Gemini 3.8 Flash API pricing
Google's current production Flash model for long-horizon software engineering, autonomous agents and complex multimodal workflows.
How much does Gemini 3.8 Flash API cost?
Gemini 3.8 Flash costs $0.75 per 1 million input tokens and $3.75 per 1 million output tokens through TokenGate.
| Condition | Input tokens / 1M | Cached input / 1M | Output tokens / 1M |
|---|---|---|---|
| Introductory, through 31 Dec 2026 | $0.75 | $0.075 | $3.75 |
| Standard, from 1 Jan 2027 | $1.50 | $0.15 | $7.50 |
- Introductory pricing through 31 December 2026. Standard pricing applies from 1 January 2027.
Estimate Gemini 3.8 Flash API cost
Estimated TokenGate cost, denominated in USDT.
Use Gemini 3.8 Flash with the OpenAI SDK
curl https://api.tokengate.com/v1/chat/completions \
-H "Authorization: Bearer $TOKENGATE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gemini-3.8-flash","messages":[{"role":"user","content":"Hello"}]}'Change the model identifier to use another supported model through the same TokenGate integration.
Model specifications
- Provider
- API model identifier
- gemini-3.8-flash
- Generation
- 3.8
- Provider lifecycle
- Active
- Context window
- 1.05M
- Maximum output tokens
- 66K
- Input modalities
- Text, Image, Video, Audio, PDF
- Output modalities
- Text
- Capabilities
- Streaming, Function calling, Structured outputs, Vision, Reasoning, Tool use, Web search, Computer use, Code execution
Best for
- Coding
- Agents
- Enterprise workflows
- Multimodal
- Long context
Access Gemini 3.8 Flash through TokenGate
Use supported models through a single TokenGate integration.
- · One API integration
- · OpenAI-compatible interface
- · Payment in USDT
Frequently asked questions
Related models
Gemini 3.7 Flash
Previous-generation Google Flash model with multimodal input and a large context window.
- Input / 1M
- $0.75
- Output / 1M
- $3.75
- Context
- 1.05M
- Generation
- 3.7
Streaming · Function calling · Structured outputs
Gemini 3.7 Flash API pricingClaude Fable 5.1
Anthropic's most capable generally available model for ambitious coding, long-running agents, research and complex knowledge work.
- Input / 1M
- $10.00
- Output / 1M
- $50.00
- Context
- —
- Generation
- 5.1
Streaming · Function calling · Vision
Claude Fable 5.1 API pricingDeepSeek V4.1 Flash
DeepSeek's current Flash model with native multimodal support and strong coding, reasoning and agentic capabilities.
- Input / 1M
- Variable pricing
- Output / 1M
- —
- Context
- —
- Generation
- 4.1
Streaming · Function calling · Structured outputs
DeepSeek V4.1 Flash API pricingTokenGate