NewHow we catch a seller listing the wrong model, and refund you if one does.
UberLLM
DeepSeek logo

How do I use DeepSeek V4.1 Flash in Claude Code?

deepseek/deepseek-v4.1-flash

Claude Code reaches DeepSeek V4.1 Flash through the Anthropic-compatible address of UberLLM. Set ANTHROPIC_BASE_URL to https://api.uberllm.dev (with no /v1 at the end), ANTHROPIC_AUTH_TOKEN to your UberLLM key and ANTHROPIC_MODEL to deepseek/deepseek-v4.1-flash[1m], then start claude. Set the opus, sonnet, haiku and subagent model variables to deepseek/deepseek-v4.1-flash as well: a slot left unset keeps asking for a Claude model at Claude prices. The [1m] at the end of the id tells Claude Code that DeepSeek V4.1 Flash has a 1M-token context; without it Claude Code plans for 200,000 tokens.

bash
export ANTHROPIC_BASE_URL=https://api.uberllm.dev
export ANTHROPIC_AUTH_TOKEN=ull_your_key
export ANTHROPIC_MODEL='deepseek/deepseek-v4.1-flash[1m]'
export ANTHROPIC_DEFAULT_OPUS_MODEL='deepseek/deepseek-v4.1-flash'
export ANTHROPIC_DEFAULT_SONNET_MODEL='deepseek/deepseek-v4.1-flash'
export ANTHROPIC_DEFAULT_HAIKU_MODEL='deepseek/deepseek-v4.1-flash'
export CLAUDE_CODE_SUBAGENT_MODEL='deepseek/deepseek-v4.1-flash'
claude

Claude Code calls: Anthropic Messages API https://api.uberllm.dev/v1/messages · Full Claude Code guide

Replace ull_your_key with your UberLLM API key. One key works in every tool and for every model.

By API, DeepSeek V4.1 Flash answers on three addresses with the same UberLLM key and the model id deepseek/deepseek-v4.1-flash: OpenAI chat completions at https://api.uberllm.dev/v1/chat/completions, the OpenAI Responses API at https://api.uberllm.dev/v1/responses and the Anthropic Messages API at https://api.uberllm.dev/v1/messages.

How much does the DeepSeek V4.1 Flash API cost?

On November 19, 2026, DeepSeek V4.1 Flash costs $0.00248 per million input tokens and $0.00991 per million output tokens through UberLLM, 99.2% below its list price of $0.30 and $1.20. 244 sellers on the market can serve it. In the 7 days before, half of its 359,231 streamed requests got their first token within 6.0 seconds, with a typical prompt of 89,693 tokens. It reads up to 1,048,576 tokens of context. UberLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 08:00 UTC.

DeepSeek V4.1 Flash in other tools

Other models in Claude Code