GitHub Copilot Pricing
GitHub Copilot charges from $0.500 per 1 million output tokens, depending on the model. Claude Haiku 5.5 is the cheapest at $0.500/1M output and $0.100/1M input; its current flagship Claude Opus 5.5 costs $20.00/1M output. The largest context window is 1.1M tokens (GPT-5.4). Prices are USD, current as of October 12, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.100/1M
Claude Haiku 5.5
Cheapest output
$0.500/1M
Claude Haiku 5.5
Longest context
1.1M
GPT-5.4
Models priced
35
Avg $13.40/1M output
Pricing by model
All prices in USD per 1 million tokens. All 35 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Claude Haiku 5.5 VisionReasoningToolsCache | $0.100 | $0.500 | 1.0M |
| GPT-6 Luna VisionReasoningToolsCache | $0.100 | $0.500 | 1.1M |
| GPT-5.6 Luna VisionReasoningToolsCache | $0.200 | $1.20 | 1.1M |
| MAI-Code-1.1-Flash VisionReasoningToolsCache | $0.200 | $1.20 | 256K |
| GPT-5.4 nano VisionReasoningToolsCache | $0.200 | $1.25 | 400K |
| GPT-5 Mini VisionReasoningToolsCache | $0.250 | $2.00 | 264K |
| Gemini 3.6 Flash VisionReasoningToolsCache | $0.750 | $3.75 | 1.0M |
| Gemini 3.7 Flash VisionReasoningToolsCache | $0.750 | $3.75 | 1.0M |
| Gemini 3.8 Flash VisionReasoningToolsCache | $0.750 | $3.75 | 1.0M |
| Kimi K2.7 Code VisionReasoningToolsCache | $0.950 | $4.00 | 256K |
| GPT-5.4 mini VisionReasoningToolsCache | $0.750 | $4.50 | 400K |
| MAI-Code-1-Flash ReasoningToolsCache | $0.750 | $4.50 | 256K |
| Claude Haiku 4.5 VisionReasoningToolsCache | $1.00 | $5.00 | 200K |
| Grok 4.5 VisionReasoningToolsCache | $2.00 | $6.00 | 500K |
| Grok 4.6 VisionReasoningToolsCache | $2.00 | $6.00 | 500K |
| Grok 4.7 VisionReasoningToolsCache | $2.00 | $6.00 | 500K |
| Gemini 3.5 Flash VisionReasoningToolsCache | $1.50 | $9.00 | 200K |
| Claude Sonnet 5 VisionReasoningToolsCache | $2.00 | $10.00 | 1.0M |
| Claude Sonnet 5.5 VisionReasoningToolsCache | $2.00 | $10.00 | 1.0M |
| GPT-6 Sol VisionReasoningToolsCache | $2.00 | $10.00 | 1.1M |
| GPT-6.1 Sol VisionReasoningToolsCache | $2.00 | $10.00 | 1.1M |
| GPT-5.6 Terra VisionReasoningToolsCache | $2.00 | $12.00 | 1.1M |
| GPT-5.3 Codex VisionReasoningToolsCache | $1.75 | $14.00 | 400K |
| Claude Sonnet 4.6 VisionReasoningToolsCache | $3.00 | $15.00 | 200K |
| GPT-5.4 VisionReasoningToolsCache | $2.50 | $15.00 | 1.1M |
| Kimi K3 VisionReasoningToolsCache | $3.00 | $15.00 | 1.0M |
| Claude Opus 5.5 VisionReasoningToolsCache | $4.00 | $20.00 | 1.0M |
| GPT-5.6 Sol VisionReasoningToolsCache | $4.00 | $20.00 | 1.1M |
| Claude Opus 4.7 VisionReasoningToolsCache | $5.00 | $25.00 | 200K |
| Claude Opus 4.8 VisionReasoningToolsCache | $5.00 | $25.00 | 200K |
| Claude Opus 5 VisionReasoningToolsCache | $5.00 | $25.00 | 1.0M |
| GPT-5.5 VisionReasoningToolsCache | $5.00 | $30.00 | 1.1M |
| Claude Fable 5 VisionReasoningToolsCache | $10.00 | $50.00 | 1.0M |
| Claude Fable 5.1 VisionReasoningToolsCache | $10.00 | $50.00 | 1.0M |
| GPT-6 Astra VisionReasoningToolsCache | $10.00 | $50.00 | 1.1M |
Frequently asked questions
How much does GitHub Copilot cost per 1M tokens?
GitHub Copilot pricing starts at $0.500 per 1 million output tokens (Claude Haiku 5.5) across 35 models, with its current flagship Claude Opus 5.5 at $20.00. Older premium models in the catalog list higher. Rates current as of October 12, 2026.
What is the cheapest GitHub Copilot model?
Claude Haiku 5.5 is the cheapest GitHub Copilot model on both axes — $0.100 per 1M input tokens and $0.500 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. Claude Haiku 5.5 reads cached input at $0.010 per 1M tokens, against $0.100 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 35 reasoning models, 34 vision models, 35 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