Skip to main content

GPT-5 Mini

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.

Input / output price
$0.25 / $2.00 per 1M
Context
400K tokens
Released
Aug 7, 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 "openai/gpt-5-mini".

Read docs

Providers

6 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Azure Foundryazure_foundry/gpt-5-mini
$0.25/M$2.00/M
Azure OpenAIazure_openai/gpt-5-mini
$0.25/M$2.00/M
Inference.netinference_net/gpt-5-mini
$0.25/M$2.00/M
OpenAIRetiringopenai/gpt-5-mini
$0.25/M$2.00/M
Perplexityperplexity/gpt-5-mini
$0.25/M$2.00/M

Is a provider down? Azure OpenAI status, ChatGPT status, Perplexity status, OpenRouter status

Pricing

Averaged across 6 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.25 per 1M
Average output
$2.00 per 1M
Average cache read
$0.02 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.25/MAzure Foundry, Azure OpenAI, Inference.net, OpenAI, Perplexity, 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

91tokens/sacross providers

Faster than 76% of the other 596 models on the gateway

Time to first token

Lower is better

3.0sacross providers

Faster than 32% of the other 153 models on the gateway

Response latency

Lower is better

14sacross providers

Faster than 14% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 17 published scores from 7 sources, each linked to where it was published.

20.0/ 100

Respan Index#129 of 176

176 ranked models. The shaded band is this model's 95% interval, 16.5 to 25.0. Grok 4 Fast Reasoning and Qwen3.5 27B fall inside it, so the gap is within the margin of error.
GPT-5 Mini by category: Coding 9.1, Agents 4.3, Reasoning 31.5, Knowledge & language 21.6, Human preference 43.9
  1. 129GPT-5 mini20.0
  2. 127Grok 4 Fast Reasoning20.2
  3. 129Qwen3.5 27B20.0

Published scores

BenchmarkScore
SWE-bench VerifiedOpenAI71%
SWE-bench VerifiedEpoch AI64.7%
WeirdMLHåvard Tveit Ihle52.7%

Compare GPT-5 Mini: GPT-5 mini vs GPT-4.1 mini, GPT-5 mini vs GPT-5.4 mini, GPT-5 mini vs GPT-6.2 Astra, GPT-5 mini vs GPT-6 Astra, GPT-5 mini vs GPT-6.1 Sol, GPT-5 mini vs GPT-6.1 Terra

Apps

Use GPT-5 Mini 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.

GPT-5 Mini FAQ

Short answers, built from the data on this page.

GPT-5 Mini is a model from OpenAI, released on Aug 7, 2025. GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.

On the Respan gateway, GPT-5 Mini costs $0.25 per 1M input tokens and $2.00 per 1M output tokens on every provider, after gateway discounts.

GPT-5 Mini is available through 6 providers: Azure Foundry, Azure OpenAI, Inference.net, OpenAI, Perplexity, and OpenRouter.

GPT-5 Mini accepts up to 400K 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 "openai/gpt-5-mini". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

GPT-5 Mini scores 20.0 out of 100 on the Respan Index v1.1, ranking #129 of 176 models. By category: Coding 9.1, Agents 4.3, Reasoning 31.5, Knowledge & language 21.6, and Human preference 43.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

GPT-5 Mini has 17 published benchmark scores, including SWE-bench Verified 71%, Vending-Bench 2 -31.18, and GPQA Diamond 81.6%. 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.