DeepSeek API: models and pricing

FastMetal serves 8 DeepSeek models through one OpenAI-compatible API key, billed per token from a prepaid balance. Change the base URL and key, and existing code calls them as is. The list also shows DeepSeek models we do not serve yet.

Sort by:

20 models

DeepSeek V4.1 Flash 1017

deepseek-v4.1-flash-1017
ZDR

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...

Provider:deepseek logoDeepSeek
Pricing:$0.2142 in · $0.8565 out / 1M tokens
Context:1.0M tokens

DeepSeek V4.1 Flash 1017 Japan

japan-deepseek-v4.1-flash-1017
Japan
ZDR

DeepSeek's V4.1 Flash 1017 - the October 17, 2026 snapshot, image input, hosted and run in Japan

Provider:deepseek logoDeepSeek
Pricing:$0.2142 in · $0.8565 out / 1M tokens
Context:1.0M tokens

DeepSeek V4.1 Flash

deepseek-v4.1-flash

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Provider:deepseek logoDeepSeek
Pricing:$0.211 in · $0.633 out / 1M tokens
Context:1.0M tokens

DeepSeek V4 Flash

deepseek-v4-flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Provider:deepseek logoDeepSeek
Pricing:$0.095 in · $0.1899 out / 1M tokens
Context:1.0M tokens
Text Overall
#105

DeepSeek V4 Pro

deepseek-v4-pro

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

Provider:deepseek logoDeepSeek
Pricing:$1.38 in · $2.75 out / 1M tokens
Context:1.0M tokens
Text Overall
#66

DeepSeek V3.2

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.

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:164K tokens
Text Overall
#125

DeepSeek V3.2 Speciale

deepseek/deepseek-v3.2-speciale

DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance.

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:164K tokens

DeepSeek V3.2 Exp

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.

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:164K tokens
Text Overall
#131

DeepSeek V3.1 Terminus

deepseek/deepseek-v3.1-terminus

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further…

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:164K tokens
Text Overall
#144

DeepSeek V3.1 Terminus (exacto)

deepseek/deepseek-v3.1-terminus:exacto

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further…

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:164K tokens

DeepSeek V3.1

deepseek/deepseek-chat-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.

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:33K tokens
Text Overall
#139

R1 0528

deepseek/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.

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:164K tokens

DeepSeek V3 0324

deepseek/deepseek-chat-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.

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:164K tokens

R1 Distill Qwen 32B

deepseek/deepseek-r1-distill-qwen-32b

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1).

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:33K tokens

R1 Distill Llama 70B

deepseek/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).

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:131K tokens

R1

deepseek/deepseek-r1

DeepSeek R1 is here: 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 in an inference pass.

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:64K tokens
Text Overall
#170

DeepSeek V3

deepseek/deepseek-chat

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.

Provider:deepseek logoDeepSeek
Pricing:Not on FastMetal yet
Context:164K tokens
Text Overall
#213

DeepSeek V4.1 Flash 1017 Uncensored

deepseek-v4.1-flash-1017-uncensored
Policy unknown

DeepSeek V4.1 Flash 1017, uncensored - the October 17 snapshot without the usual refusals, 1M context

Provider:deepseek logoDeepSeek
Pricing:$0.3482 in · $1.40 out / 1M tokens
Context:1.0M tokens

DeepSeek V4.1 Flash Uncensored

deepseek-v4.1-flash-uncensored
Policy unknown

DeepSeek V4.1 Flash, uncensored - a fine-tune without the usual refusals, 1M context

Provider:deepseek logoDeepSeek
Pricing:$0.3482 in · $1.40 out / 1M tokens
Context:1.0M tokens

deepseek-v4-flash-0731

deepseek-v4-flash-0731

DeepSeek's V4 Flash 0731

Provider:deepseek logoDeepSeek
Pricing:$0.1477 in · $0.2954 out / 1M tokens
Context:- tokens

Posts about DeepSeek

Product update

FastMetal now works with Cursor and DeepSeek Harness

Use your FastMetal API key in Cursor and in DeepSeek Harness, DeepSeek's open-source coding agent. Paste a key and a base URL, pick a model, and usage comes out of the same prepaid balance.

Tutorial

How to use DeepSeek Harness (dsh) with a custom API: FastMetal setup

DeepSeek Harness, DeepSeek's open-source coding agent, runs on any OpenAI-compatible endpoint. Here is the FastMetal setup, the one thinking setting that trips people up, and what happened when we let DeepSeek V4 Pro fix real bugs.

Column

MiniMax M3.1 Flash vs DeepSeek V4.1 Flash: same rate, 8x the tokens

MiniMax M3.1 Flash and DeepSeek V4.1 Flash bill output at the same rate. On the same 14 prompts, M3.1 Flash thought its way to 8x the output tokens, and a much larger bill.

New model

DeepSeek V4.1 Flash 1017 API: now on FastMetal

DeepSeek V4.1 Flash 1017, the October 17 snapshot of V4.1 Flash, is now on FastMetal's API and chat at the same price as V4.1 Flash, with higher coding and agent scores and shorter answers.

Column

DeepSeek V4.1 Flash vs GLM 5.3 Flash: same answer, 12x the tokens

We ran DeepSeek V4.1 Flash and GLM 5.3 Flash on the same 43 prompts. The answers were about the same length, but DeepSeek used 1.7x the output tokens on average and 12x on one SQL task. All of it was thinking.

New model

DeepSeek V4.1 Flash API: 1M context, image input, reasoning control

DeepSeek V4.1 Flash is on FastMetal: a 1M-token context, the first Flash model from DeepSeek that reads images, and a reasoning setting you can turn down to low or off.

See pricing for every model