Skip to main content

Gemini 2.5 Flash

Gemini 2 5 Flash is a Google Gemini model for multimodal reasoning, coding, generation, and long-context tasks.

Input / output price
$0.30 / $2.50 per 1M
Context
1M tokens
Released
Apr 17, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "gemini-2.5-flash".

Read docs

Providers

5 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/gemini-2.5-flash
$0.30/M$2.50/M
DeepInfradeepinfra/gemini-2.5-flash
$0.30/M$2.50/M
Inference.netinference_net/gemini-2.5-flash
$0.30/M$2.50/M
Google Vertex AIRetiredvertex_ai/gemini-2.5-flash
$0.30/M$2.50/M
OpenRouteropenrouter/gemini-2.5-flash
$0.30/M$2.50/M

Is a provider down? Gemini status, OpenRouter status

Pricing

Averaged across 5 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.30 per 1M
Average output
$2.50 per 1M
Average cache read
$0.04 per 1M
Average cache write
$0.03 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.30/MConcentrate, DeepInfra, Inference.net, Google Vertex AI, and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

14tokens/sacross providers

Faster than 42% of the other 596 models on the gateway

Time to first token

Lower is better

1.0sacross providers

Faster than 68% of the other 153 models on the gateway

Response latency

Lower is better

0.8sacross providers

Faster than 69% of the other 768 models on the gateway

Benchmarks

The Respan Index plus 13 published scores from 6 sources, each linked to where it was published.

18.6/ 100

Respan Index#141 of 176

176 ranked models. The shaded band is this model's 95% interval, 14.0 to 29.3. Gemma 4 31B and Qwen3 235B-A22B Thinking 2507 fall inside it, so the gap is within the margin of error.
Gemini 2.5 Flash by category: Coding 2.1, Agents 17.9, Reasoning 20.7, Knowledge & language 13.1 (estimated), Human preference 47.1
  1. 141Gemini 2.5 Flash18.6
  2. 140Gemma 4 31B18.7
  3. 142Qwen3 235B-A22B Thinking 250718.5

Published scores

BenchmarkScore
LiveCodeBenchstorage.googleapis.com59.3%
Aider Polyglotstorage.googleapis.com56.7%
SWE-bench Verified (single attempt)storage.googleapis.com48.9%

Compare Gemini 2.5 Flash: Gemini 2.5 Flash vs Gemini 3.5 Flash, Gemini 2.5 Flash vs Dola Seed 2.0 Pro, Gemini 2.5 Flash vs Gemini 4 Neon, Gemini 2.5 Flash vs Gemini 4 Carbon, Gemini 2.5 Flash vs Gemini 4 Hydrogen, Gemini 2.5 Flash vs Gemini 4 Argon

Apps

Use Gemini 2.5 Flash in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Gemini 2.5 Flash FAQ

Short answers, built from the data on this page.

Gemini 2.5 Flash is a model from Google Gemini AI, released on Apr 17, 2025. Gemini 2 5 Flash is a Google Gemini model for multimodal reasoning, coding, generation, and long-context tasks.

On the Respan gateway, Gemini 2.5 Flash costs $0.30 per 1M input tokens and $2.50 per 1M output tokens on every provider, after gateway discounts.

Gemini 2.5 Flash is available through 5 providers: Concentrate, DeepInfra, Inference.net, Google Vertex AI, and OpenRouter.

Gemini 2.5 Flash accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "gemini-2.5-flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Gemini 2.5 Flash scores 18.6 out of 100 on the Respan Index v1.1, ranking #141 of 176 models. By category: Coding 2.1, Agents 17.9, Reasoning 20.7, Knowledge & language 13.1 (estimated), and Human preference 47.1. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Gemini 2.5 Flash has 13 published benchmark scores, including LiveCodeBench 59.3%, BALROG 33.5%, and GPQA Diamond 82.8%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.