Gemini 2.5 Flash is Google's high-speed multimodal language model, optimized for rapid text generation, real-time image understanding, and high-frequency tasks. Supports text and image inputs. Token-based pricing: $0.30/M input tokens, $2.50/M output tokens. Two endpoints: standard async (/gemini-2-5-flash) and live streaming (/gemini-2-5-flash/stream) via SSE.
About this model
Gemini 2.5 Flash is Google's high-speed multimodal language model, optimized for rapid text generation, real-time image understanding, and high-frequency tasks. Pricing: $0.30 per million input tokens and $2.50 per million output tokens.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.30/M input tokens, $2.50/M output tokens | Token-based billing. Minimum $0.00005 per call. Built for scale. |
| Fal.ai | $0.40/M input tokens, $3.00/M output tokens | muapiapp remains more cost-effective. |
| Replicate | $0.42/M input tokens, $3.10/M output tokens | muapiapp remains more cost-effective. |
Token-based billing. Minimum $0.00005 per call. Built for scale.
muapiapp remains more cost-effective.
muapiapp remains more cost-effective.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | The user message or instruction for the model. | Explain quantum computing in simple terms. |
| Image URL | string | Optional image URL to include as multimodal input. | undefined |
| System Prompt | string | Optional system-level instruction to guide model behavior. | You are a helpful physics teacher. |
The user message or instruction for the model.
Explain quantum computing in simple terms.Optional image URL to include as multimodal input.
undefinedOptional system-level instruction to guide model behavior.
You are a helpful physics teacher.Developer documentation
POST /api/v1/gemini-2-5-flash — returns request_id, poll for result via /api/v1/predictions/{id}/result.
POST /api/v1/gemini-2-5-flash/stream — returns a live SSE stream. Each chunk: data: {"choices":[{"delta":{"content":"text"}}]}, ending with data: [DONE].
See Streaming Documentation for full code examples.
Frequently asked
Pricing is token-based: $0.30 per million input tokens and $2.50 per million output tokens. The minimum charge per call is $0.00005. Actual cost is deducted after each call based on token counts returned by the model.
Yes. Pass an image_url in the request body to include an image as part of the user message.
Yes. You can supply an optional system_prompt field to guide the model's behavior and tone.