Claude Haiku Latest
openrouter/~anthropic/claude-haiku-latest API key
models.dev2026-11-17
Type chat · Released 2026-04-27
Input window
1,000,000 tokensdocumented
models.dev · 2026-11-17
Input and output together
Context window
1,000,000 tokens
Exposed by this provider
Maximum output
128,000 tokens
Per response; not a default
Cache lifetime, short
5 mindocumented
models.dev · 2026-11-17
Cache lifetime, long
1 hdocumented
models.dev · 2026-11-17
Limits
Input window
| Limit | Value | Source |
|---|---|---|
Input windowinput_window: the most input one request can carry on this entry, in tokens as the provider counts them. | 1,000,000 tokensdocumentedInput and output together | models.dev2026-11-17 |
| Documented The figure the source documents, and the field it is in. | 1,000,000 tokenslimit.context | models.dev2026-11-17 |
| Measured What each limit evaluation that counts gives, one line per evaluation. | Not measured | – |
How the input window is worked out, and what it does not say
Documented
| Limit | Value | Source |
|---|---|---|
Context windowlimit.context: what this provider accepts for the model, input and output together. | 1,000,000 tokens | models.dev |
Largest inputlimit.input: stated where the input limit is lower than the context window. | Unknown | – |
Maximum outputlimit.output: the most one response can hold. A maximum, not what you get by default. | 128,000 tokens | models.dev |
Measured tokens
| Date | Measured through | Context | Input accepted | Input refused | Output limit | Requested output accepted | Evidence |
|---|---|---|---|---|---|---|---|
| No limits were measured on this entry. | |||||||
Price
| Base charge | Rate |
|---|---|
| Input | $0.10 / 1M tokens |
| Output | $0.50 / 1M tokens |
| Reasoning output | Unknown |
| Cache read | $0.01 / 1M tokens |
| Cache write | $0.125 / 1M tokens · 5 min lifetime $0.20 / 1M tokens · 1 h lifetime |
| Web search | $10 / 1,000 searches |
Conditional rates
| Condition | Charge | Rate | Applies to |
|---|---|---|---|
| Context above 100,000 tokens | Input | $0.50 / 1M tokens | Whole request |
| Output | $2.50 / 1M tokens | ||
| Cache read | $0.05 / 1M tokens | ||
| Context above 100,000 tokens and cache lifetime 5 min | Cache write | $0.625 / 1M tokens | Whole request |
| Context above 100,000 tokens and cache lifetime 1 h | Cache write | $1 / 1M tokens | Whole request |
Source: models.dev 2026-11-17
Other prices in the source, not shown above (0)
None
Request controls
| Control | Support | Request field | Accepted values | Default | Conditions |
|---|---|---|---|---|---|
| Service tier | Unknown | Unknown | Unknown | Unknown | Unknown |
Source: Unknown
Prompt caching
Lifetimes
| Lifetime | Documented for, or measured through | Time since the prompt was cached · served from the cache, in percent, with hits/checks | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| At once | 2.5 min | 5 min | 7.5 min | 10 min | 15 min | 20 min | 25 min | 30 min | 40 min | 50 min | 1 h | 1 h 15 | 1 h 30 | 2 h | 4 h | 8 h | 12 h | 24 h | ||
| Short retention |
| |||||||||||||||||||
| 5 mindocumentedmodels.dev2026-11-17 | Manual explicit As documented: 5m | Not applicable | ||||||||||||||||||
| Long retention |
| |||||||||||||||||||
| 1 hdocumentedmodels.dev2026-11-17 | Manual explicit As documented: 1h | Not applicable | ||||||||||||||||||
Checks served from the cache, in percent and as hits/checks, by time since the prompt was cached100 All67 Half or more33 Fewer0 None· Not checked at that ageMethodology
Cache modes
| Mode | Supported | Min. tokens | Breakpoints | Targets |
|---|---|---|---|---|
| Automatic implicit | Unknown | Unknown | Unknown | Unknown |
| Manual explicit | Supported | 512 | 4 | Unknown |
Source: models.dev · Cache modes
Retention
| Control | Support | Request field | Accepted values | Default | Conditions |
|---|---|---|---|---|---|
| Cache retention | Supported | cache_control.ttlRequest body, on a content block | Short: leave the field out Long: 1hcache_control.type=ephemeral, cache_control.ttl=1h | 5m | Set through the Chat Completions or the Anthropic Messages API. The Responses API has no field for a cache ttl. |
Source: openrouter.ai/docs/guides/best-practices/prompt-caching#cache-ttl-options 2026-11-14
Provenance
| Provenance | Value |
|---|---|
| Source | models.dev2026-11-17 |
| Inherited from | None |
| Corrections | None |
| Evidence | None |
Data
GET /api/v1/entries/openrouter/~anthropic/claude-haiku-latest
Show the full entry as published
{
"id": "~anthropic/claude-haiku-latest",
"name": "Claude Haiku Latest",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"type": "chat",
"family": "claude-haiku",
"release_date": "2026-04-27",
"limit": {
"context": 1000000,
"output": 128000
},
"capabilities": {
"cache": {
"explicit": {
"ttl": [
"5m",
"1h"
],
"min_tokens": 512,
"max_breakpoints": 4
}
},
"temperature": false,
"structured_output": true,
"system_updates": true,
"effort_updates": true,
"tools": {
"supported": true
},
"reasoning": {
"supported": true,
"effort": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
},
"cost": {
"text": {
"input": {
"price": 0.1,
"cache": {
"read": 0.01,
"write": {
"5m": 0.125,
"1h": 0.2
}
},
"overrides": [
{
"when": {
"context": {
"gt": 100000
}
},
"price": 0.5,
"cache": {
"read": 0.05,
"write": {
"5m": 0.625,
"1h": 1
}
}
}
]
},
"output": {
"price": 0.5,
"overrides": [
{
"when": {
"context": {
"gt": 100000
}
},
"price": 2.5
}
]
}
},
"web_search": {
"price": 10
}
},
"modalities": {
"input": [
"text",
"image/png",
"image/jpeg",
"image/webp",
"image/gif",
"application/pdf"
],
"output": [
"text"
]
},
"api": {
"chat-completions": {
"base_url": "https://openrouter.ai/api/v1",
"sdk": {
"aisdk": "@openrouter/ai-sdk-provider",
"opencodeai": "@opencode/ai/providers/openrouter"
},
"capabilities": {
"tools": {
"choice": [
"auto",
"none",
"required",
"tool"
],
"updates": []
}
}
},
"responses": {
"base_url": "https://openrouter.ai/api/v1",
"sdk": {
"aisdk": "@ai-sdk/openai",
"opencodeai": "@opencode/ai/providers/openai-compatible/responses"
},
"capabilities": {
"tools": {
"choice": [
"auto",
"none",
"required",
"tool"
],
"updates": []
}
}
},
"messages": {
"base_url": "https://openrouter.ai/api/v1",
"sdk": {
"aisdk": "@ai-sdk/anthropic",
"opencodeai": "@opencode/ai/providers/anthropic-compatible"
},
"capabilities": {
"tools": {
"choice": [
"auto",
"none",
"required",
"tool"
],
"updates": []
}
}
}
},
"open_weights": false,
"last_updated": "2026-04-27",
"providers_dev": {
"origin": "upstream",
"access": "api",
"provenance": [],
"inherited": null,
"cache": {
"documented": {
"support": "supported",
"modes": {
"implicit": {
"support": "unknown",
"min_tokens": null,
"max_breakpoints": null,
"targets": null
},
"explicit": {
"support": "supported",
"min_tokens": 512,
"max_breakpoints": 4,
"targets": null
}
}
},
"retention": {
"support": "supported",
"parameter": {
"name": "cache_control.ttl",
"location": "Request body, on a content block"
},
"accepted_values": [
"1h"
],
"default": "5m",
"profiles": [
{
"profile": "short",
"value": null
},
{
"profile": "long",
"value": "1h"
}
],
"conditions": [
"Set through the Chat Completions or the Anthropic Messages API. The Responses API has no field for a cache ttl."
],
"evidence": [
{
"kind": "documented",
"url": "https://openrouter.ai/docs/guides/best-practices/prompt-caching#cache-ttl-options",
"date": "2026-11-14",
"note": "'OpenRouter supports two cache TTL values for Anthropic: 5 minutes (default): \"cache_control\": { \"type\": \"ephemeral\" }. 1 hour: \"cache_control\": { \"type\": \"ephemeral\", \"ttl\": \"1h\" }.' On the Responses API: 'if you need to set a cache ttl, use the Chat Completions or Anthropic Messages API with cache_control.'"
}
]
},
"lifetime": {
"short": {
"safe_s": 300,
"basis": "documented",
"source": "models.dev",
"date": "2026-11-17",
"documented_s": 300,
"measured_s": null,
"documented_status": null,
"clients": 0,
"evaluations": 0,
"checks": 0,
"hits": 0,
"checks_inside": null,
"hits_inside": null,
"tested_from_s": null,
"first_miss_s": null
},
"long": {
"safe_s": 3600,
"basis": "documented",
"source": "models.dev",
"date": "2026-11-17",
"documented_s": 3600,
"measured_s": null,
"documented_status": null,
"clients": 0,
"evaluations": 0,
"checks": 0,
"hits": 0,
"checks_inside": null,
"hits_inside": null,
"tested_from_s": null,
"first_miss_s": null
},
"lifetimes": [
{
"retention_profile": "short",
"basis": "documented",
"source": "models.dev",
"date": "2026-11-17",
"lifetime_s": 300,
"mode": "explicit",
"documented_as": "5m",
"client": null,
"client_label": null,
"parameter": null,
"value": null,
"evaluations": 0,
"evaluation_ids": [],
"checks": 0,
"hits": 0,
"tested_from_s": null,
"first_miss_s": null,
"results": null
},
{
"retention_profile": "long",
"basis": "documented",
"source": "models.dev",
"date": "2026-11-17",
"lifetime_s": 3600,
"mode": "explicit",
"documented_as": "1h",
"client": null,
"client_label": null,
"parameter": null,
"value": null,
"evaluations": 0,
"evaluation_ids": [],
"checks": 0,
"hits": 0,
"tested_from_s": null,
"first_miss_s": null,
"results": null
}
]
},
"evaluations": []
},
"pricing": {
"coverage": "partial",
"billing": "per_use",
"reference_ref": null,
"rules": [
{
"id": "cost.text.input.price",
"when": null,
"meter": "text.input",
"operation": "set",
"amount": 0.1,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.input.price",
"period": null,
"resulting_rates": null
},
{
"id": "cost.text.input.cache.read",
"when": null,
"meter": "text.cache_read",
"operation": "set",
"amount": 0.01,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.input.cache.read",
"period": null,
"resulting_rates": null
},
{
"id": "cost.text.output.price",
"when": null,
"meter": "text.output",
"operation": "set",
"amount": 0.5,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.output.price",
"period": null,
"resulting_rates": null
},
{
"id": "cost.web_search.price",
"when": null,
"meter": "web_search",
"operation": "set",
"amount": 10,
"currency": "USD",
"unit": {
"name": "search",
"quantity": 1000
},
"applies_to": "all_usage",
"source_path": "cost.web_search.price",
"period": null,
"resulting_rates": null
},
{
"id": "cost.text.input.cache.write.5m",
"when": {
"kind": "predicate",
"field": "cache.retention_s",
"op": "eq",
"value": 300
},
"meter": "text.cache_write",
"operation": "set",
"amount": 0.125,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.input.cache.write.5m",
"period": null,
"resulting_rates": null
},
{
"id": "cost.text.input.cache.write.1h",
"when": {
"kind": "predicate",
"field": "cache.retention_s",
"op": "eq",
"value": 3600
},
"meter": "text.cache_write",
"operation": "set",
"amount": 0.2,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.input.cache.write.1h",
"period": null,
"resulting_rates": null
},
{
"id": "cost.text.input.overrides[0].price",
"when": {
"kind": "predicate",
"field": "request.context_tokens",
"op": "gt",
"value": 100000
},
"meter": "text.input",
"operation": "set",
"amount": 0.5,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.input.overrides[0].price",
"period": null,
"resulting_rates": null
},
{
"id": "cost.text.input.overrides[0].cache.read",
"when": {
"kind": "predicate",
"field": "request.context_tokens",
"op": "gt",
"value": 100000
},
"meter": "text.cache_read",
"operation": "set",
"amount": 0.05,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.input.overrides[0].cache.read",
"period": null,
"resulting_rates": null
},
{
"id": "cost.text.input.overrides[0].cache.write.5m",
"when": {
"kind": "all",
"conditions": [
{
"kind": "predicate",
"field": "request.context_tokens",
"op": "gt",
"value": 100000
},
{
"kind": "predicate",
"field": "cache.retention_s",
"op": "eq",
"value": 300
}
]
},
"meter": "text.cache_write",
"operation": "set",
"amount": 0.625,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.input.overrides[0].cache.write.5m",
"period": null,
"resulting_rates": null
},
{
"id": "cost.text.input.overrides[0].cache.write.1h",
"when": {
"kind": "all",
"conditions": [
{
"kind": "predicate",
"field": "request.context_tokens",
"op": "gt",
"value": 100000
},
{
"kind": "predicate",
"field": "cache.retention_s",
"op": "eq",
"value": 3600
}
]
},
"meter": "text.cache_write",
"operation": "set",
"amount": 1,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.input.overrides[0].cache.write.1h",
"period": null,
"resulting_rates": null
},
{
"id": "cost.text.output.overrides[0].price",
"when": {
"kind": "predicate",
"field": "request.context_tokens",
"op": "gt",
"value": 100000
},
"meter": "text.output",
"operation": "set",
"amount": 2.5,
"currency": "USD",
"unit": {
"name": "token",
"quantity": 1000000
},
"applies_to": "all_usage",
"source_path": "cost.text.output.overrides[0].price",
"period": null,
"resulting_rates": null
}
],
"rule_order": "listed",
"unparsed": [],
"evidence": [
{
"kind": "documented",
"url": "https://models.dev",
"date": "2026-11-17",
"note": "The cost models.dev records for this entry. Rules are in the order models.dev applies them: base prices, overrides in their order, then multipliers."
}
]
},
"request_controls": {
"coverage": "partial",
"items": [
{
"id": "cache.retention",
"support": "supported",
"when": null,
"bindings": [
{
"location": "body",
"path": "/cache_control/ttl",
"scope": "content_block"
}
],
"options": [
{
"value": null,
"attributes": {
"retention_s": 300,
"profile": "short"
},
"settings": [
{
"location": "body",
"path": "/cache_control/type",
"scope": "content_block",
"value": "ephemeral"
}
],
"when": null
},
{
"value": "1h",
"attributes": {
"retention_s": 3600,
"profile": "long"
},
"settings": [
{
"location": "body",
"path": "/cache_control/type",
"scope": "content_block",
"value": "ephemeral"
},
{
"location": "body",
"path": "/cache_control/ttl",
"scope": "content_block",
"value": "1h"
}
],
"when": null
}
],
"default": {
"value": "5m"
},
"conditions": [
"Set through the Chat Completions or the Anthropic Messages API. The Responses API has no field for a cache ttl."
],
"evidence": [
{
"kind": "documented",
"url": "https://openrouter.ai/docs/guides/best-practices/prompt-caching#cache-ttl-options",
"date": "2026-11-14",
"note": "'OpenRouter supports two cache TTL values for Anthropic: 5 minutes (default): \"cache_control\": { \"type\": \"ephemeral\" }. 1 hour: \"cache_control\": { \"type\": \"ephemeral\", \"ttl\": \"1h\" }.' On the Responses API: 'if you need to set a cache ttl, use the Chat Completions or Anthropic Messages API with cache_control.'"
}
]
},
{
"id": "service_tier",
"support": "unknown",
"when": null,
"bindings": null,
"options": null,
"default": null,
"conditions": [],
"evidence": []
}
]
},
"limits": {
"measured": [],
"from_measurement": [],
"input_window": {
"tokens": 1000000,
"basis": "documented",
"bound": "limit",
"scope": "window",
"source": "models.dev",
"date": "2026-11-17",
"documented_tokens": 1000000,
"documented_field": "limit.context",
"documented_source": "models.dev",
"documented_date": "2026-11-17",
"documented_status": null,
"measured_tokens": null,
"measured_bound": null,
"measured_kind": null,
"measured_refused": null,
"measured_date": null,
"clients": 0,
"evaluations": 0,
"measurements": []
}
},
"evidence": [],
"verified": null
}
}