cctrack 0.11.0__tar.gz → 0.11.2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {cctrack-0.11.0 → cctrack-0.11.2}/CLAUDE.md +2 -2
- {cctrack-0.11.0 → cctrack-0.11.2}/PKG-INFO +10 -4
- {cctrack-0.11.0 → cctrack-0.11.2}/README.md +9 -3
- {cctrack-0.11.0 → cctrack-0.11.2}/pyproject.toml +1 -1
- {cctrack-0.11.0 → cctrack-0.11.2}/src/cctrack/__init__.py +560 -40
- {cctrack-0.11.0 → cctrack-0.11.2}/tests/conftest.py +9 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/tests/test_cctrack.py +23 -0
- cctrack-0.11.2/tests/test_progress.py +84 -0
- cctrack-0.11.2/tests/test_remote_parse.py +195 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/tests/test_sandy.py +26 -6
- cctrack-0.11.2/tests/test_ssh_tty.py +83 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/.gitignore +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/LICENSE +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/scripts/compare_ccusage.py +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/scripts/diagnose_session_cost.py +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/scripts/trace_project.py +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/src/cctrack/__main__.py +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/tests/fixtures/ccusage-parity.json +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/tests/test_accounting.py +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/tests/test_codex.py +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/tests/test_detail.py +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/tests/test_hook.py +0 -0
- {cctrack-0.11.0 → cctrack-0.11.2}/tests/test_hook_reporting.py +0 -0
|
@@ -33,9 +33,9 @@ This is a single-module CLI tool. All logic lives in `src/cctrack/__init__.py`:
|
|
|
33
33
|
|
|
34
34
|
1. **Rate card** (`RATES`, `_an`/`_oa` row builders, `_family_matches`, `get_rates`, `calculate_cost`, `is_known_model`) - Anthropic and OpenAI prices. **Every model version needs its own row**: `_family_matches` lets a row absorb only the exact id, dated snapshots (`-20250514`, `-2025-08-07`) and non-version suffixes (`-codex`) — never a short-number minor version (`claude-opus-5` does NOT match `claude-opus-5-5`) or a size-tier word (`mini`, `nano`, `pro`, `max`, `luna`, `terra`, `sol`, `astra`). This is deliberate: prefix inheritance silently mispriced opus-4-8 (3×) and opus-5-5 (84%) before. Unknown models are flagged `?` and fall back to Sonnet (Claude) or GPT-5 (OpenAI) rates. `get_rates` takes the usage date (time-limited `intro` pricing) and the request's prompt size (`long_context` tiers: historical Sonnet 4/4.5 >200K, Haiku 5.5 >100K, several OpenAI models >272K). Re-verify against the official pricing pages when adding rows; don't infer a price from a neighbouring model.
|
|
35
35
|
1a. **Energy model** (`ENERGY_WH_PER_MTOK`, `estimate_energy_wh`) - Opt-in (`--energy`) order-of-magnitude estimate keyed off each rate entry's `tier`. Deliberately NOT a function of price: both cache-write TTLs use one figure because a 1h write costs more money but the same compute.
|
|
36
|
-
2. **File discovery** (`sandy_home`, `_sandy_print_state`, `sandbox_roots`, `default_dirs`, `discover_files`) - Claude transcripts from `~/.claude/projects/` plus each Sandy sandbox's `claude/projects/` (ONLY `projects/` — `claude/` also holds `history.jsonl`, job timelines, tool-audit logs). Sandbox roots come from `sandy --print-state`
|
|
36
|
+
2. **File discovery** (`sandy_home`, `_sandy_print_state`, `sandbox_roots`, `default_dirs`, `discover_files`) - Claude transcripts from `~/.claude/projects/` plus each Sandy sandbox's `claude/projects/` (ONLY `projects/` — `claude/` also holds `history.jsonl`, job timelines, tool-audit logs). Sandbox roots come from scanning `$SANDY_HOME/sandboxes/*` (default `~/.sandy`), locally and remotely. `sandy --print-state` (`sandboxes[].path`) is asked ONLY when that dir is missing — it takes many seconds and was called 3× per run, which made cctrack look hung. It is cached per run, gets stdin=/dev/null, and has a `CCTRACK_SANDY_TIMEOUT` (default 15s) with a fallback note. Per sandy's host-side path contract each root has agent homes `claude/` (→ `~/.claude` in the sandbox) and `codex/` (→ `~/.codex`); everything else under a root is private. **Dot-entries** (`_is_sandbox_name`): skip `.rsync-from.*` (an in-progress `sandy --rsync-from` copy — its hook data was being summed twice) and `*.lock`; any other dot-dir is a REAL sandbox iff it holds `WORKSPACE.json` (a workspace like `~/.dotfiles` → sandbox `.dotfiles-<sha8>`). Sandy's own enumeration, hence `--print-state`, currently omits dot-named sandboxes; the directory scan finds them. Tests are isolated from real sandboxes by `tests/conftest.py`.
|
|
37
37
|
2a. **Codex** (`codex_homes`, `discover_codex_files`, `parse_codex_lines`, `parse_codex_events`, `fetch_remote_codex`) - Reads `$CODEX_HOME` (default `~/.codex`) and every sandbox's `codex/` (sandy never sets CODEX_HOME), `sessions/` + `archived_sessions/` rollouts, incl. `.jsonl.zst` (stdlib `compression.zstd` on 3.14+, else the `zstd` CLI, else skipped and counted). Lines are `{timestamp, type, payload}`. Reconcile `token_usage_record` items with their matching `event_msg`/`token_count` snapshots; never discard the rest of a file after its first record. Keep standalone compaction usage, last-only and cumulative-only snapshots; dedup unchanged cumulative re-emissions. Prefer the record's explicit model and recorded service tier. Forked legacy usage is matched against the parent's sequence, preserving history through repeated merges and nested forks; missing parents retain uncertain usage flagged UNKNOWN. **`input_tokens` includes `cached_input_tokens` and `cache_write_input_tokens`; `output_tokens` includes reasoning** — uncached input = input − cached − cache_write. Model/cwd from the latest `turn_context`; thread id + git branch from `session_meta`. Codex events carry `agent="codex"`.
|
|
38
|
-
3. **Remote aggregation** (`remote_sandbox_roots`, `fetch_remote_jsonl`, `parse_remote_events`, `fetch_remote_hook_data`, `parse_remote_hook_data`, `fetch_remote_codex`) -
|
|
38
|
+
3. **Remote aggregation** (`fetch_remote_bundle`, `_remote_program`, `_remote_collect`, `_parse_remote_files`, `parse_hook_blob`, `remote_sandbox_roots`, `fetch_remote_jsonl`, `parse_remote_events`, `fetch_remote_hook_data`, `parse_remote_hook_data`, `fetch_remote_codex`) - **Default: parse on the host.** `fetch_remote_bundle` sends this module's own source (zlib+base64) to `ssh host python3 -`; `_remote_collect` runs there (read-only: no hook rollup) with the host's own discovery and EXACTLY the per-file code the raw stream uses (`_parse_remote_files`, `parse_hook_blob`), and returns events + parse stats + hook rows as zlib-compressed tagged JSON (`_tag_json`/`_untag_json` round-trip tuples, sets, datetimes, non-str keys — never pickle). Remote `Progress` emits `CCTRACK_PROGRESS` stderr lines that `_run_streaming` relays into the local status line. Results are cached per host; the parse_remote_* functions read the bundle. `{"failed"}` (ssh error 255, timeout) means no retry; `{"fallback"}` (no python3 / <3.10 / unreadable reply, or `CCTRACK_REMOTE_PARSE=0`) streams raw: one SSH call finds sandbox roots (same rules as locally, cached), then each fetch cats the host's dirs with file separators, gzip-compressed in transit (`_gzip_wrapped`/`_decode_stream`), and parses locally. `tests/test_remote_parse.py` runs both paths against one fake host via a fake `ssh` and requires identical events, stats and hook rows; `tests/conftest.py` stubs `fetch_remote_bundle` unless marked `real_remote_bundle`. All ssh runs through `_run_ssh`: `ssh -T`, stdin=/dev/null, local termios saved/restored (a timed-out ssh once left the terminal raw → staircased report). Fetch timeout `CCTRACK_SSH_TIMEOUT` (default 600s); a timeout warns that the host's data is MISSING. `Progress` draws a cylon bar + bytes/files on stderr only when it's a TTY (`CCTRACK_NO_PROGRESS` disables).
|
|
39
39
|
3a. **Hook parsing** (`parse_hook_rows`, `compute_hook_deltas`) - The hook gives **cost only**. Its `input_tokens`/`output_tokens`/`cache_*` fields are context-window SNAPSHOTS (`input_tokens` ≈ `cache_read + cache_write`; `output_tokens` is just the last message's), not cumulative — never use them for token counts. `cost_usd` is a session-lifetime cumulative that is unreliable in two ways handled by `compute_hook_deltas`: (1) it can already be large the first time a session is observed (a long-running/unattended session that only rendered its statusline partway through), so the **first observation is a baseline that is NOT counted** — booking a session's pre-existing cumulative onto its first-seen day is what produced a bogus $3,370 day; (2) it **drops** on resume/compaction (or when parallel processes share one session id), so a drop **rebaselines without counting the new level** — otherwise a day's booked spend can exceed the counter's own peak, which is impossible for real money. Net rule: **book only observed upward increments**; a rolled-up baseline seeds `prev` so already-counted days aren't recounted.
|
|
40
40
|
3b. **Hook install** (`install_hook`, `uninstall_hook`, `_apply_hook_install`, `_apply_hook_uninstall`, `remote_*_hook`, `HOOK_SCRIPT`) - The hook is Claude Code's `statusLine` command. Install **wraps** any existing status line: it's saved as `wrapped_status_line` in `~/.claude/cctrack/config.json` (other statusLine keys like `padding` are kept), and `HOOK_SCRIPT` records the cost and then runs it via the shell with the same stdin, passing stdout and exit code through. Re-install keeps the saved command and `installed_at` (the start of hook coverage). Uninstall restores the wrapped line only if `statusLine` still points at cctrack. `_apply_hook_*` are self-contained (imports inside) because `remote_*_hook` ship their source with `inspect.getsource` to `ssh host python3 -`. Local and remote share one implementation, and tests run that shipped program for real.
|
|
41
41
|
4. **JSONL parsing** (`parse_lines`, `parse_events`, `dedup_events`) - Extracts `assistant` events with token usage. Deduplicates by message + request identity, falling back to Anthropic message id scoped to the session when request id is absent, and then request id when older logs omit message id. Gateway message ids without request ids also include timestamps. Keep the fullest snapshot, prefer parent messages over sidechain replays, and count advisor iterations separately. `reconcile_sources` performs the final cross-host merge and rebuilds source costs so all report modes agree. Preserve copy locations in JSON/CSV.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: cctrack
|
|
3
|
-
Version: 0.11.
|
|
3
|
+
Version: 0.11.2
|
|
4
4
|
Summary: Claude Code cost tracker — scans JSONL logs and reports token usage + estimated cost
|
|
5
5
|
Project-URL: Homepage, https://github.com/rappdw/cctrack
|
|
6
6
|
Project-URL: Repository, https://github.com/rappdw/cctrack
|
|
@@ -108,7 +108,7 @@ Costs are at OpenAI's **API list prices**. If you use Codex through a ChatGPT pl
|
|
|
108
108
|
|
|
109
109
|
cctrack finds every [Sandy](https://github.com/rappdw/sandy) sandbox on the machine (and on `--remote` hosts) and includes its Claude Code and Codex usage. It follows sandy's published host-side path contract:
|
|
110
110
|
|
|
111
|
-
- **Finding sandboxes:** `sandy --print-state`
|
|
111
|
+
- **Finding sandboxes:** a direct scan of `$SANDY_HOME/sandboxes/*` (default `~/.sandy/sandboxes`), the same on `--remote` hosts. `sandy --print-state` can take many seconds, so cctrack only asks it when that directory doesn't exist, waiting at most 15 seconds (`CCTRACK_SANDY_TIMEOUT`).
|
|
112
112
|
- **Per sandbox:** Claude Code transcripts from `claude/projects/`, statusline-hook data from `claude/cctrack/`, Codex rollouts from `codex/sessions/` and `codex/archived_sessions/`. Other files under `claude/` (`history.jsonl`, job timelines, tool-audit logs) aren't transcripts and are ignored.
|
|
113
113
|
- **Copies:** matching API identities are charged once across all collected locations. The fullest usage snapshot wins; equivalent copies have deterministic attribution. Session JSON/CSV includes `source_locations` and `source_files` so every copy remains traceable. Raw statusline histories are merged before calculating cost increments. Old monthly hook summaries contain no session identities, so copied summaries cannot yet be deduplicated reliably.
|
|
114
114
|
- **Temporary copies:** the hidden `.rsync-from.<name>.<pid>/` copy that exists while `sandy --rsync-from` is pulling a sandbox in is skipped, as are `.lock` directories. A sandbox's Codex home is never shared with the host's `~/.codex`, and transcript history copied between hosts with `sandy --rsync` is deduplicated by API message/response identity.
|
|
@@ -182,7 +182,11 @@ It's installed as Claude Code's `statusLine` command (`~/.claude/hooks/cctrack-h
|
|
|
182
182
|
|
|
183
183
|
## Remote aggregation
|
|
184
184
|
|
|
185
|
-
With `--remote`, cctrack
|
|
185
|
+
With `--remote`, cctrack reads each host's Claude Code transcripts, Codex rollouts and statusline hook data (`~/.claude/cctrack/`), including the host's Sandy sandboxes. Usage from every machine is then reconciled and summed per day. Requires SSH key auth.
|
|
186
|
+
|
|
187
|
+
**Logs are parsed on the host.** Over one SSH connection, cctrack sends its own code to the host and runs it with `python3 -`. Only the usage records come back: ids, timestamps, models and token counts, compressed. Raw logs are mostly conversation content, so this cuts the transfer from gigabytes to megabytes. The host doesn't need cctrack installed, nothing on it is changed, and the results are the same as reading the raw logs. If the host has no Python 3.10+, cctrack says so and streams the raw logs instead, gzip-compressed. Set `CCTRACK_REMOTE_PARSE=0` to always stream.
|
|
188
|
+
|
|
189
|
+
Each fetch may take up to 600 seconds (set `CCTRACK_SSH_TIMEOUT` to change it). If one times out, cctrack warns that the host's data is missing from the report. While it works, a status line on stderr shows each step: files found and parsed, bytes received, elapsed time. It's shown only when stderr is a terminal; `CCTRACK_NO_PROGRESS=1` turns it off.
|
|
186
190
|
|
|
187
191
|
```bash
|
|
188
192
|
# Aggregate this machine + DGX server + laptop
|
|
@@ -198,6 +202,7 @@ Prices per million tokens. Claude prices are from [Anthropic's pricing page](htt
|
|
|
198
202
|
|
|
199
203
|
| Claude model | Input | Output | Cache Read | Cache Write 5m | Cache Write 1h |
|
|
200
204
|
|---|---|---|---|---|---|
|
|
205
|
+
| Fable 5.2 / Mythos 5.2 | $8.00 | $40.00 | $0.20 | $10.00 | $16.00 |
|
|
201
206
|
| Fable 5.1 / Mythos 5.1 | $10.00 | $50.00 | $0.25 | $12.50 | $20.00 |
|
|
202
207
|
| Fable 5 / Mythos 5 | $10.00 | $50.00 | $1.00 | $12.50 | $20.00 |
|
|
203
208
|
| Opus 5.5 | $4.00 | $20.00 | $0.20 | $5.00 | $8.00 |
|
|
@@ -213,12 +218,13 @@ Prices per million tokens. Claude prices are from [Anthropic's pricing page](htt
|
|
|
213
218
|
| Haiku 3.5 | $0.80 | $4.00 | $0.08 | $1.00 | $1.60 |
|
|
214
219
|
| Haiku 3 | $0.25 | $1.25 | $0.03 | $0.30 | $0.50 |
|
|
215
220
|
|
|
216
|
-
OpenAI prices (for Codex) are from [OpenAI's pricing page](https://developers.openai.com/api/docs/pricing), Standard tier.
|
|
221
|
+
OpenAI prices (for Codex) are from [OpenAI's pricing page](https://developers.openai.com/api/docs/pricing), Standard tier, last checked 2026-11-16. Cache writes are priced at OpenAI's 30-minute rate, shown below. OpenAI also sells 12-hour writes at 2×, but Codex logs don't record which one was used. Where no cache-write price is listed, cache writes bill as ordinary input. Some ids Codex logs aren't on OpenAI's price list at all, such as `codex-auto-review` and `gpt-daybreak-blue-latest`. Those stay flagged `?` and are estimated at GPT-5 rates.
|
|
217
222
|
|
|
218
223
|
| OpenAI model | Input | Cached input | Output | Cache write | Over 272K input |
|
|
219
224
|
|---|---|---|---|---|---|
|
|
220
225
|
| gpt-6-astra | $10.00 | $1.00 | $50.00 | $12.50 | $20 / $2 / $75 / $25 |
|
|
221
226
|
| gpt-6.1-sol | $2.00 | $0.10 | $10.00 | $2.50 | $4 / $0.20 / $15 / $5 |
|
|
227
|
+
| gpt-6.1-terra | $1.00 | $0.05 | $5.00 | $1.25 | $2 / $0.10 / $7.50 / $2.50 |
|
|
222
228
|
| gpt-6-sol | $2.00 | $0.20 | $10.00 | $2.50 | $4 / $0.40 / $15 / $5 |
|
|
223
229
|
| gpt-6-luna | $0.10 | $0.01 | $0.50 | $0.125 | $0.20 / $0.02 / $0.75 / $0.25 |
|
|
224
230
|
| gpt-5.6-sol | $4.00 | $0.40 | $20.00 | $5.00 | $8 / $0.80 / $30 / $10 |
|
|
@@ -83,7 +83,7 @@ Costs are at OpenAI's **API list prices**. If you use Codex through a ChatGPT pl
|
|
|
83
83
|
|
|
84
84
|
cctrack finds every [Sandy](https://github.com/rappdw/sandy) sandbox on the machine (and on `--remote` hosts) and includes its Claude Code and Codex usage. It follows sandy's published host-side path contract:
|
|
85
85
|
|
|
86
|
-
- **Finding sandboxes:** `sandy --print-state`
|
|
86
|
+
- **Finding sandboxes:** a direct scan of `$SANDY_HOME/sandboxes/*` (default `~/.sandy/sandboxes`), the same on `--remote` hosts. `sandy --print-state` can take many seconds, so cctrack only asks it when that directory doesn't exist, waiting at most 15 seconds (`CCTRACK_SANDY_TIMEOUT`).
|
|
87
87
|
- **Per sandbox:** Claude Code transcripts from `claude/projects/`, statusline-hook data from `claude/cctrack/`, Codex rollouts from `codex/sessions/` and `codex/archived_sessions/`. Other files under `claude/` (`history.jsonl`, job timelines, tool-audit logs) aren't transcripts and are ignored.
|
|
88
88
|
- **Copies:** matching API identities are charged once across all collected locations. The fullest usage snapshot wins; equivalent copies have deterministic attribution. Session JSON/CSV includes `source_locations` and `source_files` so every copy remains traceable. Raw statusline histories are merged before calculating cost increments. Old monthly hook summaries contain no session identities, so copied summaries cannot yet be deduplicated reliably.
|
|
89
89
|
- **Temporary copies:** the hidden `.rsync-from.<name>.<pid>/` copy that exists while `sandy --rsync-from` is pulling a sandbox in is skipped, as are `.lock` directories. A sandbox's Codex home is never shared with the host's `~/.codex`, and transcript history copied between hosts with `sandy --rsync` is deduplicated by API message/response identity.
|
|
@@ -157,7 +157,11 @@ It's installed as Claude Code's `statusLine` command (`~/.claude/hooks/cctrack-h
|
|
|
157
157
|
|
|
158
158
|
## Remote aggregation
|
|
159
159
|
|
|
160
|
-
With `--remote`, cctrack
|
|
160
|
+
With `--remote`, cctrack reads each host's Claude Code transcripts, Codex rollouts and statusline hook data (`~/.claude/cctrack/`), including the host's Sandy sandboxes. Usage from every machine is then reconciled and summed per day. Requires SSH key auth.
|
|
161
|
+
|
|
162
|
+
**Logs are parsed on the host.** Over one SSH connection, cctrack sends its own code to the host and runs it with `python3 -`. Only the usage records come back: ids, timestamps, models and token counts, compressed. Raw logs are mostly conversation content, so this cuts the transfer from gigabytes to megabytes. The host doesn't need cctrack installed, nothing on it is changed, and the results are the same as reading the raw logs. If the host has no Python 3.10+, cctrack says so and streams the raw logs instead, gzip-compressed. Set `CCTRACK_REMOTE_PARSE=0` to always stream.
|
|
163
|
+
|
|
164
|
+
Each fetch may take up to 600 seconds (set `CCTRACK_SSH_TIMEOUT` to change it). If one times out, cctrack warns that the host's data is missing from the report. While it works, a status line on stderr shows each step: files found and parsed, bytes received, elapsed time. It's shown only when stderr is a terminal; `CCTRACK_NO_PROGRESS=1` turns it off.
|
|
161
165
|
|
|
162
166
|
```bash
|
|
163
167
|
# Aggregate this machine + DGX server + laptop
|
|
@@ -173,6 +177,7 @@ Prices per million tokens. Claude prices are from [Anthropic's pricing page](htt
|
|
|
173
177
|
|
|
174
178
|
| Claude model | Input | Output | Cache Read | Cache Write 5m | Cache Write 1h |
|
|
175
179
|
|---|---|---|---|---|---|
|
|
180
|
+
| Fable 5.2 / Mythos 5.2 | $8.00 | $40.00 | $0.20 | $10.00 | $16.00 |
|
|
176
181
|
| Fable 5.1 / Mythos 5.1 | $10.00 | $50.00 | $0.25 | $12.50 | $20.00 |
|
|
177
182
|
| Fable 5 / Mythos 5 | $10.00 | $50.00 | $1.00 | $12.50 | $20.00 |
|
|
178
183
|
| Opus 5.5 | $4.00 | $20.00 | $0.20 | $5.00 | $8.00 |
|
|
@@ -188,12 +193,13 @@ Prices per million tokens. Claude prices are from [Anthropic's pricing page](htt
|
|
|
188
193
|
| Haiku 3.5 | $0.80 | $4.00 | $0.08 | $1.00 | $1.60 |
|
|
189
194
|
| Haiku 3 | $0.25 | $1.25 | $0.03 | $0.30 | $0.50 |
|
|
190
195
|
|
|
191
|
-
OpenAI prices (for Codex) are from [OpenAI's pricing page](https://developers.openai.com/api/docs/pricing), Standard tier.
|
|
196
|
+
OpenAI prices (for Codex) are from [OpenAI's pricing page](https://developers.openai.com/api/docs/pricing), Standard tier, last checked 2026-11-16. Cache writes are priced at OpenAI's 30-minute rate, shown below. OpenAI also sells 12-hour writes at 2×, but Codex logs don't record which one was used. Where no cache-write price is listed, cache writes bill as ordinary input. Some ids Codex logs aren't on OpenAI's price list at all, such as `codex-auto-review` and `gpt-daybreak-blue-latest`. Those stay flagged `?` and are estimated at GPT-5 rates.
|
|
192
197
|
|
|
193
198
|
| OpenAI model | Input | Cached input | Output | Cache write | Over 272K input |
|
|
194
199
|
|---|---|---|---|---|---|
|
|
195
200
|
| gpt-6-astra | $10.00 | $1.00 | $50.00 | $12.50 | $20 / $2 / $75 / $25 |
|
|
196
201
|
| gpt-6.1-sol | $2.00 | $0.10 | $10.00 | $2.50 | $4 / $0.20 / $15 / $5 |
|
|
202
|
+
| gpt-6.1-terra | $1.00 | $0.05 | $5.00 | $1.25 | $2 / $0.10 / $7.50 / $2.50 |
|
|
197
203
|
| gpt-6-sol | $2.00 | $0.20 | $10.00 | $2.50 | $4 / $0.40 / $15 / $5 |
|
|
198
204
|
| gpt-6-luna | $0.10 | $0.01 | $0.50 | $0.125 | $0.20 / $0.02 / $0.75 / $0.25 |
|
|
199
205
|
| gpt-5.6-sol | $4.00 | $0.40 | $20.00 | $5.00 | $8 / $0.80 / $30 / $10 |
|