BURNLENSDashboard

LLM API pricing

134 models · 9 providers · all rates per million tokens, USD

A catalog date records when BurnLens refreshed its bundled rates. Only models with a linked provider source below are independently source-verified.

This is not a hand-maintained marketing table. It is the exact pricing data the BurnLens proxy bills every request from, generated from burnlens/cost/pricing_data in the open-source repo. When a rate changes there, this page changes with it.

Cache columns matter more than they look. A coding agent re-sends its whole context every turn, so on Anthropic-style billing 90–99% of prompt tokens are cache reads at a tenth of the input rate — pricing a run off the input column alone overstates it by an order of magnitude.

What will it actually cost?

Most token calculators price the whole prompt at the input rate. Coding agents re-send their context every turn, so almost all of it is a cache read at a fraction of that rate — and the naive answer comes out several times too high. This one bills the way the provider does.

Total$37.80
Per request$0.09
Priced the naive way$135.00
  • 54,000 of the 60,000 prompt tokens bill at the cache-read rate.
  • Anthropic-style billing reports cache reads separately from the prompt count.
  • Steady state only — the turn that first populates the cache pays a one-off write premium, and reasoning, audio and per-image fees are not modelled.

Anthropic

anthropic · 23 models · catalog updated 2026-08-10

ModelInputOutputCache readCache writeNotesSource
claude-2.0$8.00$24.00———Not source-verified
claude-2.1$8.00$24.00———Not source-verified
claude-3-5-haiku-20241022$0.80$4.00$0.08$1.00—Not source-verified
claude-3-5-sonnet-20240620$3.00$15.00$0.30$3.75—Not source-verified
claude-3-5-sonnet-20241022$3.00$15.00$0.30$3.75—Not source-verified
claude-3-7-sonnet-20250219$3.00$15.00$0.30$3.75—Not source-verified
claude-3-haiku-20240307$0.25$1.25$0.03$0.30—Not source-verified
claude-3-opus-20240229$15.00$75.00$1.50$18.75—Not source-verified
claude-3-sonnet-20240229$3.00$15.00———Not source-verified
claude-fable-5$10.00$50.00$1.00$12.50—Not source-verified
claude-haiku-4-5$1.00$5.00$0.10$1.25—Not source-verified
claude-mythos-5$10.00$50.00$1.00$12.50—Not source-verified
claude-opus-4$15.00$75.00$1.50$18.75—Not source-verified
claude-opus-4-1$15.00$75.00$1.50$18.75—Not source-verified
claude-opus-4-5$5.00$25.00$0.50$6.25—Not source-verified
claude-opus-4-6$5.00$25.00$0.50$6.25—Not source-verified
claude-opus-4-7$5.00$25.00$0.50$6.25—Not source-verified
claude-opus-4-8$5.00$25.00$0.50$6.25—Not source-verified
claude-opus-5$5.00$25.00$0.50$6.25—Not source-verified
claude-sonnet-4$3.00$15.00$0.30$3.75—Not source-verified
claude-sonnet-4-5$3.00$15.00$0.30$3.75—Not source-verified
claude-sonnet-4-6$3.00$15.00$0.30$3.75—Not source-verified
claude-sonnet-5$2.00$10.00$0.20$2.50—Provider verified · effective 2026-08-10

AWS Bedrock

bedrock · 10 models · catalog updated 2026-07-18

ModelInputOutputCache readCache writeNotesSource
anthropic.claude-fable-5$10.00$50.00$1.00$12.50—Not source-verified
anthropic.claude-haiku-4-5$1.00$5.00$0.10$1.25—Not source-verified
anthropic.claude-opus-4-5$5.00$25.00$0.50$6.25—Not source-verified
anthropic.claude-opus-4-6$5.00$25.00$0.50$6.25—Not source-verified
anthropic.claude-opus-4-7$5.00$25.00$0.50$6.25—Not source-verified
anthropic.claude-opus-4-8$5.00$25.00$0.50$6.25—Not source-verified
anthropic.claude-sonnet-4$3.00$15.00$0.30$3.75—Not source-verified
anthropic.claude-sonnet-4-5$3.00$15.00$0.30$3.75—Not source-verified
anthropic.claude-sonnet-4-6$3.00$15.00$0.30$3.75—Not source-verified
anthropic.claude-sonnet-5$2.00$10.00$0.20$2.50from 2026-09-01: $3.00 in / $15.00 outNot source-verified

DeepSeek

deepseek · 4 models · catalog updated 2026-07-20

ModelInputOutputCache readCache writeNotesSource
deepseek-chat$0.14$0.28$0.0028——Not source-verified
deepseek-reasoner$0.14$0.28$0.0028——Not source-verified
deepseek-v4-flash$0.14$0.28$0.0028——Not source-verified
deepseek-v4-pro$0.435$0.87$0.0036——Not source-verified

Google

google · 13 models · catalog updated 2026-07-23

ModelInputOutputCache readCache writeNotesSource
gemini-1.0-pro$0.50$1.50———Not source-verified
gemini-1.5-flash$0.075$0.30———Not source-verified
gemini-1.5-flash-8b$0.0375$0.15———Not source-verified
gemini-1.5-pro$1.25$5.00———Not source-verified
gemini-2.0-flash$0.10$0.40———Not source-verified
gemini-2.0-flash-lite$0.075$0.30———Not source-verified
gemini-2.5-flash$0.30$2.50———Not source-verified
gemini-2.5-flash-lite$0.10$0.40———Not source-verified
gemini-2.5-pro$1.25$10.00——over 200k ctx: $2.50 in / $15.00 outNot source-verified
gemini-3-flash-preview$0.50$3.00———Not source-verified
gemini-3.1-flash-lite$0.25$1.50———Not source-verified
gemini-3.1-pro-preview$2.00$12.00——over 200k ctx: $4.00 in / $18.00 outNot source-verified
gemini-3.5-flash$1.50$9.00$0.15——Not source-verified

Groq

groq · 7 models · catalog updated 2026-07-17

ModelInputOutputCache readCache writeNotesSource
llama-3.1-8b-instant$0.05$0.08———Not source-verified
llama-3.3-70b-versatile$0.59$0.79———Not source-verified
moonshotai/kimi-k2-instruct$1.00$3.00———Not source-verified
openai/gpt-oss-120b$0.15$0.75———Not source-verified
openai/gpt-oss-20b$0.075$0.30———Not source-verified
qwen/qwen3-32b$0.29$0.59———Not source-verified
qwen/qwen3.6-27b$0.60$3.00———Not source-verified

Mistral

mistral · 11 models · catalog updated 2026-07-17

ModelInputOutputCache readCache writeNotesSource
codestral-latest$0.30$0.90———Not source-verified
magistral-medium-latest$2.00$5.00———Not source-verified
ministral-3b-latest$0.04$0.04———Not source-verified
ministral-8b-latest$0.10$0.10———Not source-verified
mistral-large-2512$0.50$1.50———Not source-verified
mistral-large-latest$0.50$1.50———Not source-verified
mistral-medium-3-5$1.50$7.50———Not source-verified
mistral-medium-latest$1.50$7.50———Not source-verified
mistral-small-2603$0.15$0.60———Not source-verified
mistral-small-latest$0.15$0.60———Not source-verified
open-mistral-nemo$0.15$0.15———Not source-verified

OpenAI

openai · 39 models · catalog updated 2026-09-27

ModelInputOutputCache readCache writeNotesSource
gpt-3.5-turbo$0.50$1.50———Not source-verified
gpt-3.5-turbo-instruct$1.50$2.00———Not source-verified
gpt-4$30.00$60.00———Not source-verified
gpt-4-32k$60.00$120.00———Not source-verified
gpt-4-turbo$10.00$30.00———Not source-verified
gpt-4-turbo-preview$10.00$30.00———Not source-verified
gpt-4.1$2.00$8.00$0.50——Not source-verified
gpt-4.1-mini$0.40$1.60$0.10——Not source-verified
gpt-4.1-nano$0.10$0.40$0.025——Not source-verified
gpt-4o$2.50$10.00$1.25——Not source-verified
gpt-4o-audio-preview$2.50$10.00——audio: $40.00 in / $80.00 outNot source-verified
gpt-4o-mini$0.15$0.60$0.075——Not source-verified
gpt-4o-mini-audio-preview$0.15$0.60——audio: $10.00 in / $20.00 outNot source-verified
gpt-4o-realtime-preview$5.00$20.00$2.50—audio: $40.00 in / $80.00 outNot source-verified
gpt-5$1.25$10.00$0.125——Not source-verified
gpt-5-codex$1.25$10.00$0.125——Not source-verified
gpt-5-mini$0.25$2.00$0.025——Not source-verified
gpt-5-nano$0.05$0.40$0.005——Not source-verified
gpt-5.2$1.75$14.00$0.175——Not source-verified
gpt-5.2-pro$21.00$168.00——reasoning: $168.00Not source-verified
gpt-5.4$2.50$15.00$0.25——Not source-verified
gpt-5.4-mini$0.75$4.50$0.075——Not source-verified
gpt-5.4-nano$0.20$1.25$0.02——Not source-verified
gpt-5.4-pro$30.00$180.00——reasoning: $180.00Not source-verified
gpt-5.5$5.00$30.00$0.50——Not source-verified
gpt-5.5-pro$30.00$180.00——reasoning: $180.00Not source-verified
gpt-5.6$4.00$20.00$0.40$5.00over 272k ctx: $8.00 in / $30.00 outProvider verified · effective 2026-08-21
gpt-5.6-luna$0.20$1.20$0.02$0.25over 272k ctx: $0.40 in / $1.80 outProvider verified · effective 2026-07-30
gpt-5.6-sol$4.00$20.00$0.40$5.00over 272k ctx: $8.00 in / $30.00 outProvider verified · effective 2026-08-21
gpt-5.6-terra$2.00$12.00$0.20$2.50over 272k ctx: $4.00 in / $18.00 outProvider verified · effective 2026-07-30
gpt-realtime-2.1$4.00$24.00$0.40—audio: $32.00 in / $64.00 outNot source-verified
gpt-realtime-2.1-mini$0.60$2.40$0.30—audio: $10.00 in / $20.00 outNot source-verified
o1$15.00$60.00$7.50—reasoning: $60.00Not source-verified
o1-mini$1.10$4.40$0.55—reasoning: $4.40Not source-verified
o1-preview$15.00$60.00$7.50—reasoning: $60.00Not source-verified
o3$2.00$8.00$0.50—reasoning: $8.00Not source-verified
o3-mini$1.10$4.40$0.55—reasoning: $4.40Not source-verified
o3-pro$20.00$80.00——reasoning: $80.00Not source-verified
o4-mini$1.10$4.40$0.275—reasoning: $4.40Not source-verified

Together AI

together · 26 models · catalog updated 2026-07-17

ModelInputOutputCache readCache writeNotesSource
LiquidAI/LFM2.5-8B-A1B$0.03$0.12———Not source-verified
MiniMaxAI/MiniMax-M2.7$0.30$1.20$0.06——Not source-verified
MiniMaxAI/MiniMax-M3$0.30$1.20$0.06——Not source-verified
Qwen/Qwen2.5-72B-Instruct-Turbo$1.20$1.20———Not source-verified
Qwen/Qwen2.5-7B-Instruct-Turbo$0.30$0.30———Not source-verified
Qwen/Qwen3.5-9B$0.17$0.25———Not source-verified
Qwen/Qwen3.6-Plus$0.50$3.00———Not source-verified
Qwen/Qwen3.7-Max$1.25$3.75———Not source-verified
Qwen/Qwen3.7-Plus$0.32$1.28———Not source-verified
deepcogito/cogito-v2-1-671b$1.25$1.25———Not source-verified
deepseek-ai/DeepSeek-R1$3.00$7.00———Not source-verified
deepseek-ai/DeepSeek-V3$1.25$1.25———Not source-verified
deepseek-ai/DeepSeek-V4-Pro$1.74$3.48$0.20——Not source-verified
google/gemma-3n-E4B-it$0.06$0.12———Not source-verified
google/gemma-4-31B-it$0.39$0.97———Not source-verified
meta-llama/Llama-3.3-70B-Instruct-Turbo$1.04$1.04———Not source-verified
meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo$3.50$3.50———Not source-verified
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo$0.18$0.18———Not source-verified
moonshotai/Kimi-K2.6$1.20$4.50$0.20——Not source-verified
moonshotai/Kimi-K2.7-Code$0.95$4.00$0.19——Not source-verified
nvidia/nemotron-3-ultra-550b-a55b$0.60$3.60$0.20——Not source-verified
openai/gpt-oss-120b$0.15$0.60———Not source-verified
openai/gpt-oss-20b$0.05$0.20———Not source-verified
pearl-ai/gemma-4-31b-it$0.28$0.86———Not source-verified
thinkingmachines/Inkling$1.00$4.05$0.17——Not source-verified
zai-org/GLM-5.2$1.40$4.40$0.26——Not source-verified

xAI

xai · 1 models · catalog updated 2026-07-20

ModelInputOutputCache readCache writeNotesSource
grok-4.5$2.00$6.00———Not source-verified

Reading the table

  • Cache read / cache write — prompt-cache rates. An em dash means the provider does not bill caching separately.
  • OpenAI and Google fold cached tokens into the input count; Anthropic reports them separately. Adding cache reads to input tokens on an OpenAI response double-counts them.
  • over Nk ctx — a long-context tier. The higher rate applies to the whole request once the prompt crosses the threshold, not just the tokens above it.
  • from YYYY-MM-DD — a rate change the provider has already announced. The proxy switches on that date with no upgrade.
  • Bedrock keys omit the geo prefix (us., eu., apac., global.). These are global cross-region rates; regional inference runs roughly 10% higher.

Stop reading prices, start measuring them

A price list tells you the rate. It does not tell you what your agents actually spend, or which repo, PR, or developer spent it. BurnLens is a local proxy that does — pip install burnlens, one environment variable.

Read the docs · Scan existing agent logs · See the dashboard