anoman

OpenAI

GPT-4o

modelgpt-4o
MidStableVisionStreamingVisionToolsBatchLong contextUnited States

Context

128K

Input / 1M tokens

$2.50

Output / 1M tokens

$10.00

Weighted tokens formula

1× provider × 4× tier

About this model

GPT-4o

OpenAI's GPT-4o — multimodal flagship combining strong general intelligence with vision, audio (via separate endpoint), and reliable tool calling. The default safe choice for new builds.

Released

2024-05

Training cutoff

2023-10

Parameters

Not disclosed

Best for

Use cases

  • General-purpose chat
  • Vision + document understanding
  • Agentic workflows with function calling
  • Multilingual customer support

Strengths

What it does well

  • Reliable tool calling + structured output
  • Strong multilingual quality
  • Vision built in
  • 128K context window
  • Battle-tested at production scale

Limitations

Know the trade-offs

  • !Trails newer models on coding (Claude Sonnet 4.6, Qwen 2.5 Coder)
  • !Knowledge cutoff trails competitors
  • !Premium pricing relative to open-weights at similar quality

Benchmarks

Published scores

Scores from official model cards and public leaderboards. Higher is better unless noted.

BenchmarkScoreMeasures
MMLU88.7General knowledge across 57 subjects
HumanEval90.2Python code generation, pass@1
MATH76.6Mathematics, mixed difficulty
GPQA53.6Graduate-level science questions

Code example

Chat completion with GPT-4o

from openai import OpenAI

client = OpenAI(
    base_url="https://api.anoman.io/v1",
    api_key="anm-sk-..."
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Weighted tokens

weighted_tokens = raw_tokens × 1 (provider) × 4 (tier)

Pro plan: 20M weighted tokens/month. Combined multiplier 4×: 5,000,000 raw tokens available.

Alternatives

Similar models in our catalog

Workloads that fit GPT-4o often fit these too. Compare benchmarks and pricing before locking in a default.

Use GPT-4o through Anoman.