Skip to main content
Blog
geminigemini 4gemini-4-argonpricing

Gemini 4 Argon API Pricing and Day 0 Support on LiteLLM

Gemini 4 Argon on LiteLLM: the LiteLLM and Gemini 4 Argon lockup, then Gemini 4 Argon selected in the LiteLLM model list.
Published:
Misbah SyedDevRel Engineer, LiteLLMMateo WangAI Engineer, LiteLLMKerry LuSoftware Engineer, LiteLLM

LiteLLM now supports Gemini 4 Argon on Day 0. Use it on Google AI Studio and Gemini Enterprise Agent Platform (formerly Vertex AI) through the LiteLLM AI Gateway. Spend, rate limits and logs are in one place.

Gemini 4 Argon pricing​

Launch prices on Google AI Studio, per 1M tokens, until November 30, 2026:

  • Input: $2.00 / MTok
  • Output: $10.00 / MTok. Thinking tokens bill as output.
  • Cache read: $0.10 / MTok. Argon supports implicit caching only.
  • Batch and Flex: 50% off input and output

On December 1, 2026, these prices double to $4.00 input, $20.00 output and $0.20 cache read.

Prices on every provider: https://models.litellm.ai/models

What's new in Gemini 4 Argon​

  • 77.9% on DeepSWE v1.1, per Google
  • 1M-token context window for input and output together. Google caps each request at 32,768 output tokens (65,536 when streaming), and LiteLLM continues past that cap for you
  • Thinking levels low, medium and high. Argon does not support thinking_budget.

Use Gemini 4 Argon with LiteLLM​

No upgrade needed: open Price Data under Models + Endpoints in the UI and click Reload Price Data (or POST /reload/model_cost_map), on v1.76.0 and above.

1. Setup config.yaml

model_list:
  - model_name: gemini-4-argon
    litellm_params:
      model: gemini/gemini-4-argon
      api_key: os.environ/GEMINI_API_KEY

2. Start the proxy

docker run -d \
  -p 4000:4000 \
  -e GEMINI_API_KEY=$GEMINI_API_KEY \
  -v $(pwd)/config.yaml:/app/config.yaml \
  ghcr.io/berriai/litellm:v1.107.0-dev.3 \
  --config /app/config.yaml

3. Test it!

curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $LITELLM_KEY' \
--data '{
  "model": "gemini-4-argon",
  "messages": [
    {
      "role": "user",
      "content": "what llm are you"
    }
  ],
  "reasoning_effort": "high"
}'

LiteLLM sends reasoning_effort to Argon as its thinking_level.

Long outputs​

From v1.107.0-dev.3, set max_tokens above Google's per-request cap and LiteLLM keeps going. When Google ends a request with a continuationToken, LiteLLM sends the request again with that token until the answer finishes or max_tokens is spent. This works for unary and streaming calls on /chat/completions, /v1/messages and /v1/responses, on Google AI Studio and Gemini Enterprise Agent Platform. A request with n above 1 is sent once, and so is a request whose max_tokens is not an integer, or one with no max_tokens while LITELLM_GEMINI_DEFAULT_MAX_OUTPUT_TOKENS is unset.

  • Requests with no max_tokens: from v1.108.0, set the env var LITELLM_GEMINI_DEFAULT_MAX_OUTPUT_TOKENS to an integer, and a Gemini chat completion, text completion or Responses API request that sends no output limit gets that budget, through the proxy or the Python SDK. /v1/messages requires max_tokens, so the env var never applies there. LiteLLM caps the budget at the model's max_output_tokens in the cost map, or at a deployment's own model_info.max_output_tokens when that is lower, since Gemini Enterprise Agent Platform answers 400 above a model's range. It gives no default to a model missing from the cost map or listed there as anything besides a chat model, such as an image model, to a chat model whose cost map entry leaves text out of supported_output_modalities, such as a Lyria music model, to a request whose modalities asks for anything besides text, to a request whose extra_body field holds a snake_case generation_config, to a request that resumes with a continuation_token, to Google's native /v1beta/models/{model}:generateContent route on a gemini/ or vertex_ai/ model or to Gemini Enterprise Agent Platform batch jobs. Any output limit the request already carries wins, such as its own max_tokens, max_completion_tokens or max_output_tokens, or a deployment's litellm_params.max_tokens. Zero, a negative number or a value that is not an integer counts as unset. On a model that returns no continuationToken, the budget is a plain output limit.
  • Choosing the budget: it also caps answers that fit in one request, so a value below the model's own per-request limit (32,768 on Gemini 4 Argon, or 65,536 when streaming) cuts them off sooner. Thinking tokens count against it too, so on a thinking model a low value can leave little or no room for the answer. It bounds output tokens, not cost, since each request to Google sends the prompt and the answer so far again and bills them as prompt tokens. A client that never set max_tokens now waits for the whole answer. With a large value, a non-streamed request can run past the client's own timeout (600 seconds in the OpenAI SDK), and the SDK then retries while LiteLLM keeps running and billing the request it gave up on, so stream long answers or give the client the room the Timeouts bullet describes.
  • Usage is summed across the requests, so cost and spend match Google's bill. The first request's prompt count is kept as usage.prompt_tokens_details.initial_prompt_tokens on an answer that took more than one request.
  • A cut-off answer on /chat/completions ends with finish_reason: "length" and returns provider_specific_fields.continuation_token. Send the request again with that "continuation_token" and a higher max_tokens to continue it, since Google counts max_tokens across the whole answer.
  • A dropped stream ends with the error. LiteLLM does not yet pick it back up from Google's mid-stream resume tokens.
  • Timeouts: each request to Google runs under the deployment's timeout, 600 seconds when unset. A non-streamed request at the 32,768 cap takes about 10 minutes, so set timeout: 1200 on deployments that serve long answers and give your client room for the whole answer.

FAQ​

How much does Gemini 4 Argon cost?​

Until November 30, 2026, it costs $2.00 per 1M input tokens and $10.00 per 1M output tokens. On December 1, the prices change to $4.00 and $20.00. Cache reads cost $0.10 per 1M tokens until then.

What is the context window of Gemini 4 Argon?​

1,048,576 tokens for input and output together. Google returns up to 32,768 output tokens per request (65,536 when streaming), and from v1.107.0-dev.3 LiteLLM continues across requests until max_tokens is spent.

How do I call Gemini 4 Argon with an OpenAI-compatible API?​

Add gemini/gemini-4-argon to your LiteLLM config. Then send a standard /chat/completions request to the proxy with "model": "gemini-4-argon".

Feedback​

Questions and feedback go in GitHub discussion #46238.

References​