connor/dotfiles
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

opencode: context limits from vendor docs, not inherited guesses

Browse Source 
Checked every hosted entry against published documentation 2026-09-21. There
were errors in BOTH directions, and the overstatements are the dangerous
half -- an understated limit wastes tokens, an overstated one is a hard API
rejection partway through a session.

  anthropic/claude-haiku-4-5   1,000,000 ->   200,000   OVERSTATED 5x
  openai/gpt-5.6-sol             200,000 -> 1,050,000
  openai/gpt-5.5                 200,000 -> 1,050,000
  openai/gpt-5.4                 200,000 -> 1,050,000
  openai/gpt-5.4-mini            200,000 -> 1,050,000
  chatgpt/* (4 aliases)          272,000 -> 1,050,000
  agent/*-gpt-5.x (11 aliases)   272,000 -> 1,050,000
  agent/*-glm-5.3 (4 aliases)    150,000 ->   200,000   deliberate cap
  anthropic/claude-{opus,sonnet}-5           unchanged, already correct

Haiku is the one that mattered. Opus 5 and Sonnet 5 really are 1M, the whole
Anthropic block was set to 1M, and Haiku inherited a limit five times its
real 200k. Opencode would have grown a session past the ceiling and the API
would have refused it.

⚠ glm-5.3 is capped at 200,000 BY CHOICE. Its real maximum is 1M. GLM bills
per input token and cost on this stack tracks context size and cache-read
volume more than model choice, so the cap is budget control, not ignorance.
Do not "correct" it upward against the docs. This is the one place where a
declared limit below the vendor maximum is intentional.

⚠ chatgpt/* now carries the API's 1,050,000, but OpenAI does not publish a
context limit for ChatGPT-plan routing and it has historically been far
below the API's. This is deliberately optimistic and being watched for a
crash; if long sessions start failing, that is the first thing to lower.

Left alone for want of evidence, not because they are right:
openai/gpt-5.3-codex (200,000), agent/librarian-glm-5.3-flash (128,000),
agent/sisyphus-junior-glm-5.3-flash (150,000). Raising an unconfirmed limit
risks the Haiku failure mode, so these stay until measured.

Unrelated but found while checking: LiteLLM declares kimi/kimi-k2.7-code at
272,000 against a published 262,144. Overstated by ~10k.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01E9UH1zGZZtA9yhohmQrcT6
This commit is contained in:
connorandClaude Opus 5 committed 2026-09-21 22:01:33 -04:00
1 parent f9cfab6221
commit 4e3a0d6ccc
3 files changed
+112 -112
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

common/opencode/personal.json
+36 -36
View File
@@ -103,8 +103,8 @@
"anthropic/claude-haiku-4-5": {
"name": "claude-haiku-4-5 (Anthropic direct)",
"limit": {
"context": 1000000,
"output": 128000
"context": 200000,
"output": 64000
},
"cost": {
"input": 1.0,
@@ -116,8 +116,8 @@
"chatgpt/gpt-5.6-sol": {
"name": "gpt-5.6-sol (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -129,8 +129,8 @@
"chatgpt/gpt-5.6-terra": {
"name": "gpt-5.6-terra (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -142,8 +142,8 @@
"chatgpt/gpt-5.6-luna": {
"name": "gpt-5.6-luna (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -155,8 +155,8 @@
"chatgpt/gpt-5.5": {
"name": "gpt-5.5 (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -168,8 +168,8 @@
"openai/gpt-5.6-sol": {
"name": "gpt-5.6-sol (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 4.0,
@@ -181,8 +181,8 @@
"openai/gpt-5.5": {
"name": "gpt-5.5 (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 5.0,
@@ -194,8 +194,8 @@
"openai/gpt-5.4": {
"name": "gpt-5.4 (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -207,8 +207,8 @@
"openai/gpt-5.4-mini": {
"name": "gpt-5.4-mini (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.75,
@@ -247,8 +247,8 @@
"agent/explore-gpt-5.6-luna": {
"name": "explore -> local/explore",
"limit": {
"context": 272000,
"output": 32000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -261,8 +261,8 @@
"agent/sisyphus-glm-5.3": {
"name": "sisyphus -> glm-5.3",
"limit": {
"context": 150000,
"output": 64000
"context": 200000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -275,8 +275,8 @@
"agent/atlas-glm-5.3": {
"name": "atlas -> glm-5.3",
"limit": {
"context": 150000,
"output": 64000
"context": 200000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -289,8 +289,8 @@
"agent/prometheus-glm-5.3": {
"name": "prometheus -> glm-5.3",
"limit": {
"context": 150000,
"output": 64000
"context": 200000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -303,8 +303,8 @@
"agent/metis-glm-5.3": {
"name": "metis -> glm-5.3",
"limit": {
"context": 150000,
"output": 64000
"context": 200000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -331,8 +331,8 @@
"agent/momus-gpt-5.5": {
"name": "momus -> gpt-5.5",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -345,8 +345,8 @@
"agent/gpt-5.6-sol-hephaestus": {
"name": "hephaestus -> gpt-5.6-sol",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 4.0,
@@ -359,8 +359,8 @@
"agent/oracle-gpt-5.5": {
"name": "oracle -> gpt-5.5",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -373,8 +373,8 @@
"agent/looker-gpt-5.5": {
"name": "looker -> gpt-5.4 (vision)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
common/opencode/work-strict.json
+38 -38
View File
@@ -77,8 +77,8 @@
"chatgpt/gpt-5.6-sol": {
"name": "gpt-5.6-sol (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -90,8 +90,8 @@
"chatgpt/gpt-5.6-terra": {
"name": "gpt-5.6-terra (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -103,8 +103,8 @@
"chatgpt/gpt-5.6-luna": {
"name": "gpt-5.6-luna (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -116,8 +116,8 @@
"chatgpt/gpt-5.5": {
"name": "gpt-5.5 (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -129,8 +129,8 @@
"openai/gpt-5.6-sol": {
"name": "gpt-5.6-sol (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 4.0,
@@ -142,8 +142,8 @@
"openai/gpt-5.5": {
"name": "gpt-5.5 (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 5.0,
@@ -155,8 +155,8 @@
"openai/gpt-5.4": {
"name": "gpt-5.4 (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -168,8 +168,8 @@
"openai/gpt-5.4-mini": {
"name": "gpt-5.4-mini (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.75,
@@ -194,8 +194,8 @@
"agent/librarian-gpt-5.6-luna": {
"name": "librarian -> local/librarian",
"limit": {
"context": 272000,
"output": 32000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -208,8 +208,8 @@
"agent/explore-gpt-5.6-luna": {
"name": "explore -> local/explore",
"limit": {
"context": 272000,
"output": 32000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -222,8 +222,8 @@
"agent/oracle-gpt-5.5": {
"name": "oracle -> work/oracle",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -236,8 +236,8 @@
"agent/looker-gpt-5.5": {
"name": "looker -> work/looker",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -250,8 +250,8 @@
"agent/momus-gpt-5.5": {
"name": "momus -> work/momus",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -264,8 +264,8 @@
"agent/sisyphus-junior-gpt-5.6-luna": {
"name": "sisyphus-junior -> work/sisyphus-junior",
"limit": {
"context": 272000,
"output": 32000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -278,8 +278,8 @@
"agent/gpt-5.6-sol-hephaestus": {
"name": "hephaestus -> work/hephaestus",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 1.75,
@@ -292,8 +292,8 @@
"agent/atlas-gpt-5.5": {
"name": "atlas -> work/atlas (gpt-5.4)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -306,8 +306,8 @@
"agent/prometheus-gpt-5.6-sol": {
"name": "prometheus -> work/prometheus",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 4.0,
@@ -320,8 +320,8 @@
"agent/sisyphus-gpt-5.6-sol": {
"name": "sisyphus -> work/sisyphus",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 4.0,
@@ -334,8 +334,8 @@
"agent/metis-gpt-5.5": {
"name": "metis -> work/metis",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
common/opencode/work.json
+38 -38
View File
@@ -77,8 +77,8 @@
"chatgpt/gpt-5.6-sol": {
"name": "gpt-5.6-sol (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -90,8 +90,8 @@
"chatgpt/gpt-5.6-terra": {
"name": "gpt-5.6-terra (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -103,8 +103,8 @@
"chatgpt/gpt-5.6-luna": {
"name": "gpt-5.6-luna (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -116,8 +116,8 @@
"chatgpt/gpt-5.5": {
"name": "gpt-5.5 (ChatGPT Plus, flat fee)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -129,8 +129,8 @@
"openai/gpt-5.6-sol": {
"name": "gpt-5.6-sol (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 4.0,
@@ -142,8 +142,8 @@
"openai/gpt-5.5": {
"name": "gpt-5.5 (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 5.0,
@@ -155,8 +155,8 @@
"openai/gpt-5.4": {
"name": "gpt-5.4 (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -168,8 +168,8 @@
"openai/gpt-5.4-mini": {
"name": "gpt-5.4-mini (OpenAI direct)",
"limit": {
"context": 200000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.75,
@@ -194,8 +194,8 @@
"agent/librarian-gpt-5.6-luna": {
"name": "librarian -> local/librarian",
"limit": {
"context": 272000,
"output": 32000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -208,8 +208,8 @@
"agent/explore-gpt-5.6-luna": {
"name": "explore -> local/explore",
"limit": {
"context": 272000,
"output": 32000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.0,
@@ -222,8 +222,8 @@
"agent/oracle-gpt-5.5": {
"name": "oracle -> work/oracle",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -236,8 +236,8 @@
"agent/looker-gpt-5.5": {
"name": "looker -> work/looker",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -250,8 +250,8 @@
"agent/momus-gpt-5.5": {
"name": "momus -> work/momus",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -264,8 +264,8 @@
"agent/sisyphus-junior-gpt-5.6-luna": {
"name": "sisyphus-junior -> work/sisyphus-junior",
"limit": {
"context": 272000,
"output": 32000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -278,8 +278,8 @@
"agent/gpt-5.6-sol-hephaestus": {
"name": "hephaestus -> work/hephaestus",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 1.75,
@@ -292,8 +292,8 @@
"agent/atlas-gpt-5.5": {
"name": "atlas -> work/atlas (gpt-5.4)",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,
@@ -306,8 +306,8 @@
"agent/prometheus-gpt-5.6-sol": {
"name": "prometheus -> work/prometheus",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 4.0,
@@ -320,8 +320,8 @@
"agent/sisyphus-gpt-5.6-sol": {
"name": "sisyphus -> work/sisyphus",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 4.0,
@@ -334,8 +334,8 @@
"agent/metis-gpt-5.5": {
"name": "metis -> work/metis",
"limit": {
"context": 272000,
"output": 64000
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2.5,