Anthropic
Claude Fable 5
claude-fable-5StandardGlobal routing
- Input
- $10
- Cache read
- $1
- Output
- $50
- Context
- 1M
Calculate model costs without flattening the billing rules.
Compare 52 official-source rate cards across nine providers. Then model requests, tokens, warm cache reads, and quality pass rates against the exact model tier.
Snapshot verified 2026-08-16 · USD per one million tokens · consumer chat subscriptions excluded
PROVIDER CALCULATORS
Start with the billing surface you use.
OpenAI3 models6 dated rate cards
Compare current GPT API input, cached-input, output, context-tier, and regional rate cards without mixing API billing with ChatGPT plan quotas.
Open calculator →Anthropic5 models5 dated rate cardsCalculate Claude API costs from official input, cache-read, cache-write, output, context-window, and routing details.
Open calculator →Google6 models7 dated rate cardsCompare Gemini API model tiers, cached-input rates, output rates, introductory dates, and explicit cache-storage caveats.
Open calculator →xAI5 models7 dated rate cardsEstimate Grok API spend from current official input, cached-input, output, context-window, and regional price scopes.
Open calculator →DeepSeek2 models6 dated rate cardsCompare DeepSeek API token rates with effective dates and time-sensitive pricing rules kept visible.
Open calculator →Kimi / Moonshot AI4 models4 dated rate cardsCalculate Kimi API costs across official model, context, cache, and batch pricing scopes.
Open calculator →Qwen / Alibaba Cloud3 models6 dated rate cardsCompare Qwen API rates while preserving region, input tier, cache mode, and context constraints.
Open calculator →Mistral AI7 models7 dated rate cardsEstimate Mistral API input and output token costs from a dated, official-source pricing snapshot.
Open calculator →Cohere4 models4 dated rate cardsCompare Cohere Command API input, output, context, and documented pricing scopes with source provenance attached.
Open calculator →PAIRWISE API COSTS
Put two providers on one workload.
Choose exact model tiers, reuse the same request and token inputs, then set separate quality pass rates before calling either side cheaper.
OpenAI / AnthropicOpenAI vs Anthropic API pricing
Compare current GPT and Claude API rate cards on the same request volume, token counts, cache-read share, and quality-pass assumptions.
Open comparison →Google / xAIGemini vs Grok API pricingCompare Google Gemini and xAI Grok API token costs with model, context, cache, region, and quality assumptions kept visible.
Open comparison →DeepSeek / Kimi / Moonshot AIDeepSeek vs Kimi API pricingCompare DeepSeek and Moonshot Kimi API spend without hiding effective dates, cache modes, context tiers, or batch-only discounts.
Open comparison →Kimi / Moonshot AI / Qwen / Alibaba CloudKimi vs Qwen API pricingCompare Moonshot Kimi and Alibaba Qwen API token costs while preserving region, input band, context, cache, and execution-mode rules.
Open comparison →Mistral AI / CohereMistral vs Cohere API pricingCompare Mistral and Cohere API rates with the same workload and quality assumptions using dated, source-linked price cards.
Open comparison →ALL RATE CARDS
Search the current snapshot.
Keep context bands, regions, cache modes, and effective dates visible. A missing cache price is never treated as free.
| Provider / model | Price scope | Input USD / 1M | Cache read USD / 1M | Output USD / 1M | Context | Source |
|---|---|---|---|---|---|---|
AnthropicClaude Fable 5claude-fable-5 | StandardGlobal routing | $10 | $1 | $50 | 1M | Official ↗ |
AnthropicClaude Haiku 4.5claude-haiku-4-5 | StandardGlobal routing | $1 | $0.1 | $5 | 200K | Official ↗ |
AnthropicClaude Opus 5claude-opus-5 | StandardGlobal routing | $5 | $0.5 | $25 | 1M | Official ↗ |
AnthropicClaude Sonnet 4.6claude-sonnet-4-6 | StandardGlobal routing | $3 | $0.3 | $15 | 1M | Official ↗ |
AnthropicClaude Sonnet 5claude-sonnet-5 | StandardGlobal routing | $2 | $0.2 | $10 | 1M | Official ↗ |
CohereCommand Acommand-a-03-2025 | Production pay-as-you-goGlobal | $2.50 | — | $10 | 256K | Official ↗ |
CohereCommand Rcommand-r-08-2024 | Production pay-as-you-goGlobal | $0.15 | — | $0.6 | — | Official ↗ |
CohereCommand R+command-r-plus-08-2024 | Production pay-as-you-goGlobal | $2.50 | — | $10 | — | Official ↗ |
CohereCommand R7Bcommand-r7b-12-2024 | Production pay-as-you-goGlobal | $0.037 | — | $0.15 | — | Official ↗ |
DeepSeekDeepSeek V4 Flashdeepseek-v4-flash | Off-peak · scheduled UTC windowsGlobalFrom 16 Aug 2026 | $0.22 | $0.007 | $0.66 | 1M | Official ↗ |
DeepSeekDeepSeek V4 Flashdeepseek-v4-flash | Peak · 01:00–04:00 and 06:00–10:00 UTCGlobalFrom 16 Aug 2026 | $0.44 | $0.014 | $1.32 | 1M | Official ↗ |
DeepSeekDeepSeek V4 Flashdeepseek-v4-flash | Standard · through 2026-08-16 16:00 UTCGlobalThrough 16 Aug 2026 | $0.14 | $0.0028 | $0.28 | 1M | Official ↗ |
DeepSeekDeepSeek V4 Prodeepseek-v4-pro | Off-peak · scheduled UTC windowsGlobalFrom 16 Aug 2026 | $0.66 | $0.022 | $1.98 | 1M | Official ↗ |
DeepSeekDeepSeek V4 Prodeepseek-v4-pro | Peak · 01:00–04:00 and 06:00–10:00 UTCGlobalFrom 16 Aug 2026 | $1.32 | $0.044 | $3.96 | 1M | Official ↗ |
DeepSeekDeepSeek V4 Prodeepseek-v4-pro | Standard · through 2026-08-16 16:00 UTCGlobalThrough 16 Aug 2026 | $0.435 | $0.003625 | $0.87 | 1M | Official ↗ |
GoogleGemini 3.1 Flash-Litegemini-3.1-flash-lite | Developer API · Standard · text/image/videoGemini Developer API | $0.25 | $0.025 | $1.50 | — | Official ↗ |
GoogleGemini 3.1 Pro Previewgemini-3.1-pro-preview | Developer API · Standard · over 200K promptGemini Developer API | $4 | $0.4 | $18 | — | Official ↗ |
GoogleGemini 3.1 Pro Previewgemini-3.1-pro-preview | Developer API · Standard · up to 200K promptGemini Developer API | $2 | $0.2 | $12 | — | Official ↗ |
GoogleGemini 3.5 Flashgemini-3.5-flash | Developer API · StandardGemini Developer API | $1.50 | $0.15 | $9 | — | Official ↗ |
GoogleGemini 3.5 Flash-Litegemini-3.5-flash-lite | Developer API · StandardGemini Developer API | $0.3 | $0.03 | $2.50 | — | Official ↗ |
GoogleGemini 3.6 Flashgemini-3.6-flash | Developer API · Standard · introductoryGemini Developer APIThrough 31 Dec 2026 | $0.75 | $0.075 | $3.75 | — | Official ↗ |
GoogleGemini 3.7 Flashgemini-3.7-flash | Developer API · Standard · introductoryGemini Developer APIThrough 31 Dec 2026 | $0.75 | $0.075 | $3.75 | — | Official ↗ |
Kimi / Moonshot AIKimi K2.6kimi-k2.6 | RealtimeGlobal | $0.95 | $0.16 | $4 | 262K | Official ↗ |
Kimi / Moonshot AIKimi K2.7 Code Highspeedkimi-k2.7-code-highspeed | Realtime · high-speed tierGlobal | $1.90 | $0.38 | $8 | 262K | Official ↗ |
Kimi / Moonshot AIKimi K2.7 Codekimi-k2.7-code | RealtimeGlobal | $0.95 | $0.19 | $4 | 262K | Official ↗ |
Kimi / Moonshot AIKimi K3kimi-k3 | RealtimeGlobal | $3 | $0.3 | $15 | 1.05M | Official ↗ |
Mistral AICodestralcodestral-latest | StandardGlobal | $0.3 | $0.03 | $0.9 | — | Official ↗ |
Mistral AIMinistral 3 14Bministral-14b-latest | StandardGlobal | $0.2 | $0.02 | $0.2 | — | Official ↗ |
Mistral AIMinistral 3 3Bministral-3b-latest | StandardGlobal | $0.1 | $0.01 | $0.1 | — | Official ↗ |
Mistral AIMinistral 3 8Bministral-8b-latest | StandardGlobal | $0.15 | $0.015 | $0.15 | — | Official ↗ |
Mistral AIMistral Large 3mistral-large-latest | StandardGlobal | $0.5 | $0.05 | $1.50 | — | Official ↗ |
Mistral AIMistral Medium 3.5mistral-medium-latest | StandardGlobal | $1.50 | $0.15 | $7.50 | — | Official ↗ |
Mistral AIMistral Small 4mistral-small-latest | StandardGlobal | $0.15 | $0.015 | $0.6 | — | Official ↗ |
OpenAIGPT-5.6 Lunagpt-5.6-luna | Standard · over 272K inputGlobal | $0.4 | $0.04 | $1.80 | 1.05M | Official ↗ |
OpenAIGPT-5.6 Lunagpt-5.6-luna | Standard · up to 272K inputGlobal | $0.2 | $0.02 | $1.20 | 1.05M | Official ↗ |
OpenAIGPT-5.6 Solgpt-5.6-sol | Standard · over 272K inputGlobal | $10 | $1 | $45 | 1.05M | Official ↗ |
OpenAIGPT-5.6 Solgpt-5.6-sol | Standard · up to 272K inputGlobal | $5 | $0.5 | $30 | 1.05M | Official ↗ |
OpenAIGPT-5.6 Terragpt-5.6-terra | Standard · over 272K inputGlobal | $4 | $0.4 | $18 | 1.05M | Official ↗ |
OpenAIGPT-5.6 Terragpt-5.6-terra | Standard · up to 272K inputGlobal | $2 | $0.2 | $12 | 1.05M | Official ↗ |
Qwen / Alibaba CloudQwen 3.7 Flashqwen3.7-flash | Beijing · 256K–1M inputChina Beijing | $0.165 | $0.033 | $0.66 | 1M | Official ↗ |
Qwen / Alibaba CloudQwen 3.7 Flashqwen3.7-flash | Beijing · 32K–256K inputChina Beijing | $0.083 | $0.017 | $0.33 | 1M | Official ↗ |
Qwen / Alibaba CloudQwen 3.7 Flashqwen3.7-flash | Beijing · up to 32K inputChina Beijing | $0.028 | $0.006 | $0.11 | 1M | Official ↗ |
Qwen / Alibaba CloudQwen 3.7 Maxqwen3.7-max | Global scope · up to 1M inputUS Virginia · Global deployment | $1.65 | $0.33 | $4.95 | 1M | Official ↗ |
Qwen / Alibaba CloudQwen 3.7 Plusqwen3.7-plus | Global scope · 256K–1M inputUS Virginia · Global deployment | $0.826 | $0.166 | $3.30 | 1M | Official ↗ |
Qwen / Alibaba CloudQwen 3.7 Plusqwen3.7-plus | Global scope · up to 256K inputUS Virginia · Global deployment | $0.276 | $0.056 | $1.10 | 1M | Official ↗ |
xAIGrok 4.20 Reasoninggrok-4.20-0309-reasoning | Standard · below 200K promptxAI direct API | $1.25 | $0.2 | $2.50 | 1M | Official ↗ |
xAIGrok 4.3grok-4.3 | Standard · 200K+ promptxAI direct API | $2.50 | $0.4 | $5 | 1M | Official ↗ |
xAIGrok 4.3grok-4.3 | Standard · below 200K promptxAI direct API | $1.25 | $0.2 | $2.50 | 1M | Official ↗ |
xAIGrok 4.5grok-4.5 | Standard · below 200K promptxAI direct API | $2 | $0.3 | $6 | 500K | Official ↗ |
xAIGrok 4.6grok-4.6 | Standard · 200K+ promptxAI direct API | $4 | $1 | $12 | 500K | Official ↗ |
xAIGrok 4.6grok-4.6 | Standard · below 200K promptxAI direct API | $2 | $0.5 | $6 | 500K | Official ↗ |
xAIGrok Build 0.1grok-build-0.1 | Standard · below 200K promptxAI direct API | $1 | $0.2 | $2 | 256K | Official ↗ |
Rates in USD per 1M tokens
Anthropic
Claude Haiku 4.5
claude-haiku-4-5StandardGlobal routing
- Input
- $1
- Cache read
- $0.1
- Output
- $5
- Context
- 200K
Anthropic
Claude Opus 5
claude-opus-5StandardGlobal routing
- Input
- $5
- Cache read
- $0.5
- Output
- $25
- Context
- 1M
Anthropic
Claude Sonnet 4.6
claude-sonnet-4-6StandardGlobal routing
- Input
- $3
- Cache read
- $0.3
- Output
- $15
- Context
- 1M
Anthropic
Claude Sonnet 5
claude-sonnet-5StandardGlobal routing
- Input
- $2
- Cache read
- $0.2
- Output
- $10
- Context
- 1M
Cohere
Command A
command-a-03-2025Production pay-as-you-goGlobal
- Input
- $2.50
- Cache read
- —
- Output
- $10
- Context
- 256K
Cohere
Command R
command-r-08-2024Production pay-as-you-goGlobal
- Input
- $0.15
- Cache read
- —
- Output
- $0.6
- Context
- —
Cohere
Command R+
command-r-plus-08-2024Production pay-as-you-goGlobal
- Input
- $2.50
- Cache read
- —
- Output
- $10
- Context
- —
Cohere
Command R7B
command-r7b-12-2024Production pay-as-you-goGlobal
- Input
- $0.037
- Cache read
- —
- Output
- $0.15
- Context
- —
DeepSeek
DeepSeek V4 Flash
deepseek-v4-flashOff-peak · scheduled UTC windowsGlobal
- Input
- $0.22
- Cache read
- $0.007
- Output
- $0.66
- Context
- 1M
DeepSeek
DeepSeek V4 Flash
deepseek-v4-flashPeak · 01:00–04:00 and 06:00–10:00 UTCGlobal
- Input
- $0.44
- Cache read
- $0.014
- Output
- $1.32
- Context
- 1M
DeepSeek
DeepSeek V4 Flash
deepseek-v4-flashStandard · through 2026-08-16 16:00 UTCGlobal
- Input
- $0.14
- Cache read
- $0.0028
- Output
- $0.28
- Context
- 1M
DeepSeek
DeepSeek V4 Pro
deepseek-v4-proOff-peak · scheduled UTC windowsGlobal
- Input
- $0.66
- Cache read
- $0.022
- Output
- $1.98
- Context
- 1M
DeepSeek
DeepSeek V4 Pro
deepseek-v4-proPeak · 01:00–04:00 and 06:00–10:00 UTCGlobal
- Input
- $1.32
- Cache read
- $0.044
- Output
- $3.96
- Context
- 1M
DeepSeek
DeepSeek V4 Pro
deepseek-v4-proStandard · through 2026-08-16 16:00 UTCGlobal
- Input
- $0.435
- Cache read
- $0.003625
- Output
- $0.87
- Context
- 1M
Google
Gemini 3.1 Flash-Lite
gemini-3.1-flash-liteDeveloper API · Standard · text/image/videoGemini Developer API
- Input
- $0.25
- Cache read
- $0.025
- Output
- $1.50
- Context
- —
Google
Gemini 3.1 Pro Preview
gemini-3.1-pro-previewDeveloper API · Standard · over 200K promptGemini Developer API
- Input
- $4
- Cache read
- $0.4
- Output
- $18
- Context
- —
Google
Gemini 3.1 Pro Preview
gemini-3.1-pro-previewDeveloper API · Standard · up to 200K promptGemini Developer API
- Input
- $2
- Cache read
- $0.2
- Output
- $12
- Context
- —
Google
Gemini 3.5 Flash
gemini-3.5-flashDeveloper API · StandardGemini Developer API
- Input
- $1.50
- Cache read
- $0.15
- Output
- $9
- Context
- —
Google
Gemini 3.5 Flash-Lite
gemini-3.5-flash-liteDeveloper API · StandardGemini Developer API
- Input
- $0.3
- Cache read
- $0.03
- Output
- $2.50
- Context
- —
Google
Gemini 3.6 Flash
gemini-3.6-flashDeveloper API · Standard · introductoryGemini Developer API
- Input
- $0.75
- Cache read
- $0.075
- Output
- $3.75
- Context
- —
Google
Gemini 3.7 Flash
gemini-3.7-flashDeveloper API · Standard · introductoryGemini Developer API
- Input
- $0.75
- Cache read
- $0.075
- Output
- $3.75
- Context
- —
Kimi / Moonshot AI
Kimi K2.6
kimi-k2.6RealtimeGlobal
- Input
- $0.95
- Cache read
- $0.16
- Output
- $4
- Context
- 262K
Kimi / Moonshot AI
Kimi K2.7 Code Highspeed
kimi-k2.7-code-highspeedRealtime · high-speed tierGlobal
- Input
- $1.90
- Cache read
- $0.38
- Output
- $8
- Context
- 262K
Kimi / Moonshot AI
Kimi K2.7 Code
kimi-k2.7-codeRealtimeGlobal
- Input
- $0.95
- Cache read
- $0.19
- Output
- $4
- Context
- 262K
Kimi / Moonshot AI
Kimi K3
kimi-k3RealtimeGlobal
- Input
- $3
- Cache read
- $0.3
- Output
- $15
- Context
- 1.05M
Mistral AI
Codestral
codestral-latestStandardGlobal
- Input
- $0.3
- Cache read
- $0.03
- Output
- $0.9
- Context
- —
Mistral AI
Ministral 3 14B
ministral-14b-latestStandardGlobal
- Input
- $0.2
- Cache read
- $0.02
- Output
- $0.2
- Context
- —
Mistral AI
Ministral 3 3B
ministral-3b-latestStandardGlobal
- Input
- $0.1
- Cache read
- $0.01
- Output
- $0.1
- Context
- —
Mistral AI
Ministral 3 8B
ministral-8b-latestStandardGlobal
- Input
- $0.15
- Cache read
- $0.015
- Output
- $0.15
- Context
- —
Mistral AI
Mistral Large 3
mistral-large-latestStandardGlobal
- Input
- $0.5
- Cache read
- $0.05
- Output
- $1.50
- Context
- —
Mistral AI
Mistral Medium 3.5
mistral-medium-latestStandardGlobal
- Input
- $1.50
- Cache read
- $0.15
- Output
- $7.50
- Context
- —
Mistral AI
Mistral Small 4
mistral-small-latestStandardGlobal
- Input
- $0.15
- Cache read
- $0.015
- Output
- $0.6
- Context
- —
OpenAI
GPT-5.6 Luna
gpt-5.6-lunaStandard · over 272K inputGlobal
- Input
- $0.4
- Cache read
- $0.04
- Output
- $1.80
- Context
- 1.05M
OpenAI
GPT-5.6 Luna
gpt-5.6-lunaStandard · up to 272K inputGlobal
- Input
- $0.2
- Cache read
- $0.02
- Output
- $1.20
- Context
- 1.05M
OpenAI
GPT-5.6 Sol
gpt-5.6-solStandard · over 272K inputGlobal
- Input
- $10
- Cache read
- $1
- Output
- $45
- Context
- 1.05M
OpenAI
GPT-5.6 Sol
gpt-5.6-solStandard · up to 272K inputGlobal
- Input
- $5
- Cache read
- $0.5
- Output
- $30
- Context
- 1.05M
OpenAI
GPT-5.6 Terra
gpt-5.6-terraStandard · over 272K inputGlobal
- Input
- $4
- Cache read
- $0.4
- Output
- $18
- Context
- 1.05M
OpenAI
GPT-5.6 Terra
gpt-5.6-terraStandard · up to 272K inputGlobal
- Input
- $2
- Cache read
- $0.2
- Output
- $12
- Context
- 1.05M
Qwen / Alibaba Cloud
Qwen 3.7 Flash
qwen3.7-flashBeijing · 256K–1M inputChina Beijing
- Input
- $0.165
- Cache read
- $0.033
- Output
- $0.66
- Context
- 1M
Qwen / Alibaba Cloud
Qwen 3.7 Flash
qwen3.7-flashBeijing · 32K–256K inputChina Beijing
- Input
- $0.083
- Cache read
- $0.017
- Output
- $0.33
- Context
- 1M
Qwen / Alibaba Cloud
Qwen 3.7 Flash
qwen3.7-flashBeijing · up to 32K inputChina Beijing
- Input
- $0.028
- Cache read
- $0.006
- Output
- $0.11
- Context
- 1M
Qwen / Alibaba Cloud
Qwen 3.7 Max
qwen3.7-maxGlobal scope · up to 1M inputUS Virginia · Global deployment
- Input
- $1.65
- Cache read
- $0.33
- Output
- $4.95
- Context
- 1M
Qwen / Alibaba Cloud
Qwen 3.7 Plus
qwen3.7-plusGlobal scope · 256K–1M inputUS Virginia · Global deployment
- Input
- $0.826
- Cache read
- $0.166
- Output
- $3.30
- Context
- 1M
Qwen / Alibaba Cloud
Qwen 3.7 Plus
qwen3.7-plusGlobal scope · up to 256K inputUS Virginia · Global deployment
- Input
- $0.276
- Cache read
- $0.056
- Output
- $1.10
- Context
- 1M
xAI
Grok 4.20 Reasoning
grok-4.20-0309-reasoningStandard · below 200K promptxAI direct API
- Input
- $1.25
- Cache read
- $0.2
- Output
- $2.50
- Context
- 1M
xAI
Grok 4.3
grok-4.3Standard · 200K+ promptxAI direct API
- Input
- $2.50
- Cache read
- $0.4
- Output
- $5
- Context
- 1M
xAI
Grok 4.3
grok-4.3Standard · below 200K promptxAI direct API
- Input
- $1.25
- Cache read
- $0.2
- Output
- $2.50
- Context
- 1M
xAI
Grok 4.5
grok-4.5Standard · below 200K promptxAI direct API
- Input
- $2
- Cache read
- $0.3
- Output
- $6
- Context
- 500K
xAI
Grok 4.6
grok-4.6Standard · 200K+ promptxAI direct API
- Input
- $4
- Cache read
- $1
- Output
- $12
- Context
- 500K
xAI
Grok 4.6
grok-4.6Standard · below 200K promptxAI direct API
- Input
- $2
- Cache read
- $0.5
- Output
- $6
- Context
- 500K
xAI
Grok Build 0.1
grok-build-0.1Standard · below 200K promptxAI direct API
- Input
- $1
- Cache read
- $0.2
- Output
- $2
- Context
- 256K
USD per 1M tokens. Snapshot verified 2026-08-16. Cache writes, cache storage, tools, regions, and provider-specific thresholds may be billed separately.
A missing cache rate is shown as “—”, never treated as free. Consumer chat-plan quotas are not API prices.
WORKLOAD CALCULATOR
Turn rates into a monthly scenario.
Compare raw spend with cost per accepted answer and the candidate pass rate needed to break even. These remain estimates until a quality-gated test confirms them.
Estimated monthly API spend · OpenAI
GPT-5.6 TerraBefore · Standard · up to 272K input: $2 input · $0.2 cache read · $12 output / 1MAfter · Standard · up to 272K input: $2 input · $0.2 cache read · $12 output / 1MGlobal · price bands selected automatically from input size
Before$120.00
After$80.85
Potential saving: $39.15 (32.6%)
QUALITY-ADJUSTED COST
Before / accepted answer$0.013390% pass assumption
After / accepted answer$0.009585% pass assumption
Candidate break-even: 60.6% pass rate. Your scenario assumes 85%.
Warm cache-read scenario, not general ROI. It excludes cache writes/storage, tools, regional uplifts, retries, and quality failures. A dash means no published cache-read rate.
OpenAI API pricing ↗