Skip to content
Inferray
DashboardGet API key

One API. Leading models. No gateway fees.

Access Claude, GPT, and Gemini through one unified inference API. Use your existing SDK, bring your team, and pay only for inference. Seats, projects, and API keys are free.

Get your API keyRead the quickstart
Works with
// same SDK — only the base URL changes
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferray.com/v1",
  apiKey: "inferray_...",
});

const resp = await client.chat.completions.create({
  model: "gpt-5.2",
  messages: [{ role: "user", content: "ship it" }],
});
GPT-5.2 · output / 1M$11.20
  • OpenAI & Anthropic compatible
  • Streaming built in
  • Zero prompt retention
  • Pay as you go, no minimum

One place for your models and your team.

Choose the right model for each task through a consistent API. Keep your existing SDKs and coding agents, with model access and billing in one place.

Organize work into projects, manage your team’s access, and create separate API keys for each integration. See usage and spend across your organization.

Add teammates and projects without adding platform costs.

Your workspace is included

Pay for the inference you use. There are no gateway fees and no extra charges for the people or projects behind your requests.

View model pricing
  • Free

    Seats

    Invite your team and manage access without per-seat charges.

  • Free

    Projects

    Keep applications and environments organized at no extra cost.

  • Free

    API keys

    Give each integration its own key without paying per key.

Leading models, one API

Compare leading models and their rates in one catalogue. Text models are priced per 1M tokens, input / output; image models show their billing unit. No gateway fees are added to these rates.

Browse the catalogue
Every model Inferray offers, with its list price and Inferray price per million tokens (input / output).
ModelList price / you pay
Claude Fable 5.1claude-fable-5-1List price $10 / $50Inferray price $7.50 / $37.50
Claude Fable 5claude-fable-5List price $10 / $50Inferray price $7.50 / $37.50
Claude Opus 5claude-opus-5List price $5 / $25Inferray price $3.75 / $18.75
Claude Opus 4.8claude-opus-4-8List price $5 / $25Inferray price $3.75 / $18.75
Claude Sonnet 5claude-sonnet-5List price $2 / $10Inferray price $1.50 / $7.50
Claude Haiku 4.5claude-haiku-4-5List price $1 / $5Inferray price $0.75 / $3.75
GPT-6 Astragpt-6-astraList price $10 / $50Inferray price $8.00 / $40.00
GPT-5.6 Solgpt-5.6-solList price $4 / $20Inferray price $3.20 / $16.00
GPT-5.6 Terragpt-5.6-terraList price $2 / $12Inferray price $1.60 / $9.60
GPT-5.6 Lunagpt-5.6-lunaList price $0.20 / $1.20Inferray price $0.16 / $0.96
GPT-5.5gpt-5.5List price $5 / $30Inferray price $4.00 / $24.00
GPT-5.4gpt-5.4List price $2.50 / $15Inferray price $2.00 / $12.00
GPT-5.2gpt-5.2List price $1.75 / $14Inferray price $1.40 / $11.20
Gemini 3 Pro Image (Preview)gemini-3-pro-image-previewList price $0.13–$0.24 / imageInferray price $0.11–$0.20 / image
Gemini 2.5 Flash Imagegemini-2.5-flash-imageList price $0.30 / $30Inferray price $0.26 / $25.50
GPT Image 2gpt-image-2List price $30 / 1M image tokensInferray price $24 / 1M image tokens
Gemini 3.8 Flashgemini-3.8-flashList price $0.75 / $3.75Inferray price $0.64 / $3.19
Gemini 2.5 Progemini-2.5-proList price $1.25 / $10Inferray price $1.06 / $8.50
DeepSeek V4.1 Flashdeepseek-v4.1-flashList price $0.15 / $0.60Inferray price $0.12 / $0.48
GLM-5.3glm-5.3List price $1.40 / $4.40Inferray price $1.12 / $3.52
Kimi K3kimi-k3List price $3 / $15Inferray price $2.40 / $12.00

Keep the tools you use

If your code already talks to OpenAI or Anthropic, this is the entire migration. Your prompts, parameters, tools, and retries are untouched — and your agents take the same two values.

Read the quickstartSet up a coding agent
client.ts2 changed
baseURL: "https://api.openai.com/v1",
baseURL: "https://api.inferray.com/v1",
apiKey: process.env.OPENAI_API_KEY,
apiKey: process.env.INFERRAY_API_KEY,

  • Streaming support

    Deliver responses as they are generated, with token usage tracked for every request.

  • Clear usage insights

    Spend, tokens, and latency broken out per project, per key, and per model.

  • Your prompts stay yours

    Inferray does not store your prompts or responses, or use them for training.

Frequently asked questions

What to know about pricing, integration, and your data.

Do you charge gateway fees?
No. You pay the model rates shown in our catalogue, with no additional gateway fee. Seats, projects, and API keys are free.
What do I have to change in my code?
Your base URL and your key. Your SDK, your prompts, your tools, and your agents all stay exactly as they are.
How does billing work?
With pay as you go, top up your balance and pay for the inference you use, with no monthly minimum. Track spend by project, API key, and model in the console.
What happens to my prompts?
Inferray does not store your prompts or responses, or use them for training. Your console shows usage and cost without retaining that content.

Start building with no gateway fees

Create your workspace, get an API key, and top up for your first request. Your team, projects, and keys are included.

Get your API keyRead the quickstart