Compare

Claude Haiku 4.5 vs FLUX.2 [Max]

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Claude Haiku 4.5
anthropic/claude-haiku-4.5
FLUX.2 [Max]
black-forest-labs/flux-2-max
Provider
Anthropic
Black Forest Labs
Family
Claude 4
FLUX
Modality
text
image
Context window
200,000 tok
Max output
8,192 tok
Released
2026-05-22
2026-05-27
License
Proprietary
Open-weight
Input price
$1.00 /1M
Output price
$5.00 /1M
Cache read
$0.100 /1M
Cache write
$1.25 /1M
Per image
$0.0000 /img
Tools
yes
Streaming
yes
Vision
yes
JSON mode
yes
Reasoning
Prompt caching
yes
Batch API
Try it
Open in playground →
Open in playground →
Claude Haiku 4.5
anthropic/claude-haiku-4.5
Full spec →

Claude Haiku 4.5 delivers similar levels of coding performance at one-third the cost and more than twice the speed of larger models.

Strengths
  • Fastest Claude
  • Cheap enough for per-token workloads
  • Still supports tools + vision
Use cases
ClassifiersRoutingHigh-throughput chatReal-time agents
FLUX.2 [Max]
black-forest-labs/flux-2-max
Full spec →

FLUX.2 [max] is Black Forest Labs' highest-quality image model — top editing consistency, strongest prompt following, and grounding search for visualizations of real-time information.

Strengths
  • Text-to-image generation
  • Creative control
Use cases
Marketing assetsProduct mockupsConcept art

Benchmarks

Claude Haiku 4.5
FLUX.2 [Max]
HumanEval
85.2
MMLU
80.1

Source: each provider's published benchmarks. Higher is better. Run an eval to compare on your own data.

Compare with another

Claude Haiku 4.5 vs GPT-5.4 Mini
anthropic/claude-haiku-4.5 · openai/gpt-5.4-mini
Claude Haiku 4.5 vs Gemini 3 Flash
anthropic/claude-haiku-4.5 · google/gemini-3-flash
Claude Opus 4.8 vs FLUX.2 [Max]
anthropic/claude-opus-4.8 · black-forest-labs/flux-2-max
Claude Opus 4.8 vs Claude Haiku 4.5
anthropic/claude-opus-4.8 · anthropic/claude-haiku-4.5
Claude Sonnet 4.6 vs FLUX.2 [Max]
anthropic/claude-sonnet-4.6 · black-forest-labs/flux-2-max
Claude Sonnet 4.6 vs Claude Haiku 4.5
anthropic/claude-sonnet-4.6 · anthropic/claude-haiku-4.5
Grok 4.20 Multi-Agent vs FLUX.2 [Max]
xai/grok-4.20-multi-agent-0309 · black-forest-labs/flux-2-max
Grok 4.20 Multi-Agent vs Claude Haiku 4.5
xai/grok-4.20-multi-agent-0309 · anthropic/claude-haiku-4.5
GPT-5.4 vs FLUX.2 [Max]
openai/gpt-5.4 · black-forest-labs/flux-2-max
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Claude Haiku 4.5
client.chat.completions.create(
    model="anthropic/claude-haiku-4.5",
    messages=[{"role":"user","content":"hello"}],
)

# FLUX.2 [Max]
client.chat.completions.create(
    model="black-forest-labs/flux-2-max",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →