---
title: "apiToken.sale — model catalog (Claude, GPT & Gemini)"
description: "Every Claude, 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 run on one `sk-pool-…` key and one prepaid balance through the unified router endpoint `https://router.apitoken.sale` — native Anthropic, OpenAI and Gemini lanes plus one OpenAI-compatible route for any model. Use the model ID unchanged in the `model` field; on shared lanes prefer the namespaced form (`anthropic/<id>`, `openai/<id>`, `google/<id>`).

# Claude models (Anthropic Messages API)

## Claude Fable 5.1

- **Model ID:** `claude-fable-5-1`
- **Tier:** Mythos
- **Context window:** 1M tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $10 input / $50 output
- **Your price (per 1M):** input $5, output $25 (flat 50% off)
- **Lane:** Anthropic Messages API (native) at `https://router.apitoken.sale` · also callable via `POST /v1/chat/completions` as `anthropic/claude-fable-5-1`
- **Best for:** The longest-horizon autonomous runs where failure costs more than tokens. The hardest software tasks — the current Mythos GA. Cache-heavy agent loops that re-read a large prefix every turn.
- **Detail page:** https://apitoken.sale/models/claude-fable-5-1

## Claude Opus 5

- **Model ID:** `claude-opus-5`
- **Tier:** Opus
- **Context window:** 1M tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $5 input / $25 output
- **Your price (per 1M):** input $2.5, output $12.5 (flat 50% off)
- **Lane:** Anthropic Messages API (native) at `https://router.apitoken.sale` · also callable via `POST /v1/chat/completions` as `anthropic/claude-opus-5`
- **Best for:** Agentic coding in Claude Code, Cursor and Cline — the new default. Long-horizon autonomous tasks and complex refactors. The hardest reasoning, planning and review work.
- **Detail page:** https://apitoken.sale/models/claude-opus-5

## Claude Fable 5

- **Model ID:** `claude-fable-5`
- **Tier:** Mythos
- **Context window:** 1M tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $10 input / $50 output
- **Your price (per 1M):** input $5, output $25 (flat 50% off)
- **Lane:** Anthropic Messages API (native) at `https://router.apitoken.sale` · also callable via `POST /v1/chat/completions` as `anthropic/claude-fable-5`
- **Best for:** The longest-horizon autonomous runs where failure costs more than tokens. The hardest software tasks — it leads SWE-bench Pro. An orchestrator or advisor role reviewing and steering cheaper models.
- **Detail page:** https://apitoken.sale/models/claude-fable-5

## Claude Opus 4.8

- **Model ID:** `claude-opus-4-8`
- **Tier:** Opus
- **Context window:** 1M tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $5 input / $25 output
- **Your price (per 1M):** input $2.5, output $12.5 (flat 50% off)
- **Lane:** Anthropic Messages API (native) at `https://router.apitoken.sale` · also callable via `POST /v1/chat/completions` as `anthropic/claude-opus-4-8`
- **Best for:** Agentic coding in Claude Code, Cursor and Cline. Long-horizon autonomous tasks and complex refactors. The hardest reasoning, planning and review work.
- **Detail page:** https://apitoken.sale/models/claude-opus-4-8

## Claude Opus 4.7

- **Model ID:** `claude-opus-4-7`
- **Tier:** Opus
- **Context window:** 1M tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $5 input / $25 output
- **Your price (per 1M):** input $2.5, output $12.5 (flat 50% off)
- **Lane:** Anthropic Messages API (native) at `https://router.apitoken.sale` · also callable via `POST /v1/chat/completions` as `anthropic/claude-opus-4-7`
- **Best for:** Workloads pinned to Opus 4.7 for reproducibility. Agentic coding and multi-step reasoning. Vision-heavy tasks with high-resolution image support.
- **Detail page:** https://apitoken.sale/models/claude-opus-4-7

## Claude Sonnet 5

- **Model ID:** `claude-sonnet-5`
- **Tier:** Sonnet
- **Context window:** 1M tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $2 input / $10 output
- **Your price (per 1M):** input $1, output $5 (flat 50% off)
- **Lane:** Anthropic Messages API (native) at `https://router.apitoken.sale` · also callable via `POST /v1/chat/completions` as `anthropic/claude-sonnet-5`
- **Best for:** Day-to-day coding — the default in most editors. Agentic workflows where Opus cost is not justified. High-volume production API traffic.
- **Detail page:** https://apitoken.sale/models/claude-sonnet-5

## Claude Sonnet 4.6

- **Model ID:** `claude-sonnet-4-6`
- **Tier:** Sonnet
- **Context window:** 200K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $3 input / $15 output
- **Your price (per 1M):** input $1.5, output $7.5 (flat 50% off)
- **Lane:** Anthropic Messages API (native) at `https://router.apitoken.sale` · also callable via `POST /v1/chat/completions` as `anthropic/claude-sonnet-4-6`
- **Best for:** Pipelines tuned and evaluated against Sonnet 4.6. Balanced coding and content workloads. Teams migrating gradually to Sonnet 5.
- **Detail page:** https://apitoken.sale/models/claude-sonnet-4-6

## Claude Haiku 4.5

- **Model ID:** `claude-haiku-4-5`
- **Tier:** Haiku
- **Context window:** 200K tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $1 input / $5 output
- **Your price (per 1M):** input $0.5, output $2.5 (flat 50% off)
- **Lane:** Anthropic Messages API (native) at `https://router.apitoken.sale` · also callable via `POST /v1/chat/completions` as `anthropic/claude-haiku-4-5`
- **Best for:** Classification, extraction and summarization at scale. Latency-sensitive chat and routing layers. Cheap pre-processing before an Opus or Sonnet call.
- **Detail page:** https://apitoken.sale/models/claude-haiku-4-5

# GPT models (OpenAI-compatible API)

## 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-5.6 Sol

- **Model ID:** `gpt-5.6-sol`
- **Tier:** Flagship
- **Context window:** 1.05M 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:** 1.05M 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:** 1.05M 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

## GPT-5.5

- **Model ID:** `gpt-5.5`
- **Tier:** Flagship
- **Context window:** 1.05M tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $5 input / $30 output
- **Cached input (per 1M):** $0.5 · **Cache write:** $5
- **Your price (per 1M):** input $2.5, output $15 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-5.5`
- **Best for:** Workloads pinned to GPT-5.5 for reproducibility. Agentic coding and multi-step reasoning. Pipelines migrating gradually to the GPT-5.6 line.
- **Detail page:** https://apitoken.sale/models/gpt-5-5

## GPT-5.4

- **Model ID:** `gpt-5.4`
- **Tier:** Balanced
- **Context window:** 1.05M tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $2.5 input / $15 output
- **Cached input (per 1M):** $0.25 · **Cache write:** $2.5
- **Your price (per 1M):** input $1.25, output $7.5 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-5.4`
- **Best for:** Pipelines tuned and evaluated against GPT-5.4. Balanced coding and content workloads. Teams migrating gradually to GPT-5.6 Terra.
- **Detail page:** https://apitoken.sale/models/gpt-5-4

## GPT Image 2

- **Model ID:** `gpt-image-2`
- **Tier:** Image
- **Context window:** per request
- **Max output:** 1 image
- **Official price (per 1M):** $5 input / $30 output
- **Cached input (per 1M):** $1.25 · **Cache write:** $0
- **Your price (per 1M):** input $2.5, output $15 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-image-2`
- **Best for:** Product image generation from a prompt on a bounded low-cost profile. Image editing against one to five PNG, JPEG or WebP references. Pipelines that already run GPT or Claude 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`
- **Tier:** Image
- **Context window:** per request
- **Max output:** 1 image
- **Official price (per 1M):** $5 input / $30 output
- **Cached input (per 1M):** $1.25 · **Cache write:** $0
- **Your price (per 1M):** input $2.5, output $15 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-image-2.5-flare`
- **Best for:** Everyday product image generation from a prompt on a bounded low-cost profile. Faster edits against one to five 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`
- **Tier:** Image
- **Context window:** per request
- **Max output:** 1 image
- **Official price (per 1M):** $5 input / $30 output
- **Cached input (per 1M):** $1.25 · **Cache write:** $0
- **Your price (per 1M):** input $2.5, output $15 (flat 50% off)
- **Lane:** OpenAI Responses / Chat Completions at `https://router.apitoken.sale/v1` (Authorization: Bearer) · namespaced ID `openai/gpt-image-2.5-sunburst`
- **Best for:** Higher-precision edits where Flare's faster everyday pass is not enough. Image editing against one to five 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

# Gemini models (Google Gemini API)

## 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

## Gemini 3.7 Flash

- **Model ID:** `gemini-3.7-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-3.7-flash`
- **Best for:** Text generation and long-context analysis on the newest 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-3-7-flash

## Gemini 3.6 Flash

- **Model ID:** `gemini-3.6-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-3.6-flash`
- **Best for:** Agentic coding and tool use at Flash speed. Multimodal workloads across text, image, audio, video and PDF input. Long-context analysis in the full 1M-token window.
- **Detail page:** https://apitoken.sale/models/gemini-3-6-flash

## Gemini 3.5 Flash

- **Model ID:** `gemini-3.5-flash`
- **Tier:** Flash
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $1.5 input / $9 output
- **Cached input (per 1M):** $0.15
- **Your price (per 1M):** input $0.75, output $4.5 (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-3.5-flash`
- **Best for:** Workloads pinned to Gemini 3.5 Flash for reproducibility. High-volume production API traffic. Multimodal pipelines migrating gradually to 3.6 Flash.
- **Detail page:** https://apitoken.sale/models/gemini-3-5-flash

## Gemini 3 Flash Preview

- **Model ID:** `gemini-3-flash-preview`
- **Tier:** Flash
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $0.5 input / $3 output
- **Cached input (per 1M):** $0.05
- **Your price (per 1M):** input $0.25, output $1.5 (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-3-flash-preview`
- **Best for:** Agentic coding and function calling at Flash latency. Multimodal text, image, audio, video and document input. Cost-efficient analysis across the full 1M-token window.
- **Detail page:** https://apitoken.sale/models/gemini-3-flash-preview

## Gemini 3.1 Pro Preview

- **Model ID:** `gemini-3.1-pro-preview`
- **Tier:** Pro
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $2 input / $12 output
- **Cached input (per 1M):** $0.2
- **Your price (per 1M):** input $1, output $6 (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-3.1-pro-preview`
- **Best for:** The hardest reasoning, planning and review work. Long-horizon agentic tasks with tool use. Deep document and codebase analysis in the 1M-token window.
- **Detail page:** https://apitoken.sale/models/gemini-3-1-pro-preview

## Gemini 3.1 Flash-Lite

- **Model ID:** `gemini-3.1-flash-lite`
- **Tier:** Flash-Lite
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $0.25 input / $1.5 output
- **Cached input (per 1M):** $0.025
- **Your price (per 1M):** input $0.125, output $0.75 (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-3.1-flash-lite`
- **Best for:** Classification, extraction and summarization at scale. Latency-sensitive chat and routing layers. Cheap pre-processing before a Flash or Pro call.
- **Detail page:** https://apitoken.sale/models/gemini-3-1-flash-lite

## Gemini 2.5 Flash

- **Model ID:** `gemini-2.5-flash`
- **Tier:** Flash
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $0.3 input / $2.5 output
- **Cached input (per 1M):** $0.03
- **Your price (per 1M):** input $0.15, output $1.25 (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-2.5-flash`
- **Best for:** Pipelines tuned and evaluated against Gemini 2.5 Flash. Balanced coding and content workloads. Teams migrating gradually to the Gemini 3 line.
- **Detail page:** https://apitoken.sale/models/gemini-2-5-flash

## Gemini 2.5 Flash-Lite

- **Model ID:** `gemini-2.5-flash-lite`
- **Tier:** Flash-Lite
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $0.1 input / $0.4 output
- **Cached input (per 1M):** $0.01
- **Your price (per 1M):** input $0.05, output $0.2 (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-2.5-flash-lite`
- **Best for:** Classification, extraction and summarization at massive scale. Latency-sensitive chat and routing layers. Cheap pre-processing before a Flash or Pro call.
- **Detail page:** https://apitoken.sale/models/gemini-2-5-flash-lite

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