mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-30 06:41:51 +00:00
1a74795735
Anthropic released Claude Opus 4.8 on 2026-05-27, available on OpenRouter, Anthropic, Amazon Bedrock, and Claude Platform on AWS: - https://openrouter.ai/anthropic/claude-opus-4.8 - https://openrouter.ai/anthropic/claude-opus-4.8-fast The fast-mode variant is a separate model ID (anthropic/claude-opus-4.8-fast) priced at 2x of the base model — a notable improvement over the 6x premium on older Opus generations (4.6/4.7). It is NOT a `speed: "fast"` request parameter like Opus 4.6; Anthropic's native fast-mode beta still only covers Opus 4.6. Changes: hermes_cli/models.py - Add anthropic/claude-opus-4.8 + anthropic/claude-opus-4.8-fast to the OpenRouter fallback snapshot and the Nous Portal curated list (live catalogs surface them automatically when reachable; the fallback list matters when the manifest fetch fails). - Add claude-opus-4-8 to the Anthropic-native picker list. agent/model_metadata.py - Register claude-opus-4-8 / claude-opus-4.8 in DEFAULT_CONTEXT_LENGTHS with 1M tokens (matches 4.6/4.7). agent/anthropic_adapter.py - Extend _XHIGH_EFFORT_SUBSTRINGS, _ADAPTIVE_THINKING_SUBSTRINGS, and _NO_SAMPLING_PARAMS_SUBSTRINGS with "4-8"/"4.8". 4.8 inherits the Opus 4.7 API contract: adaptive thinking only, xhigh effort level supported, sampling parameters (temperature/top_p/top_k) return 400. - Add claude-opus-4-8 to _ANTHROPIC_OUTPUT_LIMITS (128k max output, same as 4.7). Matches by substring so claude-opus-4-8-fast and date-stamped variants resolve correctly. agent/usage_pricing.py - Add anthropic/claude-opus-4-8: $5/$25 per MTok input/output, $0.50 cache read, $6.25 cache write (same as 4.6/4.7). - Add anthropic/claude-opus-4-8-fast: $10/$50 per MTok (2x), $1.00 cache read, $12.50 cache write. Per OpenRouter, the 2x premium is the only differentiator from regular Opus 4.8. - OpenRouter routes still pull pricing from the live /models API, so no static OpenRouter entry is needed. tests/agent/test_model_metadata.py - Extend the Claude 4.6+ context-length tag list with 4.8/4-8. website/static/api/model-catalog.json - Regenerated via `python scripts/build_model_catalog.py` to pick up the new entries in the OpenRouter and Nous Portal fallback lists. E2E verification (isolated sys.path import against the worktree): - _supports_adaptive_thinking, _supports_xhigh_effort, _forbids_sampling_params all return True for claude-opus-4.8 and claude-opus-4.8-fast. - _supports_fast_mode (the `speed: "fast"` request-parameter gate) stays False for 4.8 — fast mode is a separate model ID on OpenRouter, not a parameter Anthropic accepts on the base model. - DEFAULT_CONTEXT_LENGTHS resolves 1M for both notations. - resolve_billing_route + _lookup_official_docs_pricing resolve the correct $5/$25 (regular) and $10/$50 (fast) pricing for both dot-notation and dash-notation inputs. - 4.7 and 4.6 regression: behavior unchanged. Unit tests: 305 passed across tests/agent/test_usage_pricing.py, test_model_metadata.py, tests/hermes_cli/test_model_catalog.py, test_models.py, test_model_validation.py, test_models_dev_preferred_merge.py.
233 lines
5.3 KiB
JSON
233 lines
5.3 KiB
JSON
{
|
|
"version": 1,
|
|
"updated_at": "2026-05-28T17:19:08Z",
|
|
"metadata": {
|
|
"source": "hermes-agent repo",
|
|
"docs": "https://hermes-agent.nousresearch.com/docs/reference/model-catalog"
|
|
},
|
|
"providers": {
|
|
"openrouter": {
|
|
"metadata": {
|
|
"display_name": "OpenRouter",
|
|
"note": "Descriptions drive picker badges. Live /api/v1/models filters curated ids by tool-calling support and free pricing."
|
|
},
|
|
"models": [
|
|
{
|
|
"id": "anthropic/claude-opus-4.8",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "anthropic/claude-opus-4.8-fast",
|
|
"description": "2x price, higher output speed"
|
|
},
|
|
{
|
|
"id": "anthropic/claude-opus-4.7",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "anthropic/claude-opus-4.6",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "anthropic/claude-sonnet-4.6",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "moonshotai/kimi-k2.6",
|
|
"description": "recommended"
|
|
},
|
|
{
|
|
"id": "openrouter/pareto-code",
|
|
"description": "auto-routes to cheapest coder meeting openrouter.min_coding_score"
|
|
},
|
|
{
|
|
"id": "qwen/qwen3.7-max",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "anthropic/claude-haiku-4.5",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.5",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.5-pro",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.4-mini",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.4-nano",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.3-codex",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "xiaomi/mimo-v2.5-pro",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "tencent/hy3-preview",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "google/gemini-3-pro-image-preview",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "google/gemini-3-flash-preview",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "google/gemini-3.1-pro-preview",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "google/gemini-3.1-flash-lite-preview",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "qwen/qwen3.6-35b-a3b",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "stepfun/step-3.5-flash",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "minimax/minimax-m2.7",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "z-ai/glm-5.1",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "x-ai/grok-4.20",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "x-ai/grok-4.3",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "nvidia/nemotron-3-super-120b-a12b",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "deepseek/deepseek-v4-pro",
|
|
"description": ""
|
|
},
|
|
{
|
|
"id": "openrouter/elephant-alpha",
|
|
"description": "free"
|
|
},
|
|
{
|
|
"id": "openrouter/owl-alpha",
|
|
"description": "free"
|
|
},
|
|
{
|
|
"id": "tencent/hy3-preview:free",
|
|
"description": "free"
|
|
},
|
|
{
|
|
"id": "nvidia/nemotron-3-super-120b-a12b:free",
|
|
"description": "free"
|
|
},
|
|
{
|
|
"id": "inclusionai/ring-2.6-1t:free",
|
|
"description": "free"
|
|
}
|
|
]
|
|
},
|
|
"nous": {
|
|
"metadata": {
|
|
"display_name": "Nous Portal",
|
|
"note": "Free-tier gating is determined live via Portal pricing (partition_nous_models_by_tier), not this manifest."
|
|
},
|
|
"models": [
|
|
{
|
|
"id": "anthropic/claude-opus-4.8"
|
|
},
|
|
{
|
|
"id": "anthropic/claude-opus-4.7"
|
|
},
|
|
{
|
|
"id": "anthropic/claude-opus-4.6"
|
|
},
|
|
{
|
|
"id": "anthropic/claude-sonnet-4.6"
|
|
},
|
|
{
|
|
"id": "moonshotai/kimi-k2.6"
|
|
},
|
|
{
|
|
"id": "qwen/qwen3.7-max"
|
|
},
|
|
{
|
|
"id": "anthropic/claude-haiku-4.5"
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.5"
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.5-pro"
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.4-mini"
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.4-nano"
|
|
},
|
|
{
|
|
"id": "openai/gpt-5.3-codex"
|
|
},
|
|
{
|
|
"id": "xiaomi/mimo-v2.5-pro"
|
|
},
|
|
{
|
|
"id": "tencent/hy3-preview"
|
|
},
|
|
{
|
|
"id": "google/gemini-3-pro-preview"
|
|
},
|
|
{
|
|
"id": "google/gemini-3-flash-preview"
|
|
},
|
|
{
|
|
"id": "google/gemini-3.1-pro-preview"
|
|
},
|
|
{
|
|
"id": "google/gemini-3.1-flash-lite-preview"
|
|
},
|
|
{
|
|
"id": "qwen/qwen3.6-35b-a3b"
|
|
},
|
|
{
|
|
"id": "stepfun/step-3.5-flash"
|
|
},
|
|
{
|
|
"id": "minimax/minimax-m2.7"
|
|
},
|
|
{
|
|
"id": "z-ai/glm-5.1"
|
|
},
|
|
{
|
|
"id": "x-ai/grok-4.3"
|
|
},
|
|
{
|
|
"id": "nvidia/nemotron-3-super-120b-a12b"
|
|
},
|
|
{
|
|
"id": "deepseek/deepseek-v4-pro"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|