Compare Claude Haiku 4.5 (Anthropic) and GPT-5.1 Codex Mini (OpenAI) by price, context, capabilities, and latency.
Side by side
Compare price, provider, context, capabilities, latency, and source basis.
| Model | Provider | Input | Output | Context | Capabilities | Best for | Latency | Status | Source |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 4.5anthropic/claude-haiku-4.5 | Anthropic | $1 / 1M tokens | $5 / 1M tokens | 200k | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1245-12720ms | Catalog | Platform curated |
| GPT-5.1 Codex Miniopenai/gpt-5.1-codex-mini | OpenAI | $0.25 / 1M tokens | $2 / 1M tokens | 400k | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1741-5672ms | Catalog | Platform curated |
FAQ
GPT-5.1 Codex Mini is cheaper ($0.25 / 1M tokens input / $2 / 1M tokens output) vs Claude Haiku 4.5 ($1 / 1M tokens input / $5 / 1M tokens output). Actual cost depends on your input/output token mix — estimate it with the pricing calculator.
GPT-5.1 Codex Mini is larger (400k tokens) vs 200k tokens.
Both target Vision. Pick GPT-5.1 Codex Mini to optimize cost, or GPT-5.1 Codex Mini for the longer context window. Test both on real prompts before committing production traffic.