Skip to content

Commit d93c260

Browse files
feat(pricing): add gpt-6.1-terra fast/flex multipliers (ccusage#1975)
* feat(pricing): add gpt-6.1-terra fast/flex multipliers Co-authored-by: ryoppippi <[email protected]> * test(pricing): cover gpt-6.1-terra in embedded flex snapshot test Co-authored-by: ryoppippi <[email protected]> * ci: retrigger Co-authored-by: ryoppippi <[email protected]> --------- Co-authored-by: Cursor Agent <[email protected]> Co-authored-by: ryoppippi <[email protected]>
1 parent 8216c05 commit d93c260

4 files changed

Lines changed: 6 additions & 1 deletion

File tree

‎docs/guide/codex/index.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -74,7 +74,7 @@ Some usage remains unclassified, including older rollouts, saved headless `codex
7474

7575
Fallback detection reads the top-level `service_tier` and lets a named profile override it only when `profile = "name"` selects that profile in `config.toml`. Inactive profiles are ignored, and a selected profile without its own tier inherits the top-level setting. If Codex selected a profile through `--profile` or another configuration file, use an explicit `--speed` for unclassified usage because ccusage cannot infer that selection from `config.toml`.
7676

77-
Fast and Flex pricing use model-specific multipliers only when one is published. GPT-5.6 Sol, Terra, and Luna use the [documented 2× API Priority rate](https://learn.chatgpt.com/docs/agent-configuration/speed#fast-mode), and GPT-6 [Astra](https://developers.openai.com/api/docs/models/gpt-6-astra), [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol), and [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna) and [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol) use their documented 2× Fast rates. Models listed in OpenAI's [Flex pricing table](https://developers.openai.com/api/docs/pricing) use 0.5× Standard pricing, including dated and provider-qualified names. These are distinct from ChatGPT credit-consumption rates. ccusage's `costUSD` is an API-equivalent estimate, not a ChatGPT credit balance. When a model's Fast or Flex rate is unknown, ccusage reports standard pricing rather than assuming a multiplier, which may underestimate Fast usage or overestimate Flex usage.
77+
Fast and Flex pricing use model-specific multipliers only when one is published. GPT-5.6 Sol, Terra, and Luna use the [documented 2× API Priority rate](https://learn.chatgpt.com/docs/agent-configuration/speed#fast-mode), and GPT-6 [Astra](https://developers.openai.com/api/docs/models/gpt-6-astra), [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol), and [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna) and GPT-6.1 [Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol) and [Terra](https://developers.openai.com/api/docs/models/gpt-6.1-terra) use their documented 2× Fast rates. Models listed in OpenAI's [Flex pricing table](https://developers.openai.com/api/docs/pricing) use 0.5× Standard pricing, including dated and provider-qualified names. These are distinct from ChatGPT credit-consumption rates. ccusage's `costUSD` is an API-equivalent estimate, not a ChatGPT credit balance. When a model's Fast or Flex rate is unknown, ccusage reports standard pricing rather than assuming a multiplier, which may underestimate Fast usage or overestimate Flex usage.
7878

7979
Use [`pricingOverrides`](/guide/config-files#pricing-overrides) to configure a model's `fastMultiplier` or `flexMultiplier`.
8080

‎rust/crates/ccusage-core/src/fast-multiplier-overrides.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,7 @@
99
"gpt-6-astra": 2.0,
1010
"gpt-6-sol": 2.0,
1111
"gpt-6.1-sol": 2.0,
12+
"gpt-6.1-terra": 2.0,
1213
"gpt-6-luna": 2.0
1314
},
1415
"normalized_prefix": {

‎rust/crates/ccusage-core/src/flex-multiplier-overrides.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,7 @@
22
"exact": {
33
"gpt-6-astra": 0.5,
44
"gpt-6.1-sol": 0.5,
5+
"gpt-6.1-terra": 0.5,
56
"gpt-6-luna": 0.5,
67
"gpt-6-sol": 0.5,
78
"gpt-5.6-sol": 0.5,

‎rust/crates/ccusage-core/src/pricing.rs‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5500,6 +5500,7 @@ mod tests {
55005500
for model in [
55015501
"gpt-6-astra",
55025502
"gpt-6.1-sol",
5503+
"gpt-6.1-terra",
55035504
"gpt-6-luna",
55045505
"gpt-6-sol",
55055506
"gpt-5.6-sol",
@@ -5529,6 +5530,7 @@ mod tests {
55295530

55305531
for (model, expected) in [
55315532
("gpt-6-astra-2026-09-24", 2.0),
5533+
("gpt-6.1-terra", 2.0),
55325534
("gpt-5.4-2026-03-05", 2.0),
55335535
("openai/gpt-5.6-sol-20261001", 2.0),
55345536
("gpt-5.6-terra-2026-10-01", 2.0),
@@ -5560,6 +5562,7 @@ mod tests {
55605562
for (model, expected) in [
55615563
("gpt-6-astra-2026-09-24", 0.5),
55625564
("gpt-6.1-sol-20260924", 0.5),
5565+
("gpt-6.1-terra", 0.5),
55635566
("openai/gpt-5.5", 0.5),
55645567
("openrouter/openai/gpt-5.4-2026-03-05", 0.5),
55655568
("azure/gpt-5.2", 0.5),

0 commit comments

Comments
 (0)