claude-haiku-4.5
OpenRouter · chat model
claude-haiku-4.5 is listed here as a chat model from OpenRouter. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$1.0000 / 1M tokens
Output
$5.0000 / 1M tokens
Cached input
$0.1000 / 1M tokens
Context
200.0K
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $1.0000 / 1M tokens |
| Output | $5.0000 / 1M tokens |
| Cached input | $0.1000 / 1M tokens |
| Cache write | $1.2500 / 1M tokens |
| Embedding | $1.0000 / 1M tokens |
Token limits
Context window
200.0K
Max input tokens
200.0K
Max output tokens
200.0K
Max tokens
200.0K
Capabilities
| Capability | Supported |
|---|---|
| Vision | ✅ |
| Function calling | ✅ |
| Parallel function calling | — |
| Tool choice | ✅ |
| Prompt caching | ✅ |
| Reasoning | ✅ |
| Response schema | — |
| System messages | — |
| Audio input | — |
| Audio output | — |
| Web search | — |
| PDF input | — |
| Video input | — |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| SWE-bench Verified | 73.3% | score | Base model: Claude Haiku 4.5 (claude-haiku-4-5) | 2026-05-31 | Link |
| SWE-bench Verified | 66.60% | % resolved | Base model: Claude 4.5 Haiku (Claude 4.5 Haiku (high reasoning)) | 2026-05-31 | Link |
| SWE-bench Verified | 73.3% | accuracy | Base model: Claude Haiku 4.5 (claude-haiku-4.5) | 2026-05-31 | Link |
| GPQA Diamond | 67.2% | accuracy | Base model: Claude Haiku 4.5 (anthropic/claude-haiku-4.5) | 2026-05-31 | Link |
| Terminal-Bench Hard | 27.3% | pass rate | Base model: Claude Haiku 4.5 (anthropic/claude-haiku-4.5) | 2026-05-31 | Link |
| IFBench | 54.3% | accuracy | Base model: Claude Haiku 4.5 (anthropic/claude-haiku-4.5) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Docs
| Official docs |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| claude-haiku-4.5 OpenRouter | In $1.0000 / 1M tokens Out $5.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 200.0K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| claude-haiku-4.5 vercel_ai_gateway | In $1.0000 / 1M tokens Out $5.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 86% |
| claude-sonnet-4.6 OpenRouter | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 81% |
| gpt-5.2 OpenRouter | In $1.7500 / 1M tokens Out $14.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 80% |
| claude-opus-4.6 OpenRouter | In $5.0000 / 1M tokens Out $25.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 79% |
| claude-sonnet-4 OpenRouter | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Same provider Overall 76% |
| claude-sonnet-4.5 vercel_ai_gateway | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 76% |
| anthropic.claude-haiku-4-5-20251001-v1:0 bedrock_converse | In $1.0000 / 1M tokens Out $5.0000 / 1M tokens | fileimagetext pdf
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 76% |
| anthropic.claude-haiku-4-5@20251001 bedrock_converse | In $1.0000 / 1M tokens Out $5.0000 / 1M tokens | fileimagetext pdf
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 76% |
| claude-haiku-4-5 azure_ai | In $1.0000 / 1M tokens Out $5.0000 / 1M tokens | fileimagetext pdf
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 76% |
| claude-haiku-4-5-20251001 Anthropic | In $1.0000 / 1M tokens Out $5.0000 / 1M tokens | fileimagetext pdf
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 76% |
| claude-haiku-4-5 Anthropic | In $1.0000 / 1M tokens Out $5.0000 / 1M tokens | fileimagetext pdf
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 76% |
| global.anthropic.claude-haiku-4-5-20251001-v1:0 bedrock_converse | In $1.0000 / 1M tokens Out $5.0000 / 1M tokens | fileimagetext pdf
Output: text | VisionFunction callingTool choicePrompt caching | 64.0K | Text + image covered Overall 76% |
| gpt-5.1-codex-max OpenRouter | In $1.2500 / 1M tokens Out $10.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 75% |
| claude-sonnet-4.5 OpenRouter | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 1.0M | Same provider Overall 75% |
| claude-opus-4.5 OpenRouter | In $5.0000 / 1M tokens Out $25.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 32.0K | Same provider Overall 71% |
| claude-opus-4 OpenRouter | In $15.0000 / 1M tokens Out $75.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 32.0K | Same provider Overall 69% |
| claude-opus-4.1 OpenRouter | In $15.0000 / 1M tokens Out $75.0000 / 1M tokens | fileimagetext
Output: text | VisionFunction callingTool choicePrompt caching | 32.0K | Same provider Overall 69% |
No models match this filter.