---
title: "apiToken.sale — model catalog (GPT & Gemini)"
description: "Every GPT and Gemini model available through apiToken.sale with exact API IDs, context windows, max output and discounted per-token pricing."
url: "https://apitoken.sale/models"
language: "en"
---
# Model catalog

All models use one `sk-pool-…` key and one prepaid balance through `https://router.apitoken.sale`. Text models use the OpenAI and Gemini lanes and the Anthropic Messages route (for Messages clients such as Claude Code); on shared text lanes prefer namespaced IDs (`openai/<id>`, `google/<id>`). GPT Image models use the dedicated Images endpoints and bare model IDs listed below.

# GPT models (OpenAI-compatible API)

## GPT-6.1 Terra

- **Model ID:** `gpt-6.1-terra`
- **Tier:** Balanced
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $1 input / $5 output
- **Cached input (per 1M):** $0.05 · **Cache write:** $1.25
- **Your price (per 1M):** input $0.5, output $2.5 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-6.1-terra`
- **Best for:** Image understanding and visual reasoning at a low price. Natural writing, everyday coding and agent steps with explicit effort control. Long sessions with repeated context: cached input is $0.05 per 1M.
- **Detail page:** https://apitoken.sale/models/gpt-6-1-terra

## GPT-6.1 Sol

- **Model ID:** `gpt-6.1-sol`
- **Tier:** Balanced
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $2 input / $10 output
- **Cached input (per 1M):** $0.1 · **Cache write:** $2.5
- **Your price (per 1M):** input $1, output $5 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-6.1-sol`
- **Best for:** Complex coding and agentic work close to Astra quality at a lower price. Long sessions with repeated context: cached input is $0.10 per 1M. Tool calls, image understanding and structured JSON output.
- **Detail page:** https://apitoken.sale/models/gpt-6-1-sol

## GPT-6 Astra

- **Model ID:** `gpt-6-astra`
- **Tier:** Flagship
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $10 input / $50 output
- **Cached input (per 1M):** $1 · **Cache write:** $12.5
- **Your price (per 1M):** input $5, output $25 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-6-astra`
- **Best for:** Coding and reasoning with explicit effort control. Image understanding with structured JSON output. Function calls and long conversations through Responses or Chat Completions.
- **Detail page:** https://apitoken.sale/models/gpt-6-astra

## GPT-6 Sol

- **Model ID:** `gpt-6-sol`
- **Tier:** Balanced
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $2 input / $10 output
- **Cached input (per 1M):** $0.2 · **Cache write:** $2.5
- **Your price (per 1M):** input $1, output $5 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-6-sol`
- **Best for:** Interactive and agentic coding with explicit effort control. Everyday reasoning, tool calls and structured JSON output. Image understanding at a lower price than Astra.
- **Detail page:** https://apitoken.sale/models/gpt-6-sol

## GPT-6 Luna

- **Model ID:** `gpt-6-luna`
- **Tier:** Fast
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $0.1 input / $0.5 output
- **Cached input (per 1M):** $0.01 · **Cache write:** $0.125
- **Your price (per 1M):** input $0.05, output $0.25 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-6-luna`
- **Best for:** Classification, extraction and summarization at scale. Latency-sensitive chat, routing and tool calls. Cheap pre-processing before an Astra call.
- **Detail page:** https://apitoken.sale/models/gpt-6-luna

## GPT-5.6 Sol

- **Model ID:** `gpt-5.6-sol`
- **Tier:** Flagship
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $4 input / $20 output
- **Cached input (per 1M):** $0.4 · **Cache write:** $5
- **Your price (per 1M):** input $2, output $10 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-5.6-sol`
- **Best for:** Agentic coding in Codex CLI, opencode and OpenAI-compatible tools. Hard reasoning with adjustable effort, up to the max level. Long multi-turn sessions with cached-input pricing.
- **Detail page:** https://apitoken.sale/models/gpt-5-6-sol

## GPT-5.6 Terra

- **Model ID:** `gpt-5.6-terra`
- **Tier:** Balanced
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $2 input / $12 output
- **Cached input (per 1M):** $0.2 · **Cache write:** $2.5
- **Your price (per 1M):** input $1, output $6 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-5.6-terra`
- **Best for:** Day-to-day coding and chat below the promotional flagship price. Agentic workflows where flagship cost is not justified. High-volume production traffic on the OpenAI-compatible API.
- **Detail page:** https://apitoken.sale/models/gpt-5-6-terra

## GPT-5.6 Luna

- **Model ID:** `gpt-5.6-luna`
- **Tier:** Fast
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $0.2 input / $1.2 output
- **Cached input (per 1M):** $0.02 · **Cache write:** $0.25
- **Your price (per 1M):** input $0.1, output $0.6 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-5.6-luna`
- **Best for:** Classification, extraction and summarization at scale. Latency-sensitive chat and routing layers. Cheap pre-processing before a Sol or Terra call.
- **Detail page:** https://apitoken.sale/models/gpt-5-6-luna

# Images (GPT Image)

## GPT Image 2

- **Model ID:** `gpt-image-2`
- **Official price (per 1M tokens):** $5 text input / $8 image input / $30 image output
- **Cached input:** 25% of the corresponding fresh-input rate
- **Regular B2C price (per 1M tokens):** $2.5 text input / $4 image input / $15 image output
- **Lane:** OpenAI Images at `https://router.apitoken.sale/v1` (Authorization: Bearer)
- **Endpoints:** `POST /v1/images/generations`, `POST /v1/images/edits`
- **Best for:** Product image generation from a prompt on a bounded low-cost profile. Image editing against one to sixteen PNG, JPEG or WebP references. Pipelines that already run GPT or Gemini here — images debit the same balance.
- **Detail page:** https://apitoken.sale/models/gpt-image-2

## GPT Image 2.5 Flare

- **Model ID:** `gpt-image-2.5-flare`
- **Official price (per 1M tokens):** $5 text input / $8 image input / $30 image output
- **Cached input:** 25% of the corresponding fresh-input rate
- **Regular B2C price (per 1M tokens):** $2.5 text input / $4 image input / $15 image output
- **Lane:** OpenAI Images at `https://router.apitoken.sale/v1` (Authorization: Bearer)
- **Endpoints:** `POST /v1/images/generations`, `POST /v1/images/edits`
- **Best for:** Everyday product image generation from a prompt on a bounded low-cost profile. Faster edits against one to sixteen PNG, JPEG or WebP references. Pipelines that already run GPT Image 2 here — Flare is a drop-in Images HTTP id.
- **Detail page:** https://apitoken.sale/models/gpt-image-2.5-flare

## GPT Image 2.5 Sunburst

- **Model ID:** `gpt-image-2.5-sunburst`
- **Official price (per 1M tokens):** $5 text input / $8 image input / $30 image output
- **Cached input:** 25% of the corresponding fresh-input rate
- **Regular B2C price (per 1M tokens):** $2.5 text input / $4 image input / $15 image output
- **Lane:** OpenAI Images at `https://router.apitoken.sale/v1` (Authorization: Bearer)
- **Endpoints:** `POST /v1/images/generations`, `POST /v1/images/edits`
- **Best for:** Higher-precision edits where Flare's faster everyday pass is not enough. Image editing against one to sixteen PNG, JPEG or WebP references. Pipelines that already run GPT Image 2 here — Sunburst is a drop-in Images HTTP id.
- **Detail page:** https://apitoken.sale/models/gpt-image-2.5-sunburst

## GPT Image 2.6 Flare

- **Model ID:** `gpt-image-2.6-flare`
- **Official price (per 1M tokens):** $5 text input / $8 image input / $30 image output
- **Cached input:** 25% of the corresponding fresh-input rate
- **Regular B2C price (per 1M tokens):** $2.5 text input / $4 image input / $15 image output
- **Lane:** OpenAI Images at `https://router.apitoken.sale/v1` (Authorization: Bearer)
- **Endpoints:** `POST /v1/images/generations`, `POST /v1/images/edits`
- **Best for:** Creating static images from a text prompt. Editing up to sixteen reference images in one request. Returning PNG, JPEG or WebP from one Images API integration.
- **Detail page:** https://apitoken.sale/models/gpt-image-2.6-flare

## GPT Image 2.6 Sunburst

- **Model ID:** `gpt-image-2.6-sunburst`
- **Official price (per 1M tokens):** $5 text input / $8 image input / $30 image output
- **Cached input:** 25% of the corresponding fresh-input rate
- **Regular B2C price (per 1M tokens):** $2.5 text input / $4 image input / $15 image output
- **Lane:** OpenAI Images at `https://router.apitoken.sale/v1` (Authorization: Bearer)
- **Endpoints:** `POST /v1/images/generations`, `POST /v1/images/edits`
- **Best for:** Creating static images from a text prompt. Editing up to sixteen reference images in one request. Returning PNG, JPEG or WebP from one Images API integration.
- **Detail page:** https://apitoken.sale/models/gpt-image-2.6-sunburst

# Gemini models (Google Gemini API)

## Gemini 4 Hydrogen

- **Model ID:** `gemini-4-hydrogen`
- **Tier:** Hydrogen
- **Context window:** 1M tokens shared by input, thinking and output
- **Max output:** 64K streaming · 32K non-streaming
- **Official price (per 1M):** $1.5 input / $7.5 output
- **Cached input (per 1M):** $0.075
- **Your price (per 1M):** input $0.75, output $3.75 (flat 50% off)
- **Lane:** Gemini API (native) at `https://router.apitoken.sale` (x-goog-api-key) · also callable via `POST /v1/chat/completions` as `google/gemini-4-hydrogen`
- **Best for:** High-volume coding, agents and chat where speed and price matter most. Function-calling agents and JSON schema output. Documents, images, audio and video in one shared context.
- **Detail page:** https://apitoken.sale/models/gemini-4-hydrogen

## Gemini 4 Carbon

- **Model ID:** `gemini-4-carbon`
- **Tier:** Carbon
- **Context window:** 1M tokens shared by input, thinking and output
- **Max output:** 64K streaming · 32K non-streaming
- **Official price (per 1M):** $2 input / $10 output
- **Cached input (per 1M):** $0.1
- **Your price (per 1M):** input $1, output $5 (flat 50% off)
- **Lane:** Gemini API (native) at `https://router.apitoken.sale` (x-goog-api-key) · also callable via `POST /v1/chat/completions` as `google/gemini-4-carbon`
- **Best for:** The hardest coding, analysis and long-horizon tasks with low, medium or high reasoning. Function-calling agents and JSON schema output. Documents, images, audio and video in one shared context.
- **Detail page:** https://apitoken.sale/models/gemini-4-carbon

## Gemini 4 Argon

- **Model ID:** `gemini-4-argon`
- **Tier:** Argon
- **Context window:** 1M tokens shared by input, thinking and output
- **Max output:** 64K streaming · 32K non-streaming
- **Official price (per 1M):** $2 input / $10 output
- **Cached input (per 1M):** $0.1
- **Your price (per 1M):** input $1, output $5 (flat 50% off)
- **Lane:** Gemini API (native) at `https://router.apitoken.sale` (x-goog-api-key) · also callable via `POST /v1/chat/completions` as `google/gemini-4-argon`
- **Best for:** Coding and complex analysis with low, medium or high reasoning. Function-calling agents and JSON schema output. Documents, images, audio and video in one shared context.
- **Detail page:** https://apitoken.sale/models/gemini-4-argon

## Gemini 3.8 Flash

- **Model ID:** `gemini-3.8-flash`
- **Tier:** Flash
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $0.75 input / $3.75 output
- **Cached input (per 1M):** $0.075
- **Your price (per 1M):** input $0.375, output $1.875 (flat 50% off)
- **Lane:** Gemini API (native) at `https://router.apitoken.sale` (x-goog-api-key) · also callable via `POST /v1/chat/completions` as `google/gemini-3.8-flash`
- **Best for:** Text generation and long-context analysis on the current GA Flash generation. Incremental SSE responses with terminal authoritative usage. Cost-sensitive production traffic during the promotional rate period.
- **Detail page:** https://apitoken.sale/models/gemini-3-8-flash

---
API reference: https://apitoken.sale/md/docs · Pricing: https://apitoken.sale/md/plans
