API pricing

GitHub Copilot Pricing

GitHub Copilot charges from $1.20 per 1 million output tokens, depending on the model. GPT-5.6 Luna is the cheapest at $1.20/1M output and $0.200/1M input; its current flagship GPT-5.6 Sol costs $30.00/1M output. The largest context window is 1.1M tokens (GPT-5.4). Prices are USD, current as of August 11, 2026.

Last updated · synced weekly from the upstream model catalog

Cheapest input

$0.200/1M

GPT-5.4 nano

Cheapest output

$1.20/1M

GPT-5.6 Luna

Longest context

1.1M

GPT-5.4

Models priced

31

Avg $14.30/1M output

Pricing by model

All prices in USD per 1 million tokens. All 31 priced models, cheapest first.

ModelInput / 1MOutput / 1MContext
GPT-5.6 Luna
VisionReasoningToolsCache
$0.200$1.201.1M
GPT-5.4 nano
VisionReasoningToolsCache
$0.200$1.25400K
GPT-5 Mini
VisionReasoningToolsCache
$0.250$2.00264K
Kimi K2.7 Code
VisionReasoningToolsCache
$0.950$4.00256K
GPT-5.4 mini
VisionReasoningToolsCache
$0.750$4.50400K
Mai Code 1 Flash Internal$0.750$4.50128K
MAI-Code-1-Flash
ReasoningToolsCache
$0.750$4.50256K
Claude Haiku 4.5
VisionReasoningToolsCache
$1.00$5.00200K
Grok 4.5
VisionReasoningToolsCache
$2.00$6.00500K
Gemini 3.6 Flash
VisionReasoningToolsCache
$1.50$7.501.0M
GPT-4.1
VisionToolsCache
$2.00$8.00128K
Gemini 3.5 Flash
VisionReasoningToolsCache
$1.50$9.00200K
Claude Sonnet 5
VisionReasoningToolsCache
$2.00$10.001.0M
Gemini 3.1 Pro Preview
VisionReasoningToolsCache
$2.00$12.001.0M
GPT-5.6 Terra
VisionReasoningToolsCache
$2.00$12.001.1M
GPT-5.2
VisionReasoningToolsCache
$1.75$14.00400K
GPT-5.2 Codex
VisionReasoningToolsCache
$1.75$14.00400K
GPT-5.3 Codex
VisionReasoningToolsCache
$1.75$14.00400K
Claude Sonnet 4
VisionReasoningToolsCache
$3.00$15.00216K
Claude Sonnet 4.5
VisionReasoningToolsCache
$3.00$15.00200K
Claude Sonnet 4.6
VisionReasoningToolsCache
$3.00$15.00200K
GPT-5.4
VisionReasoningToolsCache
$2.50$15.001.1M
Kimi K3
VisionReasoningToolsCache
$3.00$15.001.0M
Claude Opus 4.5
VisionReasoningToolsCache
$5.00$25.00200K
Claude Opus 4.6
VisionReasoningToolsCache
$5.00$25.00200K
Claude Opus 4.7
VisionReasoningToolsCache
$5.00$25.00200K
Claude Opus 4.8
VisionReasoningToolsCache
$5.00$25.00200K
Claude Opus 5
VisionReasoningToolsCache
$5.00$25.001.0M
GPT-5.5
VisionReasoningToolsCache
$5.00$30.001.1M
GPT-5.6 Sol
VisionReasoningToolsCache
$5.00$30.001.1M
Claude Fable 5
VisionReasoningToolsCache
$10.00$50.001.0M

Frequently asked questions

How much does GitHub Copilot cost per 1M tokens?

GitHub Copilot pricing starts at $1.20 per 1 million output tokens (GPT-5.6 Luna) across 31 models, with its current flagship GPT-5.6 Sol at $30.00. Older premium models in the catalog list higher. Rates current as of August 11, 2026.

What is the cheapest GitHub Copilot model?

GPT-5.6 Luna is the cheapest GitHub Copilot model on output tokens at $1.20 per 1M, while GPT-5.4 nano is cheapest on input at $0.200 per 1M. Which wins for you depends on your input-to-output ratio.

What is the largest GitHub Copilot context window?

GPT-5.4 has the largest context window in the GitHub Copilot catalog at 1.1M input tokens, with up to 128K output tokens per response.

Does GitHub Copilot support prompt caching?

Yes. GPT-5.4 nano reads cached input at $0.020 per 1M tokens, against $0.200 per 1M uncached. Caching pays off when a long system prompt or document is reused across many requests.

Which GitHub Copilot models support reasoning or vision?

The GitHub Copilot catalog includes 29 reasoning models, 29 vision models, 30 with tool calling. Reasoning models bill their internal thinking as output tokens, so they cost more per visible response than the headline rate suggests.

How do I calculate my actual GitHub Copilot bill?

Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.

Other providers

What will this actually cost you?

Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.

Open the free cost calculator