retained for compatibility. Served only by its own checkpoint; it may be unavailable while that host is down.

DeepSeek V4.1 Flash 1017 Uncensored

deepseek/deepseek-v4.1-flash-1017-uncensored

Uncensored DeepSeek V4.1 Flash with text and image input, optional reasoning, and tool calling. The date label is retained for compatibility. Served only by its own checkpoint; it may be unavailable while that host is down.

DeepSeek V4.1 Flash 1017 Uncensored Thinking

deepseek/deepseek-v4.1-flash-1017-uncensored:thinking

Uncensored DeepSeek V4.1 Flash with text and image input, optional reasoning, and tool calling. The date label is retained for compatibility. Served only by its own checkpoint; it may be unavailable while that host is down.

DeepSeek V4.1 Flash 1017

deepseek/deepseek-v4.1-flash-1017

The October 17, 2026 snapshot of DeepSeek V4.1 Flash supports text and image input, tool calling, and optional reasoning with low, high, and max effort. It has a shared 1,048,576-token context window and supports up to 393,216 output tokens within the remaining context. Released under the MIT license.