Skip to content
Inferray
DashboardGet API key

Every model Inferray offers. No gateway fees.

One API key and one consistent interface for flagship models from Anthropic, OpenAI, Google, DeepSeek, Z.ai, Moonshot AI, Alibaba, and MiniMax. Prices are per 1M tokens, input / output — image models show the unit their provider bills in. Nothing is added on top of the rate you see.

Get your API keySee full pricing

Anthropic

12 models

Claude Fable 5.1

claude-fable-5-1

Anthropic

Anthropic's most intelligent model, for the hardest problems.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$10
Cached input
$0.25
Output
$50

Claude Opus 5.5

claude-opus-5-5

Anthropic

Long-running agentic coding at a lower price than Opus 5.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$4
Cached input
$0.20
Output
$20

Claude Fable 5

claude-fable-5

Anthropic

Next-generation intelligence for knowledge work and coding.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$10
Cached input
$1
Output
$50

Claude Opus 5

claude-opus-5

Anthropic

State-of-the-art agentic coding for enterprise work.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$5
Cached input
$0.50
Output
$25

Claude Opus 4.8

claude-opus-4-8

Anthropic

A proven pick for hard, long-running work.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$5
Cached input
$0.50
Output
$25

Claude Opus 4.7

claude-opus-4-7

Anthropic

Anthropic's flagship for coding and agentic workflows.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$5
Cached input
$0.50
Output
$25

Claude Opus 4.6

claude-opus-4-6

Anthropic

Advanced reasoning for long-running agentic work.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$5
Cached input
$0.50
Output
$25

Claude Sonnet 5.5

claude-sonnet-5-5

Anthropic

Anthropic's best balance of speed and intelligence.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$2
Cached input
$0.10
Output
$10

Claude Sonnet 5

claude-sonnet-5

Anthropic

Frontier reasoning at a price that scales to production.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$2
Cached input
$0.20
Output
$10

Claude Sonnet 4.6

claude-sonnet-4-6

Anthropic

Reasoning and vision at a mid-tier price.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$3
Cached input
$0.30
Output
$15

Claude Haiku 5.5

claude-haiku-5-5

Anthropic

Anthropic's fastest model, priced for volume.

  • 1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$0.10
Cached input
$0.01
Output
$0.50

Claude Haiku 4.5

claude-haiku-4-5

Anthropic

Fast and efficient for high-volume, low-latency work.

  • 200K context
  • Reasoning
  • Vision
Per 1M tokens
Input
$1
Cached input
$0.10
Output
$5

OpenAI

14 models

GPT-6 Astra

gpt-6-astra

OpenAI

OpenAI's most capable model for the hardest end-to-end work.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$10
Cached input
$1
Output
$50

GPT-6.1 Sol

gpt-6.1-sol

OpenAI

Near-Astra performance at a fraction of the price.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$2
Cached input
$0.10
Output
$10

GPT-6.1 Terra

gpt-6.1-terra

OpenAI

Fast GPT-6.1 for visual reasoning, computer use, and writing.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$1
Cached input
$0.05
Output
$5

GPT-6 Sol

gpt-6-sol

OpenAI

GPT-6 reasoning at a price for everyday production work.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$2
Cached input
$0.20
Output
$10

GPT-6 Luna

gpt-6-luna

OpenAI

The lowest-priced GPT-6 for high-volume tasks.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$0.10
Cached input
$0.01
Output
$0.50

GPT-5.6 Sol

gpt-5.6-sol

OpenAI

Frontier GPT-5.6 reasoning for complex professional work.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$4
Cached input
$0.40
Output
$20

GPT-5.6 Terra

gpt-5.6-terra

OpenAI

Balanced GPT-5.6 intelligence for everyday workloads.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$2
Cached input
$0.20
Output
$12

GPT-5.6 Luna

gpt-5.6-luna

OpenAI

Cost-optimized GPT-5.6 for high-volume tasks.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$0.20
Cached input
$0.02
Output
$1.20

GPT-5.5

gpt-5.5

OpenAI

A new class of intelligence for coding and professional work.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$5
Cached input
$0.50
Output
$30

GPT-5.4

gpt-5.4

OpenAI

Capable reasoning for complex professional work.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$2.50
Cached input
$0.25
Output
$15

GPT-5.2

gpt-5.2

OpenAI

Enhanced reasoning and tool use for everyday builds.

  • 400K context
  • Reasoning
  • Vision
Per 1M tokens
Input
$1.75
Cached input
$0.17
Output
$14

GPT Image 2.5 Sunburst

gpt-image-2.5-sunburst

OpenAI

OpenAI's most capable image model, built for precise edits.

  • Image output
  • Vision
Price
$30 / 1M image tokens

GPT Image 2.5 Flare

gpt-image-2.5-flare

OpenAI

OpenAI's fast image model for everyday work.

  • Image output
  • Vision
Price
$30 / 1M image tokens

GPT Image 2

gpt-image-2

OpenAI

OpenAI's image model for generation and editing.

  • Image output
  • Vision
Price
$30 / 1M image tokens

Google

13 models

Gemini 3 Pro Image (Preview)

gemini-3-pro-image-preview

Google

Google's most capable image model, up to 4K.

  • Image output
  • Vision
Price
$0.13–$0.24 / image

Gemini 3 Pro Image

gemini-3-pro-image

Google

Google's professional-grade image model, up to 4K.

  • Image output
  • Vision
Price
$0.13–$0.24 / image

Gemini 3.1 Flash Image

gemini-3.1-flash-image

Google

Fast, high-volume image generation and editing.

  • Image output
  • Vision
Price
$0.045–$0.15 / image

Gemini 3.1 Flash Lite Image

gemini-3.1-flash-lite-image

Google

Google's lowest-cost image model, built for scale.

  • Image output
  • Reasoning
  • Vision
Price
$0.034 / image

Gemini Nano Banana 2.1

gemini-nano-banana-2.1

Google

Fast image generation and editing with sharper 4K output.

  • Image output
  • Vision
Price
$0.034–$0.076 / image

Gemini 2.5 Flash Image

gemini-2.5-flash-image

Google

Fast image generation for high-volume work.

  • Image output
  • Vision
Price
$0.039 / image

Gemini 4 Argon

gemini-4-argon

Google

Google's frontier model for long-horizon coding and knowledge work.

  • 1.0M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$4
Cached input
$0.20
Output
$20

Gemini 3.8 Flash

gemini-3.8-flash

Google

Fast multimodal reasoning for coding and agents.

  • 1.0M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$0.75
Cached input
$0.07
Output
$3.75

Gemini 3.5 Flash

gemini-3.5-flash

Google

Frontier intelligence at Flash speed, with search and grounding.

  • 1.0M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$1.50
Cached input
$0.15
Output
$9

Gemini 3.5 Flash Lite

gemini-3.5-flash-lite

Google

The fastest, cheapest 3.5 model for high-throughput work.

  • 1.0M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$0.30
Cached input
$0.03
Output
$2.50

Gemini 3.1 Flash Lite

gemini-3.1-flash-lite

Google

Ultra-lightweight Gemini for cost-sensitive volume.

  • 1.0M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$0.25
Cached input
$0.03
Output
$1.50

Gemini 3.1 Pro (Preview)

gemini-3.1-pro-preview

Google

Google's Pro-tier reasoning, in preview.

  • 1.0M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$2
Cached input
$0.20
Output
$12

Gemini 2.5 Pro

gemini-2.5-pro

Google

Google's most capable model, multimodal and reasoning-ready.

  • 1.0M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$1.25
Cached input
$0.13
Output
$10

DeepSeek

1 model

DeepSeek V4.1 Flash

deepseek-v4.1-flash

DeepSeek

Reasoning and vision at a fraction of flagship prices.

  • 1.1M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$0.15
Cached input
$0.00
Output
$0.60

Z.ai

2 models

GLM-5.3

glm-5.3

Z.ai

A coding-first flagship with a million-token context.

  • 1M context
  • Reasoning
Per 1M tokens
Input
$1.40
Cached input
$0.26
Output
$4.40

GLM-5.2

glm-5.2

Z.ai

Long-horizon coding and agentic engineering, at a lower price.

  • 1M context
  • Reasoning
Per 1M tokens
Input
$1.40
Cached input
$0.26
Output
$4.40

Moonshot AI

2 models

Kimi K3

kimi-k3

Moonshot AI

Long-horizon coding and end-to-end knowledge work.

  • 1.0M context
  • Reasoning
  • Vision
Per 1M tokens
Input
$3
Cached input
$0.30
Output
$15

Kimi K2.6

kimi-k2.6

Moonshot AI

Moonshot's multimodal model for long-form code and agents.

  • 262K context
  • Reasoning
  • Vision
Per 1M tokens
Input
$0.95
Cached input
$0.16
Output
$4

Alibaba

1 model

Qwen3.8 Max

qwen3.8-max

Alibaba

Alibaba's flagship MoE, built for coding and long-horizon agents.

  • 984K context
  • Reasoning
  • Vision
Per 1M tokens
Input
$2
Cached input
$0.25
Output
$6

MiniMax

1 model

MiniMax M3

minimax-m3

MiniMax

Multimodal long-context inference with sparse attention.

  • 512K context
  • Reasoning
  • Vision
Per 1M tokens
Input
$0.60
Cached input
$0.12
Output
$2.40

ByteDance

1 model

Seedance 2.0 Mini

seedance-2-0-mini

ByteDance

Fast, low-cost video generation from text and images.

  • Image output
Price
$0.0378–$0.0756 / second

Same models. No gateway fees.

Point your existing client at Inferray and pay the rate shown for every model above — no gateway fee, no rewrites, no lock-in.

Get your API keyRead the quickstart