ElevenRouter
Get started
OpenAI
~openai/gpt-latest

GPT-5.5

openai/gpt-5.5Operational

GPT-5.5 (April 2026): multimodal agentic model for complex professional work; 1.05M context, 128K output.

Open in request builderTry in playground
Input
$5.00
per 1M tokens
Output
$30.00
per 1M tokens
Cache read
$0.500
per 1M tokens
Context
1.1M
tokens
Max output
128K
tokens
Official pricing

USD per million tokens, exactly what OpenAI publishes. ElevenRouter adds nothing on tokens.

Input$5.00
Output$30.00
Cache read$0.500
Cache writefree
Example · 1,000 in + 500 out$0.02000
Capabilities
  • Tool calling
  • Structured outputs
  • JSON mode
  • Reasoning
  • Vision
  • Audio input
  • Prompt caching
  • Streaming
Modalities
text+image+file->text
Tokenizer
GPT
Released
2026-09-25
Family
gpt
Availability

Measured by the routing engine; up when at least one credential can serve the model.

Last 3 days
99.82%
Last 30 days
99.82%
30 days agotoday
Full status page
Observed performance

Real requests over the last 7 days.

TTFT p50
—
TTFT p95
—
Tokens / s p50
—
Tokens / s p95
—

Percentiles appear after five successful requests.

Usage on ElevenRouter

Tokens per day across all customers, anonymous and aggregate.

0 tokens · 30d
0 requests in the last 7 days
Use it

Any OpenAI or Anthropic SDK works by changing the base URL. Supported parameters: max_tokens, temperature, top_p, frequency_penalty, presence_penalty, seed, stop, tools, tool_choice, parallel_tool_calls, response_format, structured_outputs, logit_bias, logprobs, top_logprobs, reasoning, include_reasoning, verbosity.

curl https://elevenrouter.com/api/v1/chat/completions \
  -H "Authorization: Bearer $ELEVENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "openai/gpt-5.5", "messages": [{ "role": "user", "content": "Hello" }] }'
Request builderFallbacks & variantsSDKs
Related models

Questions

How much does GPT-5.5 cost on ElevenRouter?
GPT-5.5 is billed at OpenAI's official list price: $5.00 per million input tokens and $30.00 per million output tokens, with cached input at $0.500. A request with 1,000 input and 500 output tokens costs about $0.02000.
What is the context length of GPT-5.5?
GPT-5.5 accepts up to 1.1M tokens of context and can produce up to 128K output tokens.
Does GPT-5.5 support tool calling and structured outputs?
Yes, tool calling is supported and JSON-schema structured outputs are native. Supported parameters: max_tokens, temperature, top_p, frequency_penalty, presence_penalty, seed, stop, tools, tool_choice, parallel_tool_calls, response_format, structured_outputs, logit_bias, logprobs, top_logprobs, reasoning, include_reasoning, verbosity.
How do I call GPT-5.5?
Send an OpenAI-compatible chat completion to https://elevenrouter.com/api/v1/chat/completions with "model": "openai/gpt-5.5" and your ElevenRouter key, or use the Anthropic Messages endpoint. Any OpenAI or Anthropic SDK works by changing the base URL.
Is GPT-5.5 available right now?
Availability is measured continuously by the routing engine. Current status: operational, 99.82% uptime over the last 30 days. When one credential fails, requests fail over to another automatically.