FREE TOOL · BY APIDECK
LLM cost calculator for OpenAI, Claude, Gemini, Grok and DeepSeek. Enter your workload once and compare monthly token costs, with every assumption in view.
ILLUSTRATIVE EXAMPLE
10,000 requests × 5,000 input + 1,000 output tokens per request. Cache reads 0%; writes 0%.
 AnthropicClaude Haiku 5.5 | $10.00 | $0.001 | $5.00 | $0.00 | $0.00 | $5.00 |
|---|---|---|---|---|---|---|
 OpenAIGPT-6 Luna | $10.00 | $0.001 | $5.00 | $0.00 | $0.00 | $5.00 |
 DeepSeekDeepSeek V4.1 Flash 1017 Pricing detailsPeak rates. Off-peak rates are half these amounts; actual cost depends on request timing. | $27.00 | $0.0027 | $15.00 | $0.00 | $0.00 | $12.00 |
OpenAIGPT-6.1 Terra | $100.00 | $0.01 | $50.00 | $0.00 | $0.00 | $50.00 |
DeepSeekDeepSeek V4 Pro Pricing detailsPeak rates. Off-peak rates are half these amounts; actual cost depends on request timing. | $105.60 | $0.01056 | $66.00 | $0.00 | $0.00 | $39.60 |
 xAIGrok 4.7 Pricing detailsStandard us-east-1 text rates, below the 200K higher-context threshold. | $160.00 | $0.016 | $100.00 | $0.00 | $0.00 | $60.00 |
AnthropicClaude Sonnet 5.5 | $200.00 | $0.02 | $100.00 | $0.00 | $0.00 | $100.00 |
 GoogleGemini 4 Argon Pricing detailsStandard paid tier promotional rates through November 30, 2026. Implicit caching only. | $200.00 | $0.02 | $100.00 | $0.00 | $0.00 | $100.00 |
OpenAIGPT-6.1 Sol | $200.00 | $0.02 | $100.00 | $0.00 | $0.00 | $100.00 |
AnthropicClaude Opus 5.5 | $400.00 | $0.04 | $200.00 | $0.00 | $0.00 | $200.00 |
Shared links use current pricing when opened. Cost does not measure capability. Text API usage only; tools, taxes and other charges are excluded. Estimates use the same token counts across models, although tokenizers differ.
OTHER WAYS TO BUY
LLM routers may offer promotional credits, alternative provider routes or negotiated rates. Compare the final bill, including platform fees, minimum spend and the price after a promotion ends.
Check eligible models, new-customer restrictions and expiry dates.
Match the exact model, provider route and service tier before comparing.
Include credit-purchase fees, commitments and post-promotion pricing.
Building a model or router? Send us pricing corrections, new model listings, promotional credits or marketing partnership proposals. Pricing corrections do not require a commercial partnership.
Compare LLM routers →Submit an update or partnership ↗
No partner offers are applied to the estimates above. Submit a public offer with eligibility and expiry terms for review. Sponsored or affiliate placements will be labeled and will not change the direct-provider cost ranking. Sponsorship policy →
24 publisher-corroborated model listings. Search across model providers, with available models from OpenRouter’s top ten usage ranking first. Router prices are separate from the direct-provider comparison above.
Source: OpenRouter rankings, usage through October 25, 2026. Licensed under CC BY 4.0. Popularity reflects OpenRouter token traffic, not quality or global market share. Variants absent from the pricing catalog are not substituted.
24 matching models · showing 12
Check route pricing
An estimate is unavailable for this workload: check cache rates, token limits, additional charges or variable pricing at the source.
Pricing varies by tier or time.
Check model and route details ↗Explore provider API profile →
Publisher model evidence ↗ · Reviewed 2026-10-27. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
$4.293/ month
Token-only estimate using the submitted workload above. Free variants may have rate limits.
Explore provider API profile →
Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
$12.50/ month
Token-only estimate using the submitted workload above. Free variants may have rate limits.
Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
Check route pricing
An estimate is unavailable for this workload: check cache rates, token limits, additional charges or variable pricing at the source.
Pricing varies by tier or time.
Check model and route details ↗Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
Check route pricing
An estimate is unavailable for this workload: check cache rates, token limits, additional charges or variable pricing at the source.
Pricing varies by tier or time.
Check model and route details ↗Explore provider API profile →
Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
Check route pricing
An estimate is unavailable for this workload: check cache rates, token limits, additional charges or variable pricing at the source.
Explore provider API profile →
Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
$0.00/ month
Token-only estimate using the submitted workload above. Free variants may have rate limits.
Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
$17.495/ month
Token-only estimate using the submitted workload above. Free variants may have rate limits.
Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
Check route pricing
An estimate is unavailable for this workload: check cache rates, token limits, additional charges or variable pricing at the source.
Explore provider API profile →
Publisher model evidence ↗ · Reviewed 2026-10-27. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
Check route pricing
An estimate is unavailable for this workload: check cache rates, token limits, additional charges or variable pricing at the source.
Pricing varies by tier or time.
Check model and route details ↗Explore provider API profile →
Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
Check route pricing
An estimate is unavailable for this workload: check cache rates, token limits, additional charges or variable pricing at the source.
Explore provider API profile →
Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
Check route pricing
An estimate is unavailable for this workload: check cache rates, token limits, additional charges or variable pricing at the source.
Explore provider API profile →
Publisher model evidence ↗ · Reviewed 2026-10-26. Model existence is corroborated; router availability and prices are reported by OpenRouter, not runtime-tested.
444 imported listings are withheld pending publisher review; this does not mean they are fake. Pricing snapshot: 2026-10-26, from the OpenRouter Models API. Prices can vary by route and change over time. Fees, tools and taxes are excluded. Models with variable rates or additional declared charges do not receive a calculated total. Daily automated checks propose reviewed snapshot updates; this is not a live feed.
USD per million tokens. Standard direct-provider processing, within the calculator’s 100,000-token combined request scope. No batch or regional adjustments. Daily automated checks propose OpenAI and Claude updates for review. Google, xAI and DeepSeek prices are manually reviewed. This is a dated snapshot, not a live feed.
| Model | Input | Output | Cache read | Cache write | Publisher source |
|---|---|---|---|---|---|
| GPT-6.1 SolChecked 2026-10-26 | $2.00 | $10.00 | $0.10 | $2.5030 minutes | Check pricing ↗ |
| GPT-6.1 TerraChecked 2026-10-26 | $1.00 | $5.00 | $0.05 | $1.2530 minutes | Check pricing ↗ |
| GPT-6 LunaChecked 2026-10-26 | $0.10 | $0.50 | $0.01 | $0.12530 minutes | Check pricing ↗ |
| Claude Opus 5.5Checked 2026-10-26 | $4.00 | $20.00 | $0.20 | $5.005 minutes | Check pricing ↗ |
| Claude Sonnet 5.5Checked 2026-10-26 | $2.00 | $10.00 | $0.10 | $2.505 minutes | Check pricing ↗ |
| Claude Haiku 5.5Checked 2026-10-26 | $0.10 | $0.50 | $0.01 | $0.1255 minutes | Check pricing ↗ |
| Gemini 4 ArgonStandard paid tier promotional rates through November 30, 2026. Implicit caching only.Reviewed 2026-10-27 | $2.00 | $10.00 | $0.10 | Not modeled | Check pricing ↗ |
| Grok 4.7Standard us-east-1 text rates, below the 200K higher-context threshold.Reviewed 2026-10-27 | $2.00 | $6.00 | $0.50 | Not modeled | Check pricing ↗ |
| DeepSeek V4.1 Flash 1017Peak rates. Off-peak rates are half these amounts; actual cost depends on request timing.Reviewed 2026-10-27 | $0.30 | $1.20 | $0.006 | Not modeled | Check pricing ↗ |
| DeepSeek V4 ProPeak rates. Off-peak rates are half these amounts; actual cost depends on request timing.Reviewed 2026-10-27 | $1.32 | $3.96 | $0.044 | Not modeled | Check pricing ↗ |
Prices are a dated snapshot. Recheck the publisher source before committing a budget. Cache writes are included only when you allocate a share of input to them.
API-key setup guides from the Apideck team.
Monthly cost = requests × (uncached input tokens × input rate + cached tokens × cache-read rate + cache-write tokens × write rate + output tokens × output rate) ÷ 1,000,000.
Multiply monthly requests by the input and output tokens per request and their respective per-million-token rates. Split input tokens into uncached input, cache reads and cache writes when applicable, then add the four costs.
No. These are standard direct-provider text API estimates in USD. Chat subscriptions, taxes, tools, web searches, storage, images, audio, regional uplifts and negotiated discounts are excluded. Batch, fast and long-context pricing are not modeled.
No. This compares the cost of the same token workload, not quality, latency or success rate. Tokenizers differ across models, so use actual provider usage measurements for a more accurate comparison. Include conversation history, tool schemas and billable reasoning tokens in your estimates.
Cache reads replace part of the ordinary input charge. Cache writes use their own rate. This calculator uses 30-minute writes for the listed OpenAI models and 5-minute writes for Claude. Gemini, Grok and DeepSeek cache-write estimates are not modeled; selecting cache writes makes their estimates unavailable. Cache eligibility and hit rates depend on the provider; no cache savings are assumed by default.
This is a dated snapshot, not a live price feed. Daily automated checks propose OpenAI, Claude and router updates for review; other direct-provider prices are manually reviewed. Check the linked publisher pricing before budgeting. The calculator covers requests with at most 100,000 combined input and output tokens; provider token and output limits still apply.
