GitHub Copilot Pricing
GitHub Copilot charges between $1.25 and $50.00 per 1 million output tokens, depending on the model. GPT-5.4 nano is the cheapest at $1.25/1M output and $0.200/1M input; Claude Fable 5 is the most expensive at $50.00/1M output. The largest context window is 1.1M tokens (GPT-5.4). Prices are USD, current as of July 20, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.200/1M
GPT-5.4 nano
Cheapest output
$1.25/1M
GPT-5.4 nano
Longest context
1.1M
GPT-5.4
Models priced
29
Avg $14.16/1M output
Pricing by model
All prices in USD per 1 million tokens. All 29 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| GPT-5.4 nano VisionReasoningToolsCache | $0.200 | $1.25 | 400K |
| GPT-5 Mini VisionReasoningToolsCache | $0.250 | $2.00 | 264K |
| Gemini 3 Flash Preview VisionReasoningToolsCache | $0.500 | $3.00 | 128K |
| Kimi K2.7 Code VisionReasoningToolsCache | $0.950 | $4.00 | 256K |
| GPT-5.4 mini VisionReasoningToolsCache | $0.750 | $4.50 | 400K |
| Mai Code 1 Flash Internal | $0.750 | $4.50 | 128K |
| MAI-Code-1-Flash ReasoningToolsCache | $0.750 | $4.50 | 256K |
| Claude Haiku 4.5 VisionReasoningToolsCache | $1.00 | $5.00 | 200K |
| GPT-5.6 Luna VisionReasoningToolsCache | $1.00 | $6.00 | 1.1M |
| GPT-4.1 VisionToolsCache | $2.00 | $8.00 | 128K |
| Gemini 3.5 Flash VisionReasoningToolsCache | $1.50 | $9.00 | 200K |
| Claude Sonnet 5 VisionReasoningToolsCache | $2.00 | $10.00 | 1.0M |
| Gemini 2.5 Pro VisionReasoningToolsCache | $1.25 | $10.00 | 128K |
| Gemini 3.1 Pro Preview VisionReasoningToolsCache | $2.00 | $12.00 | 1.0M |
| GPT-5.2 VisionReasoningToolsCache | $1.75 | $14.00 | 400K |
| GPT-5.2 Codex VisionReasoningToolsCache | $1.75 | $14.00 | 400K |
| GPT-5.3 Codex VisionReasoningToolsCache | $1.75 | $14.00 | 400K |
| Claude Sonnet 4 VisionReasoningToolsCache | $3.00 | $15.00 | 216K |
| Claude Sonnet 4.5 VisionReasoningToolsCache | $3.00 | $15.00 | 200K |
| Claude Sonnet 4.6 VisionReasoningToolsCache | $3.00 | $15.00 | 200K |
| GPT-5.4 VisionReasoningToolsCache | $2.50 | $15.00 | 1.1M |
| GPT-5.6 Terra VisionReasoningToolsCache | $2.50 | $15.00 | 1.1M |
| Claude Opus 4.5 VisionReasoningToolsCache | $5.00 | $25.00 | 200K |
| Claude Opus 4.6 VisionReasoningToolsCache | $5.00 | $25.00 | 200K |
| Claude Opus 4.7 VisionReasoningToolsCache | $5.00 | $25.00 | 200K |
| Claude Opus 4.8 VisionReasoningToolsCache | $5.00 | $25.00 | 200K |
| GPT-5.5 VisionReasoningToolsCache | $5.00 | $30.00 | 1.1M |
| GPT-5.6 Sol VisionReasoningToolsCache | $5.00 | $30.00 | 1.1M |
| Claude Fable 5 VisionReasoningToolsCache | $10.00 | $50.00 | 1.0M |
Frequently asked questions
How much does GitHub Copilot cost per 1M tokens?
GitHub Copilot pricing ranges from $1.25 to $50.00 per 1 million output tokens across 29 models. Input tokens are cheaper than output on every model. Rates current as of July 20, 2026.
What is the cheapest GitHub Copilot model?
GPT-5.4 nano is the cheapest GitHub Copilot model on both axes — $0.200 per 1M input tokens and $1.25 per 1M output. It is the right default for high-volume, low-complexity work such as classification, extraction and routing.
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 27 reasoning models, 27 vision models, 28 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