OpenAI: GPT-5.2-Codex vs Anthropic: Claude Haiku 4.5
Head-to-head API pricing and cost comparison between OpenAI’s OpenAI: GPT-5.2-Codex and Anthropic’s Anthropic: Claude Haiku 4.5. Prices auto-refresh daily from OpenRouter.
Anthropic: Claude Haiku 4.5 is 43% cheaper for input tokens; Anthropic: Claude Haiku 4.5 also wins on output tokens.
Side-by-side comparison
| Spec | OpenAI: GPT-5.2-Codex | Anthropic: Claude Haiku 4.5 |
|---|---|---|
| Input price (per 1M) | $1.75 | $1.00 |
| Cached input (per 1M) | $0.17 | $0.10 |
| Output price (per 1M) | $14.00 | $5.00 |
| Batch input (per 1M) | $0.88 | $0.50 |
| Batch output (per 1M) | $7.00 | $2.50 |
| Reasoning price (per 1M) | — | — |
| Context window | 400K | 200K |
| Vision support | Yes | Yes |
| Caching support | Yes | Yes |
| Batch API | Yes | Yes |
| Reasoning capability | No | No |
Monthly cost at volume
Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).
| Volume | OpenAI: GPT-5.2-Codex | Anthropic: Claude Haiku 4.5 | Savings |
|---|---|---|---|
1K req/day 500in / 200out tokens | $110.25 | $45.00 | $65.25 Anthropic: Claude Haiku 4.5 wins |
10K req/day 1500in / 500out tokens | $2,888 | $1,200 | $1,688 Anthropic: Claude Haiku 4.5 wins |
100K req/day 3000in / 800out tokens | $49,350 | $21,000 | $28,350 Anthropic: Claude Haiku 4.5 wins |
1M req/day 8000in / 2000out tokens | $1,260,000 | $540,000 | $720,000 Anthropic: Claude Haiku 4.5 wins |
Adjust input/output token counts, request volume, batch & cached pricing.
Related comparisons
Frequently asked questions
Which is cheaper, OpenAI: GPT-5.2-Codex or Anthropic: Claude Haiku 4.5?
For input tokens, Anthropic: Claude Haiku 4.5 is roughly 43% cheaper at $1.00/1M vs $1.75/1M. For output tokens, Anthropic: Claude Haiku 4.5 wins at $5.00/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.
What’s the context window difference?
OpenAI: GPT-5.2-Codex has a context window of 400K tokens. Anthropic: Claude Haiku 4.5 offers 200K tokens. Larger context windows are valuable for long documents, RAG pipelines, and multi-turn conversations — but they come with higher input-token bills if you fill them every request.
Should I use OpenAI: GPT-5.2-Codex or Anthropic: Claude Haiku 4.5?
Choose OpenAI: GPT-5.2-Codex if you’re already on the OpenAI stack, want broad ecosystem support, or prefer its feature set. Choose Anthropic: Claude Haiku 4.5 for Anthropic’s ecosystem, native vision input, or its cheaper input tokens. Run a small benchmark on your own prompts before committing — price is only one axis.
How are these prices kept current?
Prices are pulled directly from OpenRouter’s public models API once every 24 hours via a Convex cron job, then normalized to per-1M-token figures. Last refresh: Apr 21, 2026.