ModelBench
DeepSeek logo
Models/DeepSeek

DeepSeek: DeepSeek-V3.1

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

Source-linked deepseek Open weights MIT License Released 2025-08-21
API record Report
InputT
OutputT
Input price$0.25/M
Output price$0.95/M
Context131.072K
Max output8.192K
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-V3.1
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Vercel AI Gateway deepseek/deepseek-v3.1 163.84K 128K $0.25 $0.95 $0.13 ReasoningTools Docs ↗
NovitaAI deepseek/deepseek-v3.1 131.072K 32.768K $0.27 $1 $0.135 ReasoningToolsJSON Docs ↗
Jiekou.AI deepseek/deepseek-v3.1 163.84K 32.768K $0.27 $1 — ReasoningToolsJSON Docs ↗
Abacus deepseek/deepseek-v3.1 128K 8.192K $0.55 $1.66 — ReasoningTools Docs ↗
Pioneer deepseek-ai/DeepSeek-V3.1 163.84K 131.072K $0.56 $1.68 $0.56 ReasoningTools Docs ↗
Amazon Bedrock deepseek.v3-v1:0 163.84K 81.92K $0.58 $1.68 — ReasoningToolsJSON 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 $0.25/M

Across 6 priced providers

Median input $0.41/M

Midpoint of listed rates

Highest input $0.58/M

2.3× the lowest listed rate

Output range $0.95 – $1.68

Per million output tokens

Vercel AI Gateway $0.25/MLowest
NovitaAI $0.27/M
Jiekou.AI $0.27/M
Abacus $0.55/M
Pioneer $0.56/M
Amazon Bedrock $0.58/M
Cost calculator

Estimate a workload

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

Context limits also differ by provider, from 128K to 163.84K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes
✓ Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
✓ Open weights Yes
Creator
DeepSeek
Model family
deepseek
Knowledge cutoff
Not documented
License
MIT License
Release date
2025-08-21
Model ID
deepseek/deepseek-v3.1

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
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
No changes recorded

This record has not changed within the retained import history.

Provenance

Sources & verification

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

Methodology
Last verified
Aug 06, 2026
Status
Source-linked
Confidence
Medium
Catalog source
Models.dev
Models.devcatalog ↗Vercel AI Gateway documentationprovider documentation ↗NovitaAI documentationprovider documentation ↗Jiekou.AI documentationprovider documentation ↗Abacus documentationprovider documentation ↗Pioneer documentationprovider documentation ↗Amazon Bedrock documentationprovider documentation ↗
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://www.modelbench.lol/api/v1/models/deepseek/deepseek-v3.1
curl
curl "https://www.modelbench.lol/api/v1/models/deepseek/deepseek-v3.1"
Common questions

Frequently asked questions

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

What is DeepSeek-V3.1?

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes. It is published by DeepSeek and catalogued here from Models.dev.

How much does DeepSeek-V3.1 cost?

Listed input pricing starts at $0.25 per million tokens from Vercel AI Gateway, rising to $0.58 across 6 listed providers.

What is the context length of DeepSeek-V3.1?

DeepSeek-V3.1 accepts up to 131.072K tokens of context and returns up to 8.192K output tokens.

Does DeepSeek-V3.1 support tool calling and structured output?

Provider catalogs list support for tool calling, and reasoning.

Which providers serve DeepSeek-V3.1?

6 providers list this model: Vercel AI Gateway, NovitaAI, Jiekou.AI, Abacus, Pioneer, Amazon Bedrock.

Are the weights for DeepSeek-V3.1 open?

Yes. The weights are published and downloadable from Hugging Face under the MIT License license.

When was DeepSeek-V3.1 released?

The catalog records a release date of 2025-08-21, last verified Aug 06, 2026.

More models from DeepSeek

View all →
DeepSeek V4 Pro

Open MoE flagship with million-token context for coding and long agent runs

1M ctx $0.435/M in DeepSeek V4 Flash

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

1M ctx $0.14/M in DeepSeek: DeepSeek V3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

163.84K ctx $0.269/M in DeepSeek: DeepSeek V3.2 Exp

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

163.84K ctx $0.27/M in