Skip to content
DeepSeek

DeepSeek Coder V2

deepseek/deepseek-coder-v2
Open weightsCoding

Open coding specialist with fine-tuning support, a cost-effective base for code assistants and CI automation.

Model overview

Context window

128K

tokens

Input price

—

quoted on request

Output price

—

quoted on request

Weekly volume

—

tokens / week

Open weights

Yes

self-hostable

Capabilities

5

of 11 tags

Description

DeepSeek Coder V2 is a coding model from DeepSeek. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. DeepSeek’s stated focus is open-weight frontier reasoning at disruptive economics. Its mean it can also be self-hosted under its licence.

Capabilities

Tool calling
Calls functions you define and returns their arguments as structured data, the basis of agents.
JSON mode
Constrains the response to valid JSON matching a schema you supply.
Streaming
Emits tokens as they are generated, so answers appear progressively rather than all at once.
Open weights
The parameters are published, so the model can be inspected, fine-tuned and self-hosted under its licence.
Fine-tunable
Can be further trained on your own data to specialise it.

Strengths & weaknesses

Strengths

  • Very low per-token cost
  • Fine-tunable on private code
  • Solid multi-language coverage

Weaknesses

  • Trails agentic leaders on repository-scale tasks
  • No vision input

Pricing

Pricing for DeepSeek Coder V2, per 1M tokens
RatePriceUnit
Input— quoted on request—
Output— quoted on request—

This model is not provisioned yet; the rate is quoted on request.

Context window

128Ktokens

covers prompt and response together, so a long input leaves less room for the answer.

128K tokens against a peer range of 128K to 1M, median 256K. Compared across 4 coding models.

Supported features

Feature support for DeepSeek Coder V2
FeatureSupport
Tool callingSupported
JSON modeSupported
StreamingSupported
Vision inputNot supported
Audio inputNot supported
Long contextNot supported
Open weightsSupported
ReasoningNot supported
Fine-tunableSupported
BatchNot supported
CachingNot supported

Example use cases

  • Code completion

  • CI review bots

  • Fine-tuned internal assistants

Related models

Comparison

Compare against anything →
DeepSeek Coder V2 compared with Qwen3 Coder and Codestral 2
AttributeDeepSeek Coder V2Qwen3 CoderCodestral 2
Context window128K256K256K
Input priceR0.00R0.00R0.00
Output price— not charged— not charged— not charged
Tool callingSupportedSupportedSupported
JSON modeSupportedSupportedSupported
Vision inputNot supportedNot supportedNot supported
Open weightsSupportedSupportedNot supported
Prompt cachingNot supportedNot supportedNot supported

Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.

Provider information

View DeepSeek →
DeepSeek5 models

DeepSeek · 深度求索 · Hangzhou, China · est. 2023

Spun out of a quantitative trading firm, DeepSeek built its reputation by releasing open-weight models that matched closed frontier quality at a fraction of the price. Its V-series redefined cost expectations for production LLMs, and its R-series brought open reasoning models into serious enterprise conversations.

Recent releases

    Documentation

    Frequently asked questions

    Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Every figure on this page is an illustrative placeholder.