Translation Operations & Cost
Queue state, prompt-version controls, and estimated model cost for translation jobs. Generated 2026-08-23 10:49:21 UTC.
Approved-human queued5
Other queued0
Responses queued5
All-model tokens used27,328,989
Approved-human tokens left8,649,574
Approved-human cost left$83.8194
Priced model groups8
Scheduled Translation Queue
| Class | Status | Priority | Prompt | Model | API | Reasoning | Top p | Requests | Oldest |
|---|---|---|---|---|---|---|---|---|---|
| approved-human | pending | 4 | legacy_scholarly_v4_mini v1 | gpt-5.4-mini | responses | low | - | 1 | 2026-07-08 20:11:38 |
| approved-human | pending | 4 | legacy_scholarly_v4_mini_high v1 | gpt-5.4-mini | responses | high | - | 1 | 2026-07-08 20:11:40 |
| approved-human | pending | 4 | legacy_scholarly_v4_mini_medium v1 | gpt-5.4-mini | responses | medium | - | 1 | 2026-07-08 20:11:39 |
| approved-human | pending | 4 | legacy_scholarly_v4_reasoning v1 | gpt-5.5 | responses | low | - | 1 | 2026-07-10 20:29:36 |
| approved-human | pending | 4 | legacy_scholarly_v4_reasoning_high v1 | gpt-5.5 | responses | high | - | 1 | 2026-07-08 20:11:37 |
Recorded Token Usage Totals
Translation runs9,871
Total tokens27,328,989
Input tokens23,090,534
Output tokens3,515,541
Reasoning tokens2,453,715
Estimated recorded cost$128.6840
Input/output token totals use rows where split usage is recorded. Total tokens use the historical translation_runs.tokens_used value, so it can cover older rows even when input/output split data is absent.
Approved-Human Priority Completion Estimate
Remaining target pairs2,899
Remaining runs3,301
Expected total tokens8,649,574
Expected input tokens6,418,018
Expected output tokens2,231,556
Expected cost$83.8194
This estimates the work to complete approved-human evaluation targets for the baseline gpt-5.5 v1/v2/v3 set plus approved-human-only prompt versions with queue priority 4 or better. Estimates use same-prompt averages when available, then same model/API/reasoning, same model, gpt-5.5 v3, or all translation runs as a fallback. 33 row(s) have token estimates but no dollar estimate because no configured pricing or split-token sample was available.
| Prompt | Model | API | Reasoning | Priority | Targets | Complete | Remaining pairs | Remaining runs | Open | Avg tokens | Exp. input | Exp. output | Exp. reasoning | Exp. total | Exp. cost | Sample basis |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| paper_guidance_ablation_gpt56 v1 | gpt-5.6-sol | responses | medium | 1 | 101 | 100 | 1 | 3 | 0 | 1,589 | 4,343 | 424 | 683 | 4,768 | - | same prompt version (300) |
| paper_guidance_ablation_gpt56 v2 | gpt-5.6-sol | responses | medium | 1 | 101 | 100 | 1 | 3 | 0 | 3,053 | 8,528 | 631 | 701 | 9,159 | - | same prompt version (300) |
| paper_guidance_ablation_gpt56 v3 | gpt-5.6-sol | responses | medium | 1 | 101 | 100 | 1 | 3 | 0 | 3,948 | 11,199 | 644 | 727 | 11,843 | - | same prompt version (300) |
| gpt-4.1-2025-04-14 v1 | gpt-4.1-2025-04-14 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 382 | 295 | 87 | - | 382 | - | same prompt version (100) |
| gpt-4.1-2025-04-14 v2 | gpt-4.1-2025-04-14 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 1,537 | 1,454 | 83 | - | 1,537 | - | same prompt version (100) |
| gpt-4.1-2025-04-14 v3 | gpt-4.1-2025-04-14 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 3,823 | 3,739 | 84 | - | 3,823 | - | same prompt version (100) |
| gpt-4o-2024-05-13 v1 | gpt-4o-2024-05-13 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 376 | 295 | 81 | - | 376 | - | same prompt version (100) |
| gpt-4o-2024-05-13 v2 | gpt-4o-2024-05-13 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 1,536 | 1,454 | 82 | - | 1,536 | - | same prompt version (100) |
| gpt-4o-2024-05-13 v3 | gpt-4o-2024-05-13 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 3,825 | 3,739 | 86 | - | 3,825 | - | same prompt version (100) |
| gpt-4o-2024-08-06 v1 | gpt-4o-2024-08-06 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 378 | 295 | 83 | - | 378 | - | same prompt version (100) |
| gpt-4o-2024-08-06 v2 | gpt-4o-2024-08-06 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 1,536 | 1,454 | 83 | - | 1,536 | - | same prompt version (100) |
| gpt-4o-2024-08-06 v3 | gpt-4o-2024-08-06 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 3,823 | 3,739 | 84 | - | 3,823 | - | same prompt version (100) |
| gpt-4o-2024-11-20 v1 | gpt-4o-2024-11-20 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 386 | 295 | 91 | - | 386 | - | same prompt version (100) |
| gpt-4o-2024-11-20 v2 | gpt-4o-2024-11-20 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 1,537 | 1,454 | 83 | - | 1,537 | - | same prompt version (100) |
| gpt-4o-2024-11-20 v3 | gpt-4o-2024-11-20 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 3,824 | 3,739 | 85 | - | 3,824 | - | same prompt version (100) |
| gpt-4-turbo-2024-04-09 v1 | gpt-4-turbo-2024-04-09 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 488 | 404 | 84 | - | 488 | - | same prompt version (100) |
| gpt-4-turbo-2024-04-09 v2 | gpt-4-turbo-2024-04-09 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 1,716 | 1,632 | 84 | - | 1,716 | - | same prompt version (100) |
| gpt-4-turbo-2024-04-09 v3 | gpt-4-turbo-2024-04-09 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 4,291 | 4,204 | 87 | - | 4,291 | - | same prompt version (100) |
| gpt-5 v1 | gpt-5-2025-08-07 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 2,407 | 370 | 2,037 | 1,934 | 2,407 | - | same prompt version (100) |
| gpt-5 v2 | gpt-5-2025-08-07 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 3,984 | 1,529 | 2,456 | 2,355 | 3,984 | - | same prompt version (100) |
| gpt-5 v3 | gpt-5-2025-08-07 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 6,886 | 3,814 | 3,072 | 2,970 | 6,886 | - | same prompt version (100) |
| gpt-5.1 v1 | gpt-5.1-2025-11-13 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 473 | 370 | 103 | - | 473 | - | same prompt version (100) |
| gpt-5.1 v2 | gpt-5.1-2025-11-13 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 1,631 | 1,529 | 102 | - | 1,631 | - | same prompt version (100) |
| gpt-5.1 v3 | gpt-5.1-2025-11-13 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 3,920 | 3,814 | 106 | - | 3,920 | - | same prompt version (100) |
| gpt-5.2 v1 | gpt-5.2-2025-12-11 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 472 | 370 | 102 | - | 472 | - | same prompt version (97) |
| gpt-5.2 v2 | gpt-5.2-2025-12-11 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 1,623 | 1,529 | 95 | - | 1,623 | - | same prompt version (100) |
| gpt-5.2 v3 | gpt-5.2-2025-12-11 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 3,913 | 3,814 | 99 | - | 3,913 | - | same prompt version (100) |
| gpt-5.3-chat-latest v1 | gpt-5.3-chat-latest | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 468 | 370 | 98 | 85 | 468 | - | same prompt version (100) |
| gpt-5.3-chat-latest v2 | gpt-5.3-chat-latest | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 1,629 | 1,529 | 101 | 91 | 1,629 | - | same prompt version (100) |
| gpt-5.3-chat-latest v3 | gpt-5.3-chat-latest | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 3,911 | 3,814 | 97 | - | 3,911 | - | same prompt version (100) |
| gpt-5.4 v1 | gpt-5.4 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 461 | 370 | 92 | - | 461 | $0.0023 | same prompt version (100) |
| gpt-5.4 v2 | gpt-5.4 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 1,623 | 1,529 | 94 | - | 1,623 | $0.0052 | same prompt version (100) |
| gpt-5.4 v3 | gpt-5.4 | chat_completions | - | 4 | 101 | 100 | 1 | 1 | 0 | 3,911 | 3,814 | 97 | - | 3,911 | $0.0110 | same prompt version (100) |
| gpt-5.5_v3_repeat v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 101 | 0 | 0 | 0 | 4,322 | 0 | 0 | 0 | 0 | $0.0000 | same prompt version (505) |
| gpt-5.5_v3_temp0 v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 2 | 99 | 99 | 0 | 4,508 | 378,279 | 67,964 | 50,688 | 446,242 | $3.9303 | same prompt version (2) |
| gpt-5.5_v3_temp04 v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 2 | 99 | 99 | 0 | 4,766 | 378,279 | 93,506 | 76,032 | 471,784 | $4.6966 | same prompt version (2) |
| gpt-5.5_v3_temp07 v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 2 | 99 | 99 | 0 | 4,505 | 378,279 | 67,716 | 50,688 | 445,995 | $3.9229 | same prompt version (2) |
| gpt-5.5_v4_mini v1 | gpt-5.4-mini | responses | low | 4 | 101 | 101 | 0 | 0 | 0 | 3,917 | 0 | 0 | 0 | 0 | $0.0000 | same prompt version (101) |
| gpt-5.5_v4_mini_high v1 | gpt-5.4-mini | responses | high | 4 | 101 | 101 | 0 | 0 | 0 | 6,308 | 0 | 0 | 0 | 0 | $0.0000 | same prompt version (101) |
| gpt-5.5_v4_mini_medium v1 | gpt-5.4-mini | responses | medium | 4 | 101 | 101 | 0 | 0 | 0 | 4,712 | 0 | 0 | 0 | 0 | $0.0000 | same prompt version (101) |
| gpt-5.5_v4_reasoning v1 | gpt-5.5 | responses | low | 4 | 101 | 101 | 0 | 0 | 0 | 3,831 | 0 | 0 | - | 0 | $0.0000 | same prompt version (101) |
| gpt-5.5_v4_reasoning_high v1 | gpt-5.5 | responses | high | 4 | 101 | 101 | 0 | 0 | 0 | 4,775 | 0 | 0 | 0 | 0 | $0.0000 | same prompt version (101) |
| gpt-5.5_v4_reasoning_medium v1 | gpt-5.5 | responses | medium | 4 | 101 | 101 | 0 | 0 | 0 | 4,041 | 0 | 0 | 0 | 0 | $0.0000 | same prompt version (101) |
| gpt-5.6-sol v1 | gpt-5.6-sol | responses | medium | 4 | 101 | 100 | 1 | 1 | 0 | 389 | 289 | 100 | 236 | 389 | - | same prompt version (100) |
| gpt-5.6-sol v2 | gpt-5.6-sol | responses | medium | 4 | 101 | 100 | 1 | 1 | 0 | 1,582 | 1,448 | 134 | 198 | 1,582 | - | same prompt version (100) |
| gpt-5.6-sol v3 | gpt-5.6-sol | responses | medium | 4 | 101 | 100 | 1 | 1 | 0 | 3,953 | 3,733 | 220 | 237 | 3,953 | - | same prompt version (100) |
| legacy_scholarly_v3_repeat v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 2 | 99 | 495 | 0 | 4,556 | 1,891,395 | 363,676 | 278,784 | 2,255,072 | $20.3673 | same prompt version (10) |
| legacy_scholarly_v4_mini v1 | gpt-5.4-mini | responses | low | 4 | 101 | 0 | 101 | 101 | 1 | 3,917 | 376,974 | 18,680 | 8,968 | 395,654 | $0.3668 | same model/API/reasoning (101) |
| legacy_scholarly_v4_mini_high v1 | gpt-5.4-mini | responses | high | 4 | 101 | 0 | 101 | 101 | 1 | 6,308 | 376,974 | 260,169 | 250,343 | 637,143 | $1.4535 | same model/API/reasoning (101) |
| legacy_scholarly_v4_mini_medium v1 | gpt-5.4-mini | responses | medium | 4 | 101 | 0 | 101 | 101 | 1 | 4,712 | 376,974 | 98,911 | 89,145 | 475,885 | $0.7278 | same model/API/reasoning (101) |
| legacy_scholarly_v4_reasoning v1 | gpt-5.5 | responses | low | 4 | 101 | 1 | 100 | 100 | 1 | 3,602 | 348,000 | 12,200 | - | 360,200 | $2.1060 | same prompt version (1) |
| legacy_scholarly_v4_reasoning_high v1 | gpt-5.5 | responses | high | 4 | 101 | 0 | 101 | 101 | 1 | 4,775 | 377,361 | 104,948 | 136,943 | 482,309 | $5.0352 | same model/API/reasoning (101) |
| legacy_scholarly_v4_reasoning_medium v1 | gpt-5.5 | responses | medium | 4 | 101 | 1 | 100 | 100 | 0 | 4,125 | 348,000 | 64,500 | 51,600 | 412,500 | $3.6750 | same prompt version (1) |
| parallage_01_diplomatic_literal v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 663 | 44,825 | 8,857 | - | 53,683 | $0.4898 | same prompt version (20) |
| parallage_02_interlinear_gloss v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 2,204 | 44,663 | 133,877 | 55,710 | 178,540 | $4.2396 | same prompt version (20) |
| parallage_03_syntax_scaffold v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 938 | 44,096 | 31,886 | - | 75,982 | $1.1771 | same prompt version (20) |
| parallage_04_minimal_inference v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 659 | 44,501 | 8,914 | - | 53,415 | $0.4899 | same prompt version (20) |
| parallage_05_scholarly_readable v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 795 | 44,420 | 19,999 | - | 64,419 | $0.8221 | same prompt version (20) |
| parallage_06_smooth_idiomatic v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 656 | 44,096 | 9,060 | - | 53,156 | $0.4923 | same prompt version (20) |
| parallage_07_message_paraphrase v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 1,092 | 45,149 | 43,319 | - | 88,468 | $1.5253 | same prompt version (20) |
| parallage_08_controlled_english v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 665 | 44,177 | 9,696 | - | 53,873 | $0.5118 | same prompt version (20) |
| parallage_09_analyst_brief v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 721 | 45,473 | 12,960 | - | 58,433 | $0.6162 | same prompt version (20) |
| parallage_10_plain_language v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 670 | 44,339 | 9,967 | - | 54,306 | $0.5207 | same prompt version (20) |
| parallage_11_learners_translation v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 1,602 | 44,663 | 85,115 | 3,969 | 129,778 | $2.7768 | same prompt version (20) |
| parallage_12_named_entity_explicit v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 1,062 | 44,582 | 41,415 | 18,144 | 85,998 | $1.4654 | same prompt version (20) |
| parallage_13_forked_lattice v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 1,456 | 45,068 | 72,876 | 33,777 | 117,944 | $2.4116 | same prompt version (20) |
| parallage_14_uncertainty_annotated v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 1,555 | 44,906 | 81,036 | 41,472 | 125,943 | $2.6556 | same prompt version (20) |
| parallage_15_decision_log v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 1,444 | 43,691 | 73,313 | - | 117,004 | $2.4178 | same prompt version (20) |
| parallage_16_adversarial_red_team v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 921 | 44,177 | 30,411 | - | 74,589 | $1.1332 | same prompt version (20) |
| parallage_17_back_translation_audit v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 1,149 | 44,339 | 48,693 | - | 93,033 | $1.6825 | same prompt version (20) |
| parallage_audit_pack v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 2,108 | 50,900 | 119,864 | 21,639 | 170,764 | $3.8504 | same prompt version (20) |
| parallage_compact_literal v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 869 | 60,215 | 10,166 | 41,472 | 70,381 | $0.6061 | same prompt version (20) |
| parallage_idiomatic_reader v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 935 | 61,511 | 14,224 | 33,534 | 75,735 | $0.7343 | same prompt version (20) |
| parallage_lattice_pack v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 1,491 | 49,523 | 71,268 | 4,698 | 120,791 | $2.3857 | same prompt version (20) |
| parallage_scholarly_edition v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 1,095 | 67,748 | 20,934 | 67,095 | 88,683 | $0.9668 | same prompt version (20) |
| parallage_spectrum_pack v1 | gpt-5.5 | chat_completions | - | 4 | 101 | 20 | 81 | 81 | 0 | 2,017 | 54,140 | 109,265 | 21,931 | 163,405 | $3.5487 | same prompt version (20) |
| gpt-5.5 v1 | gpt-5.5 | chat_completions | - | 5 | 101 | 101 | 0 | 0 | 0 | 472 | 0 | 0 | 0 | 0 | $0.0000 | same prompt version (101) |
| gpt-5.5 v2 | gpt-5.5 | chat_completions | - | 5 | 101 | 101 | 0 | 0 | 0 | 1,745 | 0 | 0 | 0 | 0 | $0.0000 | same prompt version (102) |
| gpt-5.5 v3 | gpt-5.5 | chat_completions | - | 5 | 101 | 101 | 0 | 0 | 0 | 3,723 | - | - | - | 0 | - | same prompt version (7) |
Whole-Stephanos v3 Estimate
Preferred-source targets3,683
Already completed450
Remaining3,233
Avg tokens/run3,723
Whole-corpus tokens13,710,231
Whole-corpus cost-
This uses current preferred public Greek source text for every non-quarantined lemma. Cost uses the configured price for gpt-5.5; the sample basis is same prompt version (7 runs).
| Scope | Targets | Input tokens | Output tokens | Total tokens | Estimated cost |
|---|---|---|---|---|---|
| All preferred-source targets | 3,683 | - | - | 13,710,231 | - |
| Remaining preferred-source targets | 3,233 | - | - | 12,035,073 | - |
Prompt Version Controls
| Profile | v | Active | Approved only | Default model | API | Reasoning | Top p | Runs | Approved priority | Queued | Completed | Avg tokens |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| apparatus_variants | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| claude_fable_5 | 1 | yes | yes | claude-fable-5 | chat_completions | - | - | 1 | 50 | 0 | 100 | - |
| claude_fable_5 | 2 | yes | yes | claude-fable-5 | chat_completions | - | - | 1 | 50 | 0 | 100 | - |
| claude_fable_5 | 3 | yes | yes | claude-fable-5 | chat_completions | - | - | 1 | 50 | 0 | 100 | - |
| claude_opus_4_8 | 1 | yes | yes | claude-opus-4.8 | chat_completions | - | - | 1 | 50 | 0 | 100 | - |
| claude_opus_4_8 | 2 | yes | yes | claude-opus-4.8 | chat_completions | - | - | 1 | 50 | 0 | 100 | - |
| claude_opus_4_8 | 3 | yes | yes | claude-opus-4.8 | chat_completions | - | - | 1 | 50 | 0 | 100 | - |
| claude_sonnet_5 | 1 | yes | yes | claude-sonnet-5 | chat_completions | - | - | 1 | 50 | 0 | 100 | - |
| claude_sonnet_5 | 2 | yes | yes | claude-sonnet-5 | chat_completions | - | - | 1 | 50 | 0 | 100 | - |
| claude_sonnet_5 | 3 | yes | yes | claude-sonnet-5 | chat_completions | - | - | 1 | 50 | 0 | 100 | - |
| entry_paraphrase | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| etymology_focus | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| glossary_terms | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| gpt-4.1-2025-04-14 | 1 | yes | yes | gpt-4.1-2025-04-14 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 382 |
| gpt-4.1-2025-04-14 | 2 | yes | yes | gpt-4.1-2025-04-14 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 1,537 |
| gpt-4.1-2025-04-14 | 3 | yes | yes | gpt-4.1-2025-04-14 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 3,823 |
| gpt-4o-2024-05-13 | 1 | yes | yes | gpt-4o-2024-05-13 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 376 |
| gpt-4o-2024-05-13 | 2 | yes | yes | gpt-4o-2024-05-13 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 1,536 |
| gpt-4o-2024-05-13 | 3 | yes | yes | gpt-4o-2024-05-13 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 3,825 |
| gpt-4o-2024-08-06 | 1 | yes | yes | gpt-4o-2024-08-06 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 378 |
| gpt-4o-2024-08-06 | 2 | yes | yes | gpt-4o-2024-08-06 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 1,536 |
| gpt-4o-2024-08-06 | 3 | yes | yes | gpt-4o-2024-08-06 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 3,823 |
| gpt-4o-2024-11-20 | 1 | yes | yes | gpt-4o-2024-11-20 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 386 |
| gpt-4o-2024-11-20 | 2 | yes | yes | gpt-4o-2024-11-20 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 1,537 |
| gpt-4o-2024-11-20 | 3 | yes | yes | gpt-4o-2024-11-20 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 3,824 |
| gpt-4-turbo-2024-04-09 | 1 | yes | yes | gpt-4-turbo-2024-04-09 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 488 |
| gpt-4-turbo-2024-04-09 | 2 | yes | yes | gpt-4-turbo-2024-04-09 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 1,716 |
| gpt-4-turbo-2024-04-09 | 3 | yes | yes | gpt-4-turbo-2024-04-09 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 4,291 |
| gpt-5 | 1 | yes | yes | gpt-5-2025-08-07 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 2,407 |
| gpt-5 | 2 | yes | yes | gpt-5-2025-08-07 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 3,984 |
| gpt-5 | 3 | yes | yes | gpt-5-2025-08-07 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 6,886 |
| gpt-5.1 | 1 | yes | yes | gpt-5.1-2025-11-13 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 473 |
| gpt-5.1 | 2 | yes | yes | gpt-5.1-2025-11-13 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 1,631 |
| gpt-5.1 | 3 | yes | yes | gpt-5.1-2025-11-13 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 3,920 |
| gpt-5.2 | 1 | yes | yes | gpt-5.2-2025-12-11 | chat_completions | - | 1.00 | 1 | 4 | 0 | 117 | 474 |
| gpt-5.2 | 2 | yes | yes | gpt-5.2-2025-12-11 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 1,623 |
| gpt-5.2 | 3 | yes | yes | gpt-5.2-2025-12-11 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 3,913 |
| gpt-5.3-chat-latest | 1 | yes | yes | gpt-5.3-chat-latest | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 468 |
| gpt-5.3-chat-latest | 2 | yes | yes | gpt-5.3-chat-latest | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 1,629 |
| gpt-5.3-chat-latest | 3 | yes | yes | gpt-5.3-chat-latest | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 3,911 |
| gpt-5.4 | 1 | yes | yes | gpt-5.4 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 461 |
| gpt-5.4 | 2 | yes | yes | gpt-5.4 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 1,623 |
| gpt-5.4 | 3 | yes | yes | gpt-5.4 | chat_completions | - | 1.00 | 1 | 4 | 0 | 100 | 3,911 |
| gpt-5.5 | 1 | no | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 101 | 472 |
| gpt-5.5 | 2 | no | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 102 | 1,944 |
| gpt-5.5_v3_repeat | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 5 | 4 | 0 | 505 | 4,322 |
| gpt-5.5_v4_mini | 1 | yes | yes | gpt-5.4-mini | responses | low | - | 1 | 4 | 0 | 101 | 3,917 |
| gpt-5.5_v4_mini_high | 1 | yes | yes | gpt-5.4-mini | responses | high | - | 1 | 4 | 0 | 101 | 6,308 |
| gpt-5.5_v4_mini_medium | 1 | yes | yes | gpt-5.4-mini | responses | medium | - | 1 | 4 | 0 | 101 | 4,712 |
| gpt-5.5_v4_reasoning | 1 | yes | yes | gpt-5.5 | responses | low | - | 1 | 4 | 0 | 101 | 3,831 |
| gpt-5.5_v4_reasoning_high | 1 | yes | yes | gpt-5.5 | responses | high | - | 1 | 4 | 0 | 101 | 4,775 |
| gpt-5.5_v4_reasoning_medium | 1 | yes | yes | gpt-5.5 | responses | medium | - | 1 | 4 | 0 | 101 | 4,041 |
| gpt-5.6-sol | 1 | yes | yes | gpt-5.6-sol | responses | medium | 1.00 | 1 | 4 | 0 | 100 | 398 |
| gpt-5.6-sol | 2 | yes | yes | gpt-5.6-sol | responses | medium | 1.00 | 1 | 4 | 0 | 100 | 1,588 |
| gpt-5.6-sol | 3 | yes | yes | gpt-5.6-sol | responses | medium | 1.00 | 1 | 4 | 0 | 100 | 3,971 |
| legacy_scholarly | 1 | no | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| legacy_scholarly | 2 | no | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| legacy_scholarly_v3_repeat | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 5 | 4 | 0 | 10 | 4,556 |
| legacy_scholarly_v4_mini | 1 | yes | yes | gpt-5.4-mini | responses | low | - | 1 | 4 | 1 | 0 | - |
| legacy_scholarly_v4_mini_high | 1 | yes | yes | gpt-5.4-mini | responses | high | - | 1 | 4 | 1 | 0 | - |
| legacy_scholarly_v4_mini_medium | 1 | yes | yes | gpt-5.4-mini | responses | medium | - | 1 | 4 | 1 | 0 | - |
| legacy_scholarly_v4_reasoning | 1 | yes | yes | gpt-5.5 | responses | low | - | 1 | 4 | 1 | 1 | 3,602 |
| legacy_scholarly_v4_reasoning_high | 1 | yes | yes | gpt-5.5 | responses | high | - | 1 | 4 | 1 | 0 | - |
| legacy_scholarly_v4_reasoning_medium | 1 | yes | yes | gpt-5.5 | responses | medium | - | 1 | 4 | 0 | 1 | 4,125 |
| limerick | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| lit_tech_cool | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| lit_tech_warm | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| paper_guidance_ablation_gpt56 | 1 | yes | yes | gpt-5.6-sol | responses | medium | 1.00 | 3 | 1 | 0 | 300 | 1,589 |
| paper_guidance_ablation_gpt56 | 2 | yes | yes | gpt-5.6-sol | responses | medium | 1.00 | 3 | 1 | 0 | 300 | 3,053 |
| paper_guidance_ablation_gpt56 | 3 | yes | yes | gpt-5.6-sol | responses | medium | 1.00 | 3 | 1 | 0 | 300 | 3,948 |
| parallage_01_diplomatic_literal | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 663 |
| parallage_02_interlinear_gloss | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 2,204 |
| parallage_03_syntax_scaffold | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 938 |
| parallage_04_minimal_inference | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 659 |
| parallage_05_scholarly_readable | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 795 |
| parallage_06_smooth_idiomatic | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 656 |
| parallage_07_message_paraphrase | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 1,092 |
| parallage_08_controlled_english | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 665 |
| parallage_09_analyst_brief | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 721 |
| parallage_10_plain_language | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 670 |
| parallage_11_learners_translation | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 1,602 |
| parallage_12_named_entity_explicit | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 1,062 |
| parallage_13_forked_lattice | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 1,456 |
| parallage_14_uncertainty_annotated | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 1,555 |
| parallage_15_decision_log | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 1,444 |
| parallage_16_adversarial_red_team | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 921 |
| parallage_17_back_translation_audit | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 1,149 |
| parallage_18_mnemonic_translation | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 5 | 0 | 20 | 1,110 |
| parallage_19_alliterative_mnemonic | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 5 | 0 | 20 | 968 |
| parallage_20_rhyming_poetry | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 5 | 0 | 20 | 763 |
| parallage_audit_pack | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 2,108 |
| parallage_compact_literal | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 869 |
| parallage_idiomatic_reader | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 935 |
| parallage_lattice_pack | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 1,491 |
| parallage_memory_pack | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 5 | 0 | 20 | 1,176 |
| parallage_scholarly_edition | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 1,095 |
| parallage_spectrum_pack | 1 | yes | yes | gpt-5.5 | chat_completions | - | - | 1 | 4 | 0 | 20 | 2,017 |
| poetic_rhyming_lines | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| readable_context_cool | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| readable_context_warm | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| risk_factors_5 | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| year10_student | 1 | yes | yes | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 0 | - |
| gpt-5.5 | 3 | yes | no | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 2,501 | 3,756 |
| legacy_scholarly | 3 | yes | no | gpt-5.5 | chat_completions | - | 1.00 | 1 | 5 | 0 | 381 | 3,192 |
Model Cost Averages
Prices are configured in model_pricing.py as of 2026-07-31. Dollar estimates use rows with recorded input/output token splits; reasoning tokens are shown separately but already included in output-token billing.
| Model | API | Reasoning | Input / output $ per 1M | Runs | Priced runs | Input tokens | Output tokens | Reasoning tokens | Token share | Avg tokens | Total est. | Avg est. | Last run |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| gpt-5.5 | chat_completions | - | $5 / $30 | 4,146 | 3,935 | 12,192,770 | 1,774,512 | 1,163,722 | 53.7% | 3,541 | $114.1992 | $0.0290 | 2026-08-23 20:14:52 |
| gpt-5.5 | responses | high | $5 / $30 | 101 | 101 | 377,361 | 104,948 | 94,911 | 1.8% | 4,775 | $5.0352 | $0.0499 | 2026-08-14 20:11:34 |
| gpt-5.5 | responses | medium | $5 / $30 | 102 | 102 | 380,703 | 31,595 | 21,576 | 1.5% | 4,042 | $2.8514 | $0.0280 | 2026-08-14 20:11:31 |
| gpt-5.5 | responses | low | $5 / $30 | 102 | 102 | 380,703 | 9,809 | 0 | 1.4% | 3,829 | $2.1978 | $0.0215 | 2026-08-14 20:11:28 |
| gpt-5.4 | chat_completions | - | $2.5 / $15 | 300 | 300 | 571,244 | 28,278 | 0 | 2.2% | 1,998 | $1.8523 | $0.0062 | 2026-07-15 07:30:59 |
| gpt-5.4-mini | responses | high | $0.75 / $4.5 | 101 | 101 | 376,974 | 260,169 | 250,343 | 2.3% | 6,308 | $1.4535 | $0.0144 | 2026-07-08 16:52:11 |
| gpt-5.4-mini | responses | medium | $0.75 / $4.5 | 101 | 101 | 376,974 | 98,911 | 89,145 | 1.7% | 4,712 | $0.7278 | $0.0072 | 2026-07-08 16:52:05 |
| gpt-5.4-mini | responses | low | $0.75 / $4.5 | 101 | 101 | 376,974 | 18,680 | 8,968 | 1.4% | 3,917 | $0.3668 | $0.0036 | 2026-07-08 16:51:49 |
| gpt-5.6-sol | responses | medium | - | 1,200 | 1,200 | 2,953,976 | 215,403 | 98,074 | 11.6% | 2,641 | - | - | 2026-07-18 21:28:23 |
| claude-fable-5 | chat_completions | - | - | 300 | 0 | 0 | 0 | 0 | 0.0% | - | - | - | 2026-07-05 18:49:58 |
| claude-opus-4.8 | chat_completions | - | - | 300 | 0 | 0 | 0 | 0 | 0.0% | - | - | - | 2026-08-22 19:05:38 |
| claude-sonnet-5 | chat_completions | - | - | 300 | 0 | 0 | 0 | 0 | 0.0% | - | - | - | 2026-07-05 18:49:58 |
| gpt-4-turbo-2024-04-09 | chat_completions | - | - | 300 | 300 | 623,999 | 25,581 | 0 | 2.4% | 2,165 | - | - | 2026-07-16 07:00:26 |
| gpt-4.1-2025-04-14 | chat_completions | - | - | 300 | 300 | 548,744 | 25,418 | 0 | 2.1% | 1,914 | - | - | 2026-07-16 07:00:57 |
| gpt-4o-2024-05-13 | chat_completions | - | - | 300 | 300 | 548,744 | 24,935 | 0 | 2.1% | 1,912 | - | - | 2026-07-16 07:03:13 |
| gpt-4o-2024-08-06 | chat_completions | - | - | 300 | 300 | 548,744 | 24,949 | 0 | 2.1% | 1,912 | - | - | 2026-07-16 07:00:37 |
| gpt-4o-2024-11-20 | chat_completions | - | - | 300 | 300 | 548,744 | 25,982 | 0 | 2.1% | 1,916 | - | - | 2026-07-16 07:00:47 |
| gpt-5-2025-08-07 | chat_completions | - | - | 300 | 300 | 571,244 | 756,468 | 725,824 | 4.9% | 4,426 | - | - | 2026-07-15 13:54:52 |
| gpt-5.1-2025-11-13 | chat_completions | - | - | 300 | 300 | 571,244 | 31,091 | 0 | 2.2% | 2,008 | - | - | 2026-07-15 13:55:05 |
| gpt-5.3-chat-latest | chat_completions | - | - | 300 | 300 | 571,244 | 29,567 | 1,152 | 2.2% | 2,003 | - | - | 2026-07-15 12:36:11 |
| gpt-5.2-2025-12-11 | chat_completions | - | - | 297 | 297 | 570,148 | 29,245 | 0 | 2.2% | 2,018 | - | - | 2026-07-15 12:36:28 |
| gpt-5.2 | chat_completions | - | - | 20 | 0 | 0 | 0 | 0 | 0.0% | 506 | - | - | 2026-02-14 12:02:32 |
Configured Pricing
| Model | Input $/1M | Output $/1M | Source |
|---|---|---|---|
| gpt-5.6-luna | $0.2 | $1.2 | OpenAI pricing |
| gpt-5.5 | $5 | $30 | OpenAI pricing |
| gpt-5.4 | $2.5 | $15 | OpenAI pricing |
| gpt-5.4-mini | $0.75 | $4.5 | OpenAI pricing |