gemini-3-7-flash

gemini first-party price GPQA 95%

Also listed as deepinfra/google/gemini-3.7-flash, gemini-3.7-flash, gemini/gemini-3.7-flash, openrouter/google/gemini-3.7-flash, perplexity/google/gemini-3.7-flash, vertex_ai/gemini-3.7-flash

Input$0.750per 1M tokens

Output$3.75per 1M tokens

Cached input$0.075per 1M tokens

A 1,000-in / 300-out request costs $0.0019 First-party list price · gemini · recorded 2026-06-19

Price over time

One price recorded so far — nothing to chart yet. It will appear here the day the price changes.

The same capability, cheaper

gemini-3-7-flash scores 95% on GPQA Diamond. The cheapest model clearing the GPQA 90%+ bar today is glm-5-3-flash at $0.237 blended — 6.3× less than this model's $1.50. Blended = 75% input, 25% output. Capability is one benchmark, not the whole story.

95%
GPQA Diamond: 97%
Mock AIME: 1,048,576
Context window: 2026-08-13
Released: Google DeepMind
Developer: 1
Price changes: 2026-06-19
Tracked since

Recorded price changes

One row per change, newest first. US dollars per million tokens. Each row links to the exact commit or archived page the figure was read from.

Date	Input	Output	Cached in	Blended	Change	Source
2026-06-19	$0.750	$3.75	$0.075	$1.50		litellm@3ead9d1

How this was collected

Prices come from replaying the version history of LiteLLM's public pricing file and from vendor pricing pages archived by the Wayback Machine, then cleaned to remove metadata edits, same-day churn, unit slips and typo corrections. The full method and every script is in the repository. List pricing, not negotiated pricing.

See how the cost of a fixed level of capability has fallen →