Polarison

Claude Haiku 4.5 vs GPT-6 Astra: pricing and benchmarks

Claude Haiku 4.5 is 90% cheaper on input tokens ($1.00 vs $10.00 per 1M). Claude Haiku 4.5 is 90% cheaper on output tokens ($5.00 vs $50.00 per 1M). On our document Q&A workload (50,000 questions a month), Claude Haiku 4.5 costs $550.00 a month versus $5,500 for GPT-6 Astra, 90% less. GPT-6 Astra scores 166.3 on the Epoch Capabilities Index vs 142.4 for Claude Haiku 4.5.

Prices verified September 14, 2026.

Which should you choose?

Overall capability
GPT-6 Astra

GPT-6 Astra scores 166.3 on the Epoch Capabilities Index vs 142.4 for Claude Haiku 4.5.

Price
Claude Haiku 4.5

Claude Haiku 4.5 costs $2.00 per 1M tokens (3:1 input-to-output mix) vs $20.00 for GPT-6 Astra, 90% less.

Best value
Too close to call

A trade-off: GPT-6 Astra is 23.9 ECI points more capable but costs 10.0x as much as Claude Haiku 4.5.

Pricing and specs

Claude Haiku 4.5GPT-6 Astra
ProviderAnthropicOpenAI
API model IDclaude-haiku-4-5-20251001gpt-6-astra
Input / 1M tokens$1.00$10.00
Cached input / 1M tokens$0.10$1.00
Output / 1M tokens$5.00$50.00
Long-context rates$20.00 in / $75.00 out on long-context requests
Context window200K tokens1.05M tokens
Max output64K tokens128K tokens
Batch discount50% off50% off

Benchmarks

Claude Haiku 4.5GPT-6 Astra
Epoch Capabilities Index142.4166.3
GPQA Diamond· Science reasoning61.6%94.4%
FrontierMath (Tiers 1–3)· Advanced math93.7%
SimpleQA Verified· Factual accuracy13.2%75.6%
ARC-AGI-2· Abstract reasoning4.0%95.0%
DeepSWE· Coding74.1%
APEX-Agents· Agentic work8.9%46.7%

Source: Epoch AI, best recorded result per model (CC BY 4.0). A dash means no published score. See all benchmarks

Monthly cost for real workloads

WorkloadClaude Haiku 4.5GPT-6 AstraDifference
Support chatbot
100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each.
$350.00$3,500Claude Haiku 4.5 90% cheaper
Document Q&A (RAG)
50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each.
$550.00$5,500Claude Haiku 4.5 90% cheaper
Coding agent
10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens.
$248.00$2,480Claude Haiku 4.5 90% cheaper

Estimates use standard list prices and ignore cache-write surcharges. Different tokenizers can count the same text differently, so test with your own prompts.

Claude Haiku 4.5 vs GPT-6 Astra cost calculator

Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.

Claude Haiku 4.5 pricing notes

Anthropic’s fastest model, with near-frontier intelligence.

  • Cache writes cost $1.25 (5-minute cache) or $2 (1-hour cache) per 1M tokens.
  • Uses Anthropic’s previous tokenizer.
Anthropic official pricing ↗

GPT-6 Astra pricing notes

OpenAI’s most capable model, built for the hardest end-to-end reasoning and coding work.

  • Cache writes are billed at $12.50 per 1M tokens.
  • Fast mode costs 2x the standard rate; Flex costs half.
  • Regional (data residency) endpoints add a 10% uplift.
OpenAI official pricing ↗

Frequently asked questions

Is Claude Haiku 4.5 cheaper than GPT-6 Astra?
Claude Haiku 4.5 is 90% cheaper on input tokens ($1.00 vs $10.00 per 1M). Claude Haiku 4.5 is 90% cheaper on output tokens ($5.00 vs $50.00 per 1M). On our document Q&A workload (50,000 questions a month), Claude Haiku 4.5 costs $550.00 a month versus $5,500 for GPT-6 Astra, 90% less.
Which is more capable, Claude Haiku 4.5 or GPT-6 Astra?
GPT-6 Astra scores 166.3 on the Epoch Capabilities Index vs 142.4 for Claude Haiku 4.5.
How much does Claude Haiku 4.5 cost per 1M tokens?
Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens, and $0.10 per 1M cached input tokens on Anthropic’s standard tier.
How much does GPT-6 Astra cost per 1M tokens?
GPT-6 Astra costs $10.00 per 1M input tokens and $50.00 per 1M output tokens, and $1.00 per 1M cached input tokens on OpenAI’s standard tier.
Which has the larger context window, Claude Haiku 4.5 or GPT-6 Astra?
GPT-6 Astra has the larger context window: 1.05M tokens versus 200K for Claude Haiku 4.5.

Related comparisons