New Sign up free, 10 calls on us. Up to $1, no card needed.

GPT-5.5

Released 2026-04-24

chatVisionCodeTool callingReasoningPrompt caching

GPT-5.5 is OpenAI's frontier flagship of its generation, introduced as "a new class of intelligence for coding and professional work" and sitting above GPT-5.4 in the lineup.

Input
text image $5/M
Output
text $30/M
Cache read
$0.5/M
Context
1.1M
Knowledge cutoff
2025-12

Benchmarks

Above averageNo peer higher88 / 13419 / 134
GPT-5.5 other models measured peer average no peer scored higher
SWE-Bench Pro
59.4%
GeneBench Pro
12%
OSWorld-Verified
78.7%
Cybergym
81.8%
HealthBench
56.5%
GDPval-AA v2 Elo · 642-1861
1493.7
Harvey Lab-AA
86.3%
GPQA Diamond
93.6%
Blueprint-Bench 2
36.2%
BrowseComp
84.4%
Video-MME (w. sub)
89.3%

Vendor-published: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai

Price in context

Where the price sits among 60 comparable models

Input$5/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$30/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.5/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Tokens

Context window (vendor spec) 1,050,000
Max output (vendor spec) 128,000
Knowledge cutoff 2025-12

Prompt caching

How it caches automatic
Min prefix 1,024
Lifetime 5-10m, up to 1h

Thinking

Vendor control reasoning.effort
Accepted values none · low · medium · high · xhigh
Default medium applied when the request sets nothing
Can be turned off Yes
Thinking behaviour Supports interleaved thinking: visible output before and between thinking, and thinking between tool calls.
Parameter reasoning_effort
Values minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies

Model

Modalities text + image → text
  • Described as a new class of intelligence for coding and professional work
  • 1.05M context / 128k max output
  • prompts over 272k input tokens billed at 2x input / 1.5x output

per OpenAI official docs ↗

One prompt, measured through the gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. CHECK exactly 3 sentences

GPT-5.5 passed · 3 sentences

Enabling reasoning makes the model do additional internal “thinking” before producing the final answer, which consumes more compute and billable tokens. Even if user volume and output length stayed the same, each request now costs more because the model is spending extra capacity to solve the problem. In short, we bought higher-quality answers, but the unit cost per answer increased enough to double the total LLM bill.

out 131 tok (+42 thinking) latency 2.9 s

Instruction following (exactly three sentences - countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. CHECK fix passes tests

GPT-5.5 passed · 8/8 cases

```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 best = max(best, cur) return best ``` The bug was that `cur` and `best` were counting the number of equal *adjacent comparisons*, not the number of items in the run. A run of one item has length `1`, but the original code initialized both values to `0`, so single-element inputs returned `0`. Similarly, a run like `[2, 2, 2]` has length `3`, but only two adjacent equal comparisons, so the result was off by one. Also, `best` should be updated after every element is processed, not only inside the equality branch, so runs that continue through the final index are properly considered.

out 401 tok (+182 thinking) latency 5.9 s

Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. CHECK valid JSON, schema exact

GPT-5.5 passed · 5/5 fields, guidance "withheld pending the Q4 close"

{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":11,"guidance":"withheld pending the Q4 close"}

out 557 tok (+512 thinking) latency 6.7 s

Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. CHECK 120 words, 0 banned words

GPT-5.5 passed · 120 words, 0 banned, 1 question

Today we’re introducing Prompt Cache Routing, a new API gateway feature that stores reusable prompt prefixes and applies them across leading model providers. Teams can reduce latency, lower token spend, and keep application logic portable without rewriting requests for each vendor. Have you ever paid twice to send the same system instructions? With shared cache keys, provider-aware metadata, and automatic fallback handling, the gateway detects eligible prompt segments, reuses cached context, and records savings in your existing observability dashboards. Policies let admins set retention windows, data boundaries, and provider allowlists by workspace or environment. Prompt Cache Routing is available now in beta for Pro and Enterprise customers, with SDK support, Terraform resources, and clear migration guides included at launch worldwide.

out 859 tok (+700 thinking) latency 8.7 s

Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.

Use GPT-5.5 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About GPT-5.5

  • It pairs a 1,050,000-token context window (vendor spec) and 128K max output with image input, reasoning-effort control from none through xhigh, streaming, structured outputs, and OpenAI's full hosted tool suite, with a December 2025 knowledge cutoff.
  • Three changes at this release are worth reading before migrating from GPT-5.4.
  • Reasoning effort now defaults to medium rather than none, which quietly raises token spend and latency for any client that never set it.
  • Image detail left unset or set to auto now uses the model's original behaviour.
  • And caching works only with extended prompt caching, with in-memory prompt caching unsupported on this model.
  • The tool list runs to function calling, web search, file search, tool search, image generation, code interpreter, hosted shell, apply patch, skills, computer use, and MCP, across Chat Completions, Responses, and Batch.
  • Prompts above 272K input tokens are billed at 2x input and 1.5x output for the full request, and OpenAI notes that requests in that long-context range also draw on reduced rate-limit allocations.
  • Synthorai serves GPT-5.5 natively on its OpenAI-compatible API.

FAQ

Is the GPT-5.5 API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $5/M input tokens, that credit alone covers roughly 24 requests of ~8K tokens against GPT-5.5.

What is GPT-5.5 best at?

New class of intelligence for professional work; 1,050,000-token context, 128K output; reasoning-effort control from none through xhigh. See the About section for the full picture from the vendor's own release notes.

How much does GPT-5.5 cost?

GPT-5.5 costs $5 per million input tokens and $30 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.5/M.

Does GPT-5.5 support prompt caching?

Yes, automatically: OpenAI-served prompts cache with no code changes. Cached input tokens bill at $0.5/M vs $5/M uncached; prompts need a 1,024-token stable prefix to cache (TTL 5-10m, up to 1h). Prompt caching guide →

How do I get access to GPT-5.5?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gpt-5.5", and you're done. One API key covers every model on the gateway.

What is GPT-5.5's knowledge cutoff?

GPT-5.5's knowledge cutoff is 2025-12, per the vendor's official documentation (as of 2026-07-09).

Related models

Compare

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your API key Compare your cost →