This is the pricing matrix bundled with halton-meter v0.1.24. Cost
computation runs locally on the user’s machine using these rates.
Sourced from each provider’s public pricing page on the bundle date.
Methodology →
All figures are USD per million tokens. Cache and thinking columns are shown where the provider exposes them; an em dash means the provider does not bill that lane separately for the model. Gemini’s tiered surcharge for prompts above 200k tokens is shown on the row directly beneath the standard rate.
Anthropic
25 models · per million tokens
| Model | Input | Output | Cache read | Cache write | Thinking |
|---|---|---|---|---|---|
claude-3-5-haiku-20241022 | $0.8 | $4 | $0.08 | $1 | $4 |
claude-3-5-haiku-latest | $0.8 | $4 | $0.08 | $1 | $4 |
claude-3-7-sonnet-20250219 | $3 | $15 | $0.3 | $3.75 | $15 |
claude-3-7-sonnet-latest | $3 | $15 | $0.3 | $3.75 | $15 |
claude-3-haiku-20240307 | $0.25 | $1.25 | $0.03 | $0.3125 | $1.25 |
claude-3-opus-20240229 | $15 | $75 | $1.5 | $18.75 | $75 |
claude-3-opus-latest | $15 | $75 | $1.5 | $18.75 | $75 |
claude-haiku-4-5 | $1 | $5 | $0.1 | $1.25 | $5 |
claude-haiku-4-5-20251001 | $1 | $5 | $0.1 | $1.25 | $5 |
claude-opus-4-0 | $15 | $75 | $1.5 | $18.75 | $75 |
claude-opus-4-1 | $15 | $75 | $1.5 | $18.75 | $75 |
claude-opus-4-1-20250805 | $15 | $75 | $1.5 | $18.75 | $75 |
claude-opus-4-20250514 | $15 | $75 | $1.5 | $18.75 | $75 |
claude-opus-4-5 | $5 | $25 | $0.5 | $6.25 | $25 |
claude-opus-4-5-20251101 | $5 | $25 | $0.5 | $6.25 | $25 |
claude-opus-4-6 | $5 | $25 | $0.5 | $6.25 | $25 |
claude-opus-4-6-20251101 | $5 | $25 | $0.5 | $6.25 | $25 |
claude-opus-4-7 | $5 | $25 | $0.5 | $6.25 | $25 |
claude-opus-4-7-20260101 | $5 | $25 | $0.5 | $6.25 | $25 |
claude-sonnet-4-0 | $3 | $15 | $0.3 | $3.75 | $15 |
claude-sonnet-4-20250514 | $3 | $15 | $0.3 | $3.75 | $15 |
claude-sonnet-4-5 | $3 | $15 | $0.3 | $3.75 | $15 |
claude-sonnet-4-5-20250929 | $3 | $15 | $0.3 | $3.75 | $15 |
claude-sonnet-4-6 | $3 | $15 | $0.3 | $3.75 | $15 |
claude-sonnet-4-6-20251101 | $3 | $15 | $0.3 | $3.75 | $15 |
OpenAI
21 models · per million tokens
| Model | Input | Output | Cache read | Cache write | Thinking |
|---|---|---|---|---|---|
codex-auto-review | $0.4 | $1.6 | $0.1 | $0 | $1.6 |
codex-unknown | $2 | $8 | $0.5 | $0 | $8 |
gpt-3.5-turbo | $0.5 | $1.5 | $0 | $0 | $1.5 |
gpt-4.1 | $2 | $8 | $0.5 | $0 | $8 |
gpt-4.1-mini | $0.4 | $1.6 | $0.1 | $0 | $1.6 |
gpt-4.1-nano | $0.1 | $0.4 | $0.025 | $0 | $0.4 |
gpt-4o | $2.5 | $10 | $1.25 | $0 | $10 |
gpt-4o-mini | $0.15 | $0.6 | $0.075 | $0 | $0.6 |
gpt-5.2 | $2 | $8 | $0.5 | $0 | $8 |
gpt-5.3-codex | $2 | $8 | $0.5 | $0 | $8 |
gpt-5.4 | $2 | $8 | $0.5 | $0 | $8 |
gpt-5.4-mini | $0.4 | $1.6 | $0.1 | $0 | $1.6 |
gpt-5.5 | $2 | $8 | $0.5 | $0 | $8 |
o1 | $15 | $60 | $7.5 | $0 | $60 |
o1-pro | $150 | $600 | $0 | $0 | $600 |
o3 | $10 | $40 | $2.5 | $0 | $40 |
o3-mini | $1.1 | $4.4 | $0.55 | $0 | $4.4 |
o4-mini | $1.1 | $4.4 | $0.275 | $0 | $4.4 |
text-embedding-3-large | $0.13 | $0 | $0 | $0 | $0 |
text-embedding-3-small | $0.02 | $0 | $0 | $0 | $0 |
text-embedding-ada-002 | $0.1 | $0 | $0 | $0 | $0 |
Google Gemini
7 models · per million tokens
| Model | Input | Output | Cache read | Cache write | Thinking |
|---|---|---|---|---|---|
gemini-2.5-pro | $1.25 | $10 | $0.31 | $1.5625 | $10 |
| >200k tokens | $2.5 | $15 | $0.63 | $3.125 | $15 |
gemini-3-flash-preview | $0.25 | $1.5 | $0.025 | $0.3125 | $1.5 |
gemini-3.1-flash-image-preview | $0.5 | $3 | $0.05 | $0.625 | $3 |
| modal: audio in $0 audio out $0 image gen $60 | |||||
gemini-3.1-flash-lite-preview | $0.25 | $1.5 | $0.025 | $0.3125 | $1.5 |
gemini-3.1-flash-live-preview | $0.75 | $4.5 | $0.075 | $0.9375 | $4.5 |
| modal: audio in $3 audio out $12 image gen $0 | |||||
gemini-3.1-pro-preview | $2 | $12 | $0.5 | $2.5 | $12 |
| >200k tokens | $4 | $18 | $1 | $5 | $18 |
gemini-code-assist-unknown | $0.25 | $1.5 | $0.025 | $0.3125 | $1.5 |
xAI
7 models · per million tokens
| Model | Input | Output | Cache read | Cache write | Thinking |
|---|---|---|---|---|---|
grok-2-vision-1212 | $2 | $10 | $0 | $0 | $10 |
grok-3 | $3 | $15 | $0 | $0 | $15 |
grok-3-fast | $5 | $25 | $0 | $0 | $25 |
grok-3-mini | $0.3 | $0.5 | $0 | $0 | $0.5 |
grok-3-mini-fast | $0.6 | $4 | $0 | $0 | $4 |
grok-4 | $3 | $15 | $0 | $0 | $15 |
grok-4-mini | $0.3 | $0.5 | $0 | $0 | $0.5 |
Last updated 2026-05-01 from daemon/halton_meter/pricing/matrix.py.
JSON: /rates.json · Freshness manifest:
/rates-manifest.json