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

How do I use Gemini 3.8 Flash in Claude Code?

google/gemini-3.8-flash

Claude Code reaches Gemini 3.8 Flash through the Anthropic-compatible address of MartLLM. Set ANTHROPIC_BASE_URL to https://api.martllm.com (with no /v1 at the end), ANTHROPIC_AUTH_TOKEN to your MartLLM key and ANTHROPIC_MODEL to google/gemini-3.8-flash[1m], then start claude. Set the opus, sonnet, haiku and subagent model variables to google/gemini-3.8-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 Gemini 3.8 Flash has a 1M-token context; without it Claude Code plans for 200,000 tokens.

bash
export ANTHROPIC_BASE_URL=https://api.martllm.com
export ANTHROPIC_AUTH_TOKEN=ull_your_key
export ANTHROPIC_MODEL='google/gemini-3.8-flash[1m]'
export ANTHROPIC_DEFAULT_OPUS_MODEL='google/gemini-3.8-flash'
export ANTHROPIC_DEFAULT_SONNET_MODEL='google/gemini-3.8-flash'
export ANTHROPIC_DEFAULT_HAIKU_MODEL='google/gemini-3.8-flash'
export CLAUDE_CODE_SUBAGENT_MODEL='google/gemini-3.8-flash'
claude

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

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

By API, Gemini 3.8 Flash answers on three addresses with the same MartLLM key and the model id google/gemini-3.8-flash: OpenAI chat completions at https://api.martllm.com/v1/chat/completions, the OpenAI Responses API at https://api.martllm.com/v1/responses and the Anthropic Messages API at https://api.martllm.com/v1/messages.

How much does the Gemini 3.8 Flash API cost?

On November 20, 2026, Gemini 3.8 Flash costs $0.0749 per million input tokens and $0.3743 per million output tokens through MartLLM, 90% below its list price of $0.75 and $3.75. 65 sellers on the market can serve it. In the 7 days before, half of its 29,091 streamed requests got their first token within 3.3 seconds, with a typical prompt of 47,838 tokens. It reads up to 1,048,576 tokens of context. MartLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 11:00 UTC.

Gemini 3.8 Flash in other tools

Other models in Claude Code