API PRICES
Anthropic · claude-haiku-4-5
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 1 / output 5 USD/million tokensAnthropic ·
- Lowest inference provider (cash)
- Input 1 / output 5 USD/million tokensDeepInfra ·
- Lowest relay (credit)
- 0.3 CNY credit/million total tokensapi.everygpt.site "Claude-Kiro高缓存" ·
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-4-5 official price: input 1, output 5 USD per million tokens (Anthropic, observed 2026-10-24). Cheapest inference provider: DeepInfra, input 1, output 5 USD per million tokens. Cheapest relay: api.everygpt.site, group "Claude-Kiro high cache [machine translation] (on site: Claude-Kiro高缓存)" 0.3 CNY_CREDIT per million total tokens (credit price, not cash, observed 2026-10-23). 230 sites have comparable prices; 432 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: section: Model pricing · 1-hour cache write 2 USD per MTok; cacheWrite is the 5-minute write
Price ranges per million tokens
Official cash prices · Lowest 2 · median 2 · highest 2 · 1 quotes USD / per million tokens
Inference provider cash prices · Lowest 2 · median 2 · highest 2 · 2 quotes USD / per million tokens
Relay CNY credit prices · Lowest 0.3 · median 1.2 · highest 2.8 · 4 quotes CNY / per million tokens, site credit
Official price
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| Anthropic | Standard | 1 | 5 | 0.1 | 1.25 | USD / 1M tokens | section: Model pricing · 1-hour cache write 2 USD per MTok; cacheWrite is the 5-minute writeFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"section: Model pricing",
"1-hour cache write 2 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
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|---|
| DeepInfra | Standard | 1 | 5 | — | — | USD / 1M tokens | Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| OpenRouter · Aggregator | Standard | 1 | 5 | 0.1 | 1.25 | USD / 1M tokens | Additional web_search price 0.01 USD (per unit as declared by OpenRouter)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000001",
"cacheWrite": "0.00000125",
"input": "0.000001",
"output": "0.000005"
},
"conditions": [],
"contextTier": null,
"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
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| Anthropic | Batch | 0.5 | 2.5 | — | — | USD / 1M tokens | Batch processing · section: Feature-specific pricingFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": "batch",
"conditionNotes": [
"section: Feature-specific pricing"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Inference providers
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | Batch | 0.5 | 2.5 | 0.05 | 0.625 | USD / 1M tokens | 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": "0.00000005",
"cacheWrite": "0.000000625",
"input": "0.0000005",
"output": "0.0000025"
},
"conditions": [
"OpenRouter batch variant"
],
"contextTier": null,
"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
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| Anthropic | Batch | 0.5 | 2.5 | — | — | USD / 1M tokens | Batch processing · section: Feature-specific pricingFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": "batch",
"conditionNotes": [
"section: Feature-specific pricing"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| Anthropic | Standard | 1 | 5 | 0.1 | 1.25 | USD / 1M tokens | section: Model pricing · 1-hour cache write 2 USD per MTok; cacheWrite is the 5-minute writeFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"section: Model pricing",
"1-hour cache write 2 USD per MTok; cacheWrite is the 5-minute write"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Inference providers
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | Batch | 0.5 | 2.5 | 0.05 | 0.625 | USD / 1M tokens | 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": "0.00000005",
"cacheWrite": "0.000000625",
"input": "0.0000005",
"output": "0.0000025"
},
"conditions": [
"OpenRouter batch variant"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| OpenRouter · Aggregator | Standard | 1 | 5 | 0.1 | 1.25 | USD / 1M tokens | Additional web_search price 0.01 USD (per unit as declared by OpenRouter)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000001",
"cacheWrite": "0.00000125",
"input": "0.000001",
"output": "0.000005"
},
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| DeepInfra | Standard | 1 | 5 | — | — | USD / 1M tokens | Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Unit: CNY credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Price range: lowest 0.3 · median 1.2 · highest 2.8 (4 quotes, CNY credits per million total tokens)
Relays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑CNY credits / 1M | Output CNY credits / 1M | Cache readCNY credits / 1M | BlendedCNY credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | api.everygpt.siteAsk or discussCollected: Collected this cycle View 4 plans | Claude-Kiro high cache [machine translation]Group on site: Claude-Kiro高缓存 Kiro stable claude, light workloads [machine translation]Original: Kiro稳定claude,轻度工作 Operator pending verification | 0.15 | 0.75 | 0.015 | 0.3Median price ÷ this price: 4× | Full prices and sources |
| 02 | api.everygpt.siteAsk or discussCollected: Collected this cycle View 4 plans | Claude-KiroMAX KiroPro full-price account pool, absolutely great to use, opus5-5 recommended [machine translation]Original: KiroPro正价号池,绝对的好用,推荐opus5-5 Operator pending verification | 0.5 | 2.5 | 0.05 | 1Median price ÷ this price: 1.2× | Full prices and sources |
| 03 | api.everygpt.siteAsk or discussCollected: Collected this cycle View 4 plans | Claude - special-price Claude [machine translation]Group on site: Claude-特惠Claude High-IQ CC account, 70-80% of CC's strength [machine translation]Original: 高智商CC号,7-8成CC的实力 Operator pending verification | 0.7 | 3.5 | 0.07 | 1.4Median price ÷ this price: 0.9× | Full prices and sources |
| 04 | api.everygpt.siteAsk or discussCollected: Collected this cycle View 4 plans | Claude-CCMAX 站点写明 VIP 用户另有价格 ClaudeCode-max nearly 0 injection full-strength account pool, VIP 8-zhe (80% of original price) [machine translation]Original: ClaudeCode-max 几乎 0 注入 满血号池,VIP8折 Operator pending verification | 1.4 | 7 | 0.14 | 2.8Median price ÷ this price: 0.4× | Full prices and sources |
Special groups · 2 rows · not ranked
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.
- test or debug group: 2 rows
- api.vakv.cn · CCMAX-0 injection-test group [machine translation]Group on site: CCMAX-0注入-测试分组 · claude-haiku-4-5 · Input 1.8 / Output 9 CNY credits / 1M
- vakv.cn · CCMAX-0 injection-test group [machine translation]Group on site: CCMAX-0注入-测试分组 · claude-haiku-4-5 · Input 1.8 / Output 9 CNY credits / 1M
Related variants · 4 rows · not ranked
These are special editions of the model (thinking, max, search, batch, long context, free, etc.). They are priced differently from the base model, so they are listed separately and not ranked. Names that only add an effort level such as low, high or nothinking are compared with the base model.
- claude-haiku-4-5-thinking (-thinking · thinking edition): 4 rows
- yapi.click · claude_neight · claude-haiku-4-5-thinking · Input 0.1824 / Output 0.912 CNY credits / 1M
- yapi.click · vip · claude-haiku-4-5-thinking · Input 0.48 / Output 2.4 CNY credits / 1M
- yapi.click · ccmax · claude-haiku-4-5-thinking · Input 0.48 / Output 2.4 CNY credits / 1M
- yapi.click · default · claude-haiku-4-5-thinking · Input 0.48 / Output 2.4 CNY credits / 1M
How this ranking works
All per-token prices: 93,968 prices from 854 sites (about 751 companies). 84,786 are ranked, from 838 sites (about 736 companies); 9,182 more are listed separately and not ranked. Prices collected up to 2026-10-24.
This model has 1304 recorded prices; 569 can be compared directly (554 ranked, 15 listed separately). Not comparable yet: price not parsed yet 352, tiered by rules (see Tiered prices) 148, ratio looks unset 106, new price under review; showing the previous one 45, display unit not confirmed 21, billed per request or another unit 15
4 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.
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.
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for Anthropic · claude-haiku-4-5?
api.everygpt.site, group "Claude-Kiro高缓存 (Claude-Kiro high cache)", 0.3 CNY credit per million total tokens, observed 2026-10-23. 230 sites have comparable prices.
What is the official price for Anthropic · claude-haiku-4-5?
Input 1, output 5 USD per million tokens, checked 2026-10-24. Lowest inference provider: DeepInfra, input 1, output 5 USD per million tokens.
How do I use Anthropic · claude-haiku-4-5 in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest Anthropic · claude-haiku-4-5 API to Claude Code for me". Install Skill →