Switch model

API PRICES

Anthropic · claude-haiku-5-5

Provider prices, cheapest first

Browse all models

Price comparison

Official (cash)
Input 0.1 / output 0.5 USD/million tokensAnthropic ·
Lowest inference provider (cash)
Input 0.105 / output 0.525 USD/million tokensOpenRouter · Aggregator · Via OpenRouter with 5% fee, original price × 1.05 ·
Lowest relay (credit)
Not listed

Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.

All official and inference price observations

Anthropic · claude-haiku-5-5 official price: input 0.1, output 0.5 USD per million tokens (Anthropic, observed 2026-11-13). Cheapest inference provider: OpenRouter, input 0.105, output 0.525 USD per million tokens. This is the price via OpenRouter with a 5% fee added, original price × 1.05. Original price: input 0.1, output 0.5. 133 sites have comparable prices; 993 sites list this model. Conditions: Context tier: PROMPT_LE_100000 · section: Model pricing · 1-hour cache write 0.20 USD per MTok; cacheWrite is the 5-minute write · Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)

Price ranges per million tokens

Official cash prices · Lowest 0.2 · median 0.2 · highest 0.2 · 1 quotes USD / per million tokens · 1 of these are priced by context length; each counts once, at its lowest tier

Inference provider cash prices · Lowest 0.21 · median 0.21 · highest 0.21 · 1 quotes USD / per million tokens

Each quote is blended into one price by this workload: ordinary input 75% · cache read 0% · output 25% · cache write 0%. Only prices in effect now are counted.

Official price

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
AnthropicStandard0.10.50.01
0.125 · 5 min
0.2 · 1 hour
USD / 1M tokensContext tier: PROMPT_LE_100000 · section: Model pricing · 1-hour cache write 0.20 USD per MTok; cacheWrite is the 5-minute writeCache write is compared at the 5 min price; a 1 hour price is also listed
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": "PROMPT_LE_100000",
  "processingMode": null,
  "conditionNotes": [
    "section: Model pricing",
    "1-hour cache write 0.20 USD per MTok; cacheWrite is the 5-minute write"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
AnthropicStandard0.52.50.05
0.625 · 5 min
1 · 1 hour
USD / 1M tokensContext tier: PROMPT_GT_100000 · section: Model pricing · 1-hour cache write 1 USD per MTok; cacheWrite is the 5-minute writeCache write is compared at the 5 min price; a 1 hour price is also listed
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": "PROMPT_GT_100000",
  "processingMode": null,
  "conditionNotes": [
    "section: Model pricing",
    "1-hour cache write 1 USD per MTok; cacheWrite is the 5-minute write"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.

Inference providers

For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.

ProviderTariffInputOutputCache readCache writeVia OpenRouter with 5% feeUnitObservedConditions and sourcevs official
OpenRouter · AggregatorStandard0.10.50.010.125
Input 0.105
Output 0.525
Cache read 0.0105
Cache write 0.13125
Original price × 1.05
USD / 1M tokensContext tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.00000001",
    "cacheWrite": "0.000000125",
    "input": "0.0000001",
    "output": "0.0000005"
  },
  "conditions": [],
  "contextTier": "OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE",
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Other tariffs and prices to review

Official price

For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.

ProviderTariffInputOutputCache readCache writeVia OpenRouter with 5% feeUnitObservedConditions and source
AnthropicBatch0.050.25——USD / 1M tokensContext tier: PROMPT_LE_100000 · Batch processing · section: Feature-specific pricing
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": "PROMPT_LE_100000",
  "processingMode": "batch",
  "conditionNotes": [
    "section: Feature-specific pricing"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
AnthropicBatch0.251.25——USD / 1M tokensContext tier: PROMPT_GT_100000 · Batch processing · section: Feature-specific pricing
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": "PROMPT_GT_100000",
  "processingMode": "batch",
  "conditionNotes": [
    "section: Feature-specific pricing"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
AnthropicOther tariff0.110.550.011
0.1375 · 5 min
0.22 · 1 hour
USD / 1M tokensContext tier: PROMPT_LE_100000 · Processing mode: us-data-residency · base declaration: section: Model pricing · base declaration: 1-hour cache write 0.20 USD per MTok; cacheWrite is the 5-minute write · declared multiplier: 1.1x · For Claude 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens,… · Global routing (the default) uses standard pricing. · This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed). · single modifier only; no cross-products · single modifier only; no cross-product of pricing modifiersCache write is compared at the 5 min price; a 1 hour price is also listed
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "base declaration: section: Model pricing",
    "base declaration: 1-hour cache write 0.20 USD per MTok; cacheWrite is the 5-minute write",
    "declared multiplier: 1.1x",
    "For Claude 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads.",
    "Global routing (the default) uses standard pricing.",
    "This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed).",
    "single modifier only; no cross-products",
    "single modifier only; no cross-product of pricing modifiers"
  ],
  "contextTier": "PROMPT_LE_100000",
  "processingMode": "us-data-residency",
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
AnthropicOther tariff0.552.750.055
0.6875 · 5 min
1.1 · 1 hour
USD / 1M tokensContext tier: PROMPT_GT_100000 · Processing mode: us-data-residency · base declaration: section: Model pricing · base declaration: 1-hour cache write 1 USD per MTok; cacheWrite is the 5-minute write · declared multiplier: 1.1x · For Claude 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens,… · Global routing (the default) uses standard pricing. · This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed). · single modifier only; no cross-products · single modifier only; no cross-product of pricing modifiersCache write is compared at the 5 min price; a 1 hour price is also listed
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "base declaration: section: Model pricing",
    "base declaration: 1-hour cache write 1 USD per MTok; cacheWrite is the 5-minute write",
    "declared multiplier: 1.1x",
    "For Claude 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads.",
    "Global routing (the default) uses standard pricing.",
    "This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed).",
    "single modifier only; no cross-products",
    "single modifier only; no cross-product of pricing modifiers"
  ],
  "contextTier": "PROMPT_GT_100000",
  "processingMode": "us-data-residency",
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
GoogleStandard0.10.50.010.125
Input 0.105
Output 0.525
Cache read 0.0105
Cache write 0.13125
Original price × 1.05
USD / 1M tokensServed through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · endpoint region: global · price listed by OpenRouter for this provider (endpoint google-vertex/global)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.00000001",
    "cacheWrite": "0.000000125",
    "input": "0.0000001",
    "output": "0.0000005"
  },
  "conditions": [
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "endpoint region: global",
    "price listed by OpenRouter for this provider (endpoint google-vertex/global)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Claude Platform on AWSStandard0.10.50.010.125
Input 0.105
Output 0.525
Cache read 0.0105
Cache write 0.13125
Original price × 1.05
USD / 1M tokensServed through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · price listed by OpenRouter for this provider (endpoint claude-on-aws)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.00000001",
    "cacheWrite": "0.000000125",
    "input": "0.0000001",
    "output": "0.0000005"
  },
  "conditions": [
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "price listed by OpenRouter for this provider (endpoint claude-on-aws)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
AzureStandard0.10.50.010.125
Input 0.105
Output 0.525
Cache read 0.0105
Cache write 0.13125
Original price × 1.05
USD / 1M tokensOpenRouter endpoint status -2 (not normal) · Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · endpoint region: global · price listed by OpenRouter for this provider (endpoint azure/global)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.00000001",
    "cacheWrite": "0.000000125",
    "input": "0.0000001",
    "output": "0.0000005"
  },
  "conditions": [
    "OpenRouter endpoint status -2 (not normal)",
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "endpoint region: global",
    "price listed by OpenRouter for this provider (endpoint azure/global)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
AnthropicStandard0.10.50.010.125
Input 0.105
Output 0.525
Cache read 0.0105
Cache write 0.13125
Original price × 1.05
USD / 1M tokensOpenRouter endpoint status -5 (not normal) · Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · price listed by OpenRouter for this provider (endpoint anthropic)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.00000001",
    "cacheWrite": "0.000000125",
    "input": "0.0000001",
    "output": "0.0000005"
  },
  "conditions": [
    "OpenRouter endpoint status -5 (not normal)",
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "price listed by OpenRouter for this provider (endpoint anthropic)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Amazon BedrockStandard0.10.50.010.125
Input 0.105
Output 0.525
Cache read 0.0105
Cache write 0.13125
Original price × 1.05
USD / 1M tokensServed through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · price listed by OpenRouter for this provider (endpoint amazon-bedrock)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.00000001",
    "cacheWrite": "0.000000125",
    "input": "0.0000001",
    "output": "0.0000005"
  },
  "conditions": [
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "price listed by OpenRouter for this provider (endpoint amazon-bedrock)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
GoogleOther tariff0.110.550.0110.1375
Input 0.1155
Output 0.5775
Cache read 0.01155
Cache write 0.14438
Original price × 1.05
USD / 1M tokensOpenRouter endpoint variant: europe · Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · price listed by OpenRouter for this provider (endpoint google-vertex/europe)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000011",
    "cacheWrite": "0.0000001375",
    "input": "0.00000011",
    "output": "0.00000055"
  },
  "conditions": [
    "OpenRouter endpoint variant: europe",
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "price listed by OpenRouter for this provider (endpoint google-vertex/europe)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
GoogleStandard0.110.550.0110.1375
Input 0.1155
Output 0.5775
Cache read 0.01155
Cache write 0.14438
Original price × 1.05
USD / 1M tokensServed through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · endpoint region: us · price listed by OpenRouter for this provider (endpoint google-vertex/us)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000011",
    "cacheWrite": "0.0000001375",
    "input": "0.00000011",
    "output": "0.00000055"
  },
  "conditions": [
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "endpoint region: us",
    "price listed by OpenRouter for this provider (endpoint google-vertex/us)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
AzureStandard0.110.550.0110.1375
Input 0.1155
Output 0.5775
Cache read 0.01155
Cache write 0.14438
Original price × 1.05
USD / 1M tokensServed through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · endpoint region: us · price listed by OpenRouter for this provider (endpoint azure/us)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000011",
    "cacheWrite": "0.0000001375",
    "input": "0.00000011",
    "output": "0.00000055"
  },
  "conditions": [
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "endpoint region: us",
    "price listed by OpenRouter for this provider (endpoint azure/us)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Amazon BedrockStandard0.110.550.0110.1375
Input 0.1155
Output 0.5775
Cache read 0.01155
Cache write 0.14438
Original price × 1.05
USD / 1M tokensServed through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · endpoint region: us-east-1 · price listed by OpenRouter for this provider (endpoint amazon-bedrock/us-east-1)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000011",
    "cacheWrite": "0.0000001375",
    "input": "0.00000011",
    "output": "0.00000055"
  },
  "conditions": [
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "endpoint region: us-east-1",
    "price listed by OpenRouter for this provider (endpoint amazon-bedrock/us-east-1)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Amazon BedrockStandard0.110.550.0110.1375
Input 0.1155
Output 0.5775
Cache read 0.01155
Cache write 0.14438
Original price × 1.05
USD / 1M tokensServed through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) · endpoint region: eu-west-1 · price listed by OpenRouter for this provider (endpoint amazon-bedrock/eu-west-1)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000011",
    "cacheWrite": "0.0000001375",
    "input": "0.00000011",
    "output": "0.00000055"
  },
  "conditions": [
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)",
    "endpoint region: eu-west-1",
    "price listed by OpenRouter for this provider (endpoint amazon-bedrock/eu-west-1)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Inference providers

For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.

ProviderTariffInputOutputCache readCache writeVia OpenRouter with 5% feeUnitObservedConditions and source
OpenRouter · AggregatorStandard0.52.50.050.625
Input 0.525
Output 2.625
Cache read 0.0525
Cache write 0.65625
Original price × 1.05
USD / 1M tokensContext tier: OPENROUTER_MIN_PROMPT_TOKENS_100000 · OpenRouter override for prompts from 100000 tokens (boundary inclusivity not stated) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.00000005",
    "cacheWrite": "0.000000625",
    "input": "0.0000005",
    "output": "0.0000025"
  },
  "conditions": [
    "OpenRouter override for prompts from 100000 tokens (boundary inclusivity not stated)"
  ],
  "contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_100000",
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
OpenRouter · AggregatorBatch0.050.250.0050.0625
Input 0.0525
Output 0.2625
Cache read 0.00525
Cache write 0.065625
Original price × 1.05
USD / 1M tokensContext tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · OpenRouter batch variant · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000005",
    "cacheWrite": "0.0000000625",
    "input": "0.00000005",
    "output": "0.00000025"
  },
  "conditions": [
    "OpenRouter batch variant"
  ],
  "contextTier": "OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE",
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
OpenRouter · AggregatorBatch0.251.250.0250.3125
Input 0.2625
Output 1.3125
Cache read 0.02625
Cache write 0.32813
Original price × 1.05
USD / 1M tokensContext tier: OPENROUTER_MIN_PROMPT_TOKENS_100000 · OpenRouter batch variant · OpenRouter override for prompts from 100000 tokens (boundary inclusivity not stated) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000025",
    "cacheWrite": "0.0000003125",
    "input": "0.00000025",
    "output": "0.00000125"
  },
  "conditions": [
    "OpenRouter batch variant",
    "OpenRouter override for prompts from 100000 tokens (boundary inclusivity not stated)"
  ],
  "contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_100000",
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Older official and inference provider prices

Earlier price observations and their original conditions

Official price

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
AnthropicOther tariff0.110.550.011
0.1375 · 5 min
0.22 · 1 hour
USD / 1M tokensContext tier: PROMPT_LE_100000 · Processing mode: us-data-residency · base declaration: section: Model pricing · base declaration: 1-hour cache write 0.20 USD per MTok; cacheWrite is the 5-minute write · declared multiplier: 1.1x · For Claude 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens,… · Global routing (the default) uses standard pricing. · This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed). · Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Bedrock, have independent regional pricing. · single modifier only; no cross-products · single modifier only; no cross-product of pricing modifiersCache write is compared at the 5 min price; a 1 hour price is also listed
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "base declaration: section: Model pricing",
    "base declaration: 1-hour cache write 0.20 USD per MTok; cacheWrite is the 5-minute write",
    "declared multiplier: 1.1x",
    "For Claude 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads.",
    "Global routing (the default) uses standard pricing.",
    "This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed).",
    "Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Bedrock, have independent regional pricing.",
    "single modifier only; no cross-products",
    "single modifier only; no cross-product of pricing modifiers"
  ],
  "contextTier": "PROMPT_LE_100000",
  "processingMode": "us-data-residency",
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
AnthropicOther tariff0.552.750.055
0.6875 · 5 min
1.1 · 1 hour
USD / 1M tokensContext tier: PROMPT_GT_100000 · Processing mode: us-data-residency · base declaration: section: Model pricing · base declaration: 1-hour cache write 1 USD per MTok; cacheWrite is the 5-minute write · declared multiplier: 1.1x · For Claude 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens,… · Global routing (the default) uses standard pricing. · This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed). · Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Bedrock, have independent regional pricing. · single modifier only; no cross-products · single modifier only; no cross-product of pricing modifiersCache write is compared at the 5 min price; a 1 hour price is also listed
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "base declaration: section: Model pricing",
    "base declaration: 1-hour cache write 1 USD per MTok; cacheWrite is the 5-minute write",
    "declared multiplier: 1.1x",
    "For Claude 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads.",
    "Global routing (the default) uses standard pricing.",
    "This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed).",
    "Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Bedrock, have independent regional pricing.",
    "single modifier only; no cross-products",
    "single modifier only; no cross-product of pricing modifiers"
  ],
  "contextTier": "PROMPT_GT_100000",
  "processingMode": "us-data-residency",
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.

Showing: Special groups。These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics. Back to the default ranking

Searching…

Browse all providers

Blended price = input × 75% + output × 25%, without cache.

Price range: lowest — · median — · highest — (0 quotes, USD credits per million total tokens)

sites have comparable prices133993 sites list this model; approximately 1 operators
Lowest input price—USD credits / 1M
Median of each provider’s lowest price—USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Special groups · not ranked · Flagged · not ranked · Recent price
—cc.kakade.topAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected:
Collected this cycle
View 1 plans
CC-vip-official group [machine translation]Group on site: CC-vip-官方组
Official CC [machine translation]Original: 官方CC

Note: Its group is marked as a test group, discontinued or gated. This price is not ranked or counted.

Group notes: near-zero-ratio group

Operator pending verification
2100.24
Details
Full prices and sources
How this ranking works

All per-token prices: 128,524 prices from 1,383 sites (about 1,275 companies). 109,485 are ranked, from 1,349 sites (about 1,244 companies); 19,039 more are listed separately and not ranked. Prices collected up to 2026-11-15.

This model has 3304 recorded prices; 328 can be compared directly (325 ranked, 3 listed separately). Not comparable yet: price not parsed yet 863, ratio looks unset 165, new price under review; showing the previous one 85, display unit not confirmed 16, scope of the official doc price not confirmed 6, CAPTURE_FRAMEWORK_UNIT_SEMANTICS_NOT_REVIEWED 5. 1795 more are tiered by rules and compared on the Tiered prices board

1 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. No recent prices to summarize in this group.

Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.

“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.

Full methodology →

Sources not accepted this cycle and reasons

FAQ

Which API is cheapest for Anthropic · claude-haiku-5-5?

No valid quotes within 10 days. Older quotes are listed as reference prices. 1739 tiered prices are listed on the tiered board.

What is the official price for Anthropic · claude-haiku-5-5?

Input 0.1, output 0.5 USD per million tokens, checked 2026-11-13. Lowest inference provider: OpenRouter, input 0.105, output 0.525 USD per million tokens. This is the price via OpenRouter with a 5% fee added, original price × 1.05. Original price: input 0.1, output 0.5.

How do I use Anthropic · claude-haiku-5-5 in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest Anthropic · claude-haiku-5-5 API to Claude Code for me". Install Skill →