GPT-5.6 Sol API

Call GPT-5.6 Sol with one TokenMilo API key. The previous GPT generation, still widely used and very low cost. Billed per token at 90% below the official OpenAI price.

Get an API key

Model IDgpt-5.6-sol
ProviderOpenAI
FamilyGPT-5.6
Discount90% off official

GPT-5.6 Sol pricing

USD per 1M tokens. Prices updated 2026-11-13.

TokenMiloOfficial OpenAI
Input$0.342$4
Output$2.05$20
Cache read$0.034—
Cache write (5 min)$0.432—
Cache write (1 hour)$0.432—

1-hour cache writes are billed at the same price as 5-minute writes.

What it costs in practice

WorkloadTokenMiloOfficialYou save
1,000 requests × 2,000 in / 500 out tokens$1.71$18.00$16.29
1,000 requests × 50,000 in / 2,000 out tokens$21.20$240$219

What GPT-5.6 Sol is good for

  • Low-cost chat and summarisation
  • Batch jobs and data processing
  • Prototyping
  • Legacy integrations pinned to GPT-5.x

Supported endpoints

OpenAI Chat Completions · recommendedPOST https://api.tokenmilo.com/v1/chat/completions
OpenAI Responses · recommendedPOST https://api.tokenmilo.com/v1/responses
Anthropic MessagesPOST https://api.tokenmilo.com/v1/messages

Base URL and API key are the same for every format. API guide →

Code examples

curl

curl https://api.tokenmilo.com/v1/chat/completions \
  -H "Authorization: Bearer $TOKENMILO_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [{"role": "user", "content": "Hello, GPT-5.6 Sol!"}]
  }'

Python

# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.tokenmilo.com/v1",
    api_key=os.environ["TOKENMILO_API_KEY"],
)
res = client.responses.create(
    model="gpt-5.6-sol",
    input="Explain prompt caching in one paragraph.",
)
print(res.output_text)

Use GPT-5.6 Sol in your tools

Other GPT-5.6 models

More OpenAI models

FAQ

Is this the real GPT-5.6 Sol?

Yes. Requests with model ID gpt-5.6-sol are served by the genuine OpenAI model — no quantized, swapped or downgraded variant. Response quality is the same as calling OpenAI directly.

How much does GPT-5.6 Sol cost on TokenMilo?

$0.342 per 1M input tokens and $2.05 per 1M output tokens, compared with $4 / $20 officially — 90% less. There is no subscription or monthly minimum.

Which API format should I use for GPT-5.6 Sol?

Use the OpenAI Chat Completions or Responses API at https://api.tokenmilo.com/v1. Codex CLI and most OpenAI SDK-based tools work by changing only the base URL and key.

Does GPT-5.6 Sol support prompt caching?

Yes. Cache reads are billed at $0.034 per 1M tokens, which makes long system prompts and coding-agent sessions much cheaper.

Start using GPT-5.6 Sol

Sign up, top up, create a key — and point your SDK at TokenMilo.

Get an API key All models Full pricing