AI token cost calculator
Priced from the same rate table a live proxy bills with — verified rates across 14 platforms, each with a provenance label and a retrieval date. Where no verified rate exists, you get a dash and the reason, never a guess. Share the URL and the calculation travels with it.
Cache tokens (optional)
Pick a model to price a call.
The full rate table
Standard-tier, global-endpoint, on-demand rates in USD per million tokens, as resolved on 2026-09-20 — time-windowed rates (promotions, scheduled steps) answer for that date. Regional and multi-region endpoint classes, batch discounts, long-context tiers and cache-write tiers are applied by the calculator above, per request. A dash is a rate that does not exist or was not verified — the same rule the dashboard follows.
| Platform | Model | Input $/MTok | Output $/MTok | Cache read $/MTok | Provenance | Verified |
|---|---|---|---|---|---|---|
| anthropic | claude-fable-5 | $10.00 | $50.00 | $1.00 | VERIFIED | 2026-09-11 |
| anthropic | claude-fable-5-1 | $10.00 | $50.00 | $0.25 | VERIFIED | 2026-09-11 |
| anthropic | claude-haiku-4-5-20251001 | $1.00 | $5.00 | $0.10 | VERIFIED | 2026-09-11 |
| anthropic | claude-opus-4-8 | $5.00 | $25.00 | $0.50 | VERIFIED | 2026-09-11 |
| anthropic | claude-opus-5 | $5.00 | $25.00 | $0.50 | VERIFIED | 2026-09-11 |
| anthropic | claude-sonnet-4-6 | $3.00 | $15.00 | $0.30 | VERIFIED | 2026-09-11 |
| anthropic | claude-sonnet-5 | $2.00 | $10.00 | $0.20 | VERIFIED | 2026-09-11 |
| baseten | moonshotai/Kimi-K3 | $3.00 | $15.00 | $0.30 | VERIFIED | 2026-09-11 |
| baseten | zai-org/GLM-5.3 | $1.40 | $4.40 | $0.14 | VERIFIED | 2026-09-11 |
| bedrock | anthropic.claude-fable-5 | — | — | — | CONTRACT_DESIGNATED | 2026-09-11 |
| bedrock | anthropic.claude-fable-5-1 | — | — | — | CONTRACT_DESIGNATED | 2026-09-11 |
| bedrock | anthropic.claude-haiku-4-5-20251001 | — | — | — | CONTRACT_DESIGNATED | 2026-09-11 |
| bedrock | anthropic.claude-opus-4-8 | — | — | — | VERIFIED | 2026-09-11 |
| bedrock | anthropic.claude-opus-5 | — | — | — | CONTRACT_DESIGNATED | 2026-09-11 |
| bedrock | anthropic.claude-sonnet-4-5-20250929 | — | — | — | VERIFIED | 2026-09-11 |
| bedrock | anthropic.claude-sonnet-4-6 | — | — | — | VERIFIED | 2026-09-11 |
| bedrock | anthropic.claude-sonnet-5 | — | — | — | CONTRACT_DESIGNATED | 2026-09-11 |
| bedrock | meta.llama3-3-70b-instruct | — | — | — | unverified | 2026-09-11 |
| cerebras | gpt-oss-120b | — | — | — | unverified | 2026-09-11 |
| deepseek | deepseek-flash | $0.15 | $0.60 | $0.003 | VERIFIED | 2026-09-11 |
| deepseek | deepseek-v4-pro | $0.66 | $1.98 | $0.022 | VERIFIED | 2026-09-11 |
| fireworks | fireworks/deepseek-v4-pro-0813 | $1.32 | $3.96 | $0.044 | VERIFIED | 2026-09-11 |
| fireworks | fireworks/glm-5p3 | $1.40 | $4.40 | $0.26 | VERIFIED | 2026-09-11 |
| fireworks | fireworks/kimi-k3 | $3.00 | $15.00 | $0.30 | VERIFIED | 2026-09-11 |
| gemini-3.6-flash | $0.75 | $3.75 | $0.075 | VERIFIED | 2026-09-11 | |
| gemini-3.7-flash | $0.75 | $3.75 | $0.075 | VERIFIED | 2026-09-11 | |
| gemini-3.8-flash | $0.75 | $3.75 | $0.075 | VERIFIED | 2026-09-11 | |
| groq | openai/gpt-oss-120b | $0.15 | $0.60 | — | VERIFIED | 2026-09-11 |
| groq | Qwen/Qwen3.8-27B | $0.80 | $4.00 | — | VERIFIED | 2026-09-11 |
| mistral | codestral-25-08 | $0.30 | $0.90 | $0.030 | INFERRED | 2026-09-11 |
| mistral | ministral-3-14b-25-12 | $0.20 | $0.20 | $0.020 | INFERRED | 2026-09-11 |
| mistral | ministral-3-3b-25-12 | $0.10 | $0.10 | $0.010 | INFERRED | 2026-09-11 |
| mistral | ministral-3-8b-25-12 | $0.15 | $0.15 | $0.015 | INFERRED | 2026-09-11 |
| mistral | mistral-large-3-25-12 | $0.50 | $1.50 | $0.050 | INFERRED | 2026-09-11 |
| mistral | mistral-medium-3-5-26-04 | $1.50 | $7.50 | $0.15 | INFERRED | 2026-09-11 |
| mistral | mistral-small-4-0-26-03 | $0.15 | $0.60 | $0.015 | INFERRED | 2026-09-11 |
| moonshot | kimi-k2.6 | $0.95 | $4.00 | $0.16 | VERIFIED | 2026-09-11 |
| moonshot | kimi-k3 | $3.00 | $15.00 | $0.30 | VERIFIED | 2026-09-11 |
| openai | chat-latest | $5.00 | $30.00 | $0.50 | VERIFIED | 2026-09-11 |
| openai | gpt-4o | $2.50 | $10.00 | $0.25 | INFERRED | 2026-07-14 |
| openai | gpt-4o-mini | $0.15 | $0.60 | $0.015 | INFERRED | 2026-07-14 |
| openai | gpt-5.3-codex | $1.75 | $14.00 | $0.17 | VERIFIED | 2026-09-11 |
| openai | gpt-5.6-cyber | $12.50 | $75.00 | $1.25 | VERIFIED | 2026-09-11 |
| openai | gpt-5.6-luna | $0.20 | $1.20 | $0.020 | VERIFIED | 2026-09-11 |
| openai | gpt-5.6-sol | $4.00 | $20.00 | $0.40 | VERIFIED | 2026-09-11 |
| openai | gpt-5.6-terra | $2.00 | $12.00 | $0.20 | VERIFIED | 2026-09-11 |
| openai | gpt-6-astra | $10.00 | $50.00 | $1.00 | VERIFIED | 2026-09-11 |
| together | deepseek-ai/DeepSeek-V4-Pro-0813 | $1.32 | $3.96 | $0.13 | VERIFIED | 2026-09-11 |
| together | meta-llama/Llama-3.3-70B-Instruct-Turbo | $1.04 | $1.04 | — | VERIFIED | 2026-09-11 |
| together | zai-org/GLM-5.3-Flash | $0.15 | $0.50 | $0.030 | VERIFIED | 2026-09-11 |
| vertex | claude-fable-5 | $10.00 | $50.00 | $1.00 | VERIFIED | 2026-09-11 |
| vertex | claude-fable-5-1 | $10.00 | $50.00 | $0.25 | VERIFIED | 2026-09-11 |
| vertex | claude-haiku-4-5@20251001 | $1.00 | $5.00 | $0.10 | VERIFIED | 2026-09-11 |
| vertex | claude-opus-4-5@20251101 | $5.00 | $25.00 | $0.50 | VERIFIED | 2026-09-11 |
| vertex | claude-opus-4-6 | $5.00 | $25.00 | $0.50 | VERIFIED | 2026-09-11 |
| vertex | claude-opus-4-7 | $5.00 | $25.00 | $0.50 | VERIFIED | 2026-09-11 |
| vertex | claude-opus-4-8 | $5.00 | $25.00 | $0.50 | VERIFIED | 2026-09-11 |
| vertex | claude-opus-5 | $5.00 | $25.00 | $0.50 | VERIFIED | 2026-09-11 |
| vertex | claude-sonnet-4-5@20250929 | $3.00 | $15.00 | $0.30 | VERIFIED | 2026-09-11 |
| vertex | claude-sonnet-4-6 | $3.00 | $15.00 | $0.30 | VERIFIED | 2026-09-11 |
| vertex | claude-sonnet-5 | $2.00 | $10.00 | $0.20 | VERIFIED | 2026-09-11 |
| xai | grok-4.3 | $1.25 | $2.50 | $0.20 | VERIFIED | 2026-09-11 |
| xai | grok-4.5 | $2.00 | $6.00 | $0.30 | VERIFIED | 2026-09-11 |
| xai | grok-4.6 | $2.00 | $6.00 | $0.50 | VERIFIED | 2026-09-11 |
| xai | grok-build-0.1 | $1.00 | $2.00 | $0.20 | VERIFIED | 2026-09-11 |
| zai | glm-5.3 | $1.40 | $4.40 | $0.26 | VERIFIED | 2026-09-11 |
| zai | glm-5.3-flash | $0.15 | $0.50 | $0.030 | VERIFIED | 2026-09-11 |
About these numbers
Where do these rates come from?
From the same rate table Vigil’s proxy prices live traffic with, code-generated into this site at build time and checked for staleness against the proxy source on every test run. Every row carries a provenance label and the date a human last verified it against the provider’s published pricing page. None of the figures on this page is hand-maintained.
Why does some model show a dash instead of a price?
Because no verified rate exists for it, and a plausible guess is worse than an honest gap. A model whose pricing page could not be read, a billing mode with no published treatment, or a timestamp outside every known validity window all resolve to “insufficient data” rather than to the nearest number.
Why do I have to pick a platform, not just a model?
The same model name is a different product on different platforms: Claude on Anthropic direct, on AWS Bedrock and on Google Vertex has three separately set rate tables, different endpoint classes with a +10% regional factor on the clouds, and three separate prompt caches. A price without a platform is not a price.
The proxy behind this table watches every call your agents make and applies these rates to your real traffic — monitoring is free. How the same model ends up with different prices per platform is written up in the pricing-key field guide.