Long context

gpt-5.6-sol API pricing

OpenAI's GPT series — broad general capability, wide ecosystem, and the native models behind Codex CLI.

Model IDopenai/gpt-5.6-sol

ChatStreamingTool callingVision

Get API Key Run your first request

Call summary

Input

$5.00$0.50/ 1M tokens

Cache write $0.50

Output

$40.00$4.00/ 1M tokens

Cache read $0.25

Context Window

1.05M

API Endpoints

Available Configurations

gpt-5.6-sol API endpoints

One API key — call this model through any of the 2 endpoints below.

POST/v1/chat/completionsOpenAI-compatible · Works for every model

Docs

POST/v1/responsesResponses API · Native for Codex CLI

Docs

gpt-5.6-sol pricing tiers

Pricing is tiered by total input length per request (cache included); once a threshold is crossed, the whole request is billed at that tier. All prices are per 1M tokens.

Tier

Standard≤ 272K

Input

$5.00$0.50Cache write: $0.50

Output

$40.00$4.00Cache read: $0.25

Tier

Long context> 272K

Input

$10.00$1.00Cache write: $6.25

Output

$45.00$4.50Cache read: $0.50

Tier	Input	Output
Standard≤ 272K	$5.00$0.50Cache write: $0.50	$40.00$4.00Cache read: $0.25
Long context> 272K	$10.00$1.00Cache write: $6.25	$45.00$4.50Cache read: $0.50

Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

Successful response share

94.82%

Success 2xx

94.82%

Rate limit 429

1.16%

Server 5xx

4.02%

TPS

49.12

tokens/s

Avg. time to first token

16.57 s

Avg. latency

29.82 s

Includes production requests ending in 2xx, 429, or 5xx. Average latency uses successful requests; time to first token and TPS require complete observations from successful streams. Public thresholds are 100 requests and 5 independent principals.

Updated Sep 9, 2026, 8:59 PM UTC

More GPT models on Router One

6 other GPT models on the same gateway and API key — each page lists endpoints, posted price, and context window.

codex-auto-review$0.50 in / $3.00 out per 1M1.05M context gpt-5.3-codex-spark$0.4314 in / $3.4521 out per 1M400K context gpt-5.5$0.50 in / $2.25 out per 1M1.05M context gpt-5.6-terra$0.25 in / $1.50 out per 1M1.05M context gpt-6-astra$2.00 in / $10.00 out per 1M1.05M context gpt-image-2$0.50 per image

gpt-5.6-sol compared with other models

Spec and price matchups against peer models.

Claude Opus 5vsGPT-5.6 Sol GPT-5.6 SolvsGPT-5.5 GPT-6 AstravsGPT-5.6 Sol Claude Fable 5vsGPT-5.6 Sol Grok 4.6vsGPT-5.6 Sol GPT-5.6 SolvsGPT-5.6 Terra

Call gpt-5.6-sol from your code

The same API key works across all 2 endpoints below.

Endpoint

/v1/chat/completions

Model ID

openai/gpt-5.6-sol

Routing mode

auto

Request example

bash

curl -X POST \
  https://api.router.one/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-5.6-sol",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Get API Key

gpt-5.6-sol at a glance

gpt-5.6-sol is a GPT-series text model on Router One. request input ≤ 272,000 tokens: Input $0.50 / 1M tokens, Output $4.00 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.25 / 1M tokens; request input > 272,000 tokens: Input $1.00 / 1M tokens, Output $4.50 / 1M tokens, Cache write $6.25 / 1M tokens, Cached input $0.50 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold. Context window: 1.05M tokens. Accepts text, image; returns text. Endpoints: POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path).

gpt-5.6-sol FAQ

How much does gpt-5.6-sol cost on Router One?

request input ≤ 272,000 tokens: Input $0.50 / 1M tokens, Output $4.00 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.25 / 1M tokens; request input > 272,000 tokens: Input $1.00 / 1M tokens, Output $4.50 / 1M tokens, Cache write $6.25 / 1M tokens, Cached input $0.50 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.

Which endpoints serve gpt-5.6-sol?

gpt-5.6-sol is served on 2 endpoints — POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path). The same Router One API key works on each.

What is gpt-5.6-sol's context window?

gpt-5.6-sol accepts up to 1.05M tokens of context per request on Router One.

Start using gpt-5.6-sol

Create an API key and call gpt-5.6-sol at request input ≤ 272,000 tokens: $0.50 in / $4.00 out per 1M tokens on Router One — pay as you go, with per-request cost and latency visibility.

Get API Key Plans & pay-as-you-go pricing Compare models side by side Quickstart guide