# Gemini 3.8 Flash

> Google's workhorse model for coding and agents, with sharper multi-turn coding, rapid refactoring, code synthesis, and tighter tool-execution logic.

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `google/gemini-3.8-flash`
- Status: available
- Released: 2026-09-02
- Context: 1M tokens
- Max output: 64K tokens
- Input: text, image, audio, video, pdf; output: text
- Knowledge cutoff: 2026-03
- Capability score: 158 (as of 2026-11-02, see https://www.ohmygpt.com/rankings.md)
- Human preference rating (LMArena text): 1498

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Input | $0.675 | per 1M tokens |
| Output | $3.375 | per 1M tokens |
| Cache read | $0.0675 | per 1M tokens |
| Reasoning output | $3.375 | per 1M tokens |
| Web search | $0.0126 | per request |

## Providers

Without a prefix each request goes to the best-priced healthy provider. To pin one, send the model as `<provider>:google/gemini-3.8-flash`.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| Google (Gemini) | `google:google/gemini-3.8-flash` | United States | $0.675 | $3.375 | no |
| Google Vertex AI | `vertex:google/gemini-3.8-flash` | Global | $0.675 | $3.375 | no |

## Endpoints

| API | Request | model |
| --- | --- | --- |
| OpenAI Chat | POST https://api.ohmygpt.com/v1/chat/completions | `google/gemini-3.8-flash` |
| OpenAI Responses | POST https://api.ohmygpt.com/v1/responses | `google/gemini-3.8-flash` |
| Anthropic Messages | POST https://api.ohmygpt.com/v1/messages | `google/gemini-3.8-flash` |
| Google Gemini | POST https://api.ohmygpt.com/v1/models/google/gemini-3.8-flash:generateContent | `google/gemini-3.8-flash` |

## Example

```bash
curl https://api.ohmygpt.com/v1/models/google/gemini-3.8-flash:generateContent \
  -H "x-goog-api-key: $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Hello"
          }
        ]
      }
    ]
  }'
```

Web page: https://www.ohmygpt.com/models/google/gemini-3.8-flash