Sarvam 105B
sarvam/sarvam-105bText · 131K context · Nov 2026 · 1 upstreamsupstream上游
Sarvam's flagship 105B-parameter sparse Mixture-of-Experts model with 10.3B active parameters, built for reasoning, tool use and the ten most-spoken Indian languages. The 1711 weights run behind the stable sarvam-105b API id with a 128K context window.
Needs your own keyTo use Sarvam 105B, add your Sarvam AI key. AnyRouter adds no fee.
- contextngữ cảnh上下文
- 131K
- inputđầu vào输入
- —
- outputđầu ra输出
- —
- routestuyến路由
- 2
- speed, 24htốc độ, 24h速度,24h
- No data yetChưa có dữ liệu暂无数据
Upstreams
2- 1Sarvam AIStandardBYOKBilled to your key
- 2Sarvam AIStandardBYOKBilled to your key
Compare
Compared with models of similar price and context window.
| Model | In / out per 1M | Context | |
|---|---|---|---|
| Sarvam 105B | $0 / $0 | 131K | |
| Muse Glimmer 30B | $0 / $0 | 131K | |
| Amos 1 Large | $0 / $0 | 131K | |
| d3-edge | $0 / $0 | 131K | |
| d3-flash | $0 / $0 | 131K |
Quick start
curl https://anyrouter.dev/api/v1/chat/completions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sarvam/sarvam-105b",
"messages": [
{
"role": "user",
"content": "Say hi in 3 words."
}
]
}'Details
- Owner
- Sarvam
- Kind
- Chat
- Released
- Nov 2026
- Context
- 131K
- Capabilities
- Data policy
- See each route
- Endpoint
/api/v1/chat/completions
GalleryThư viện ảnh图库
Images from the vendorẢnh từ nhà phát hành图片来自厂商
- Agentic tool use and long-context reasoning.
- Indic-language chat across native script, romanized and code-mixed input.
Sarvam's flagship 105B-parameter sparse Mixture-of-Experts model with 10.3B active parameters, built for reasoning, tool use and the ten most-spoken Indian languages. The 1711 weights run behind the stable sarvam-105b API id with a 128K context window.
Architecture and licenseKiến trúc và giấy phép架构与许可
- Active parametersTham số kích hoạt激活参数
- 10.3B[1]
- Native contextNgữ cảnh gốc原生上下文
- 131,072[2]
- LicenseGiấy phép许可
- Apache-2.0 · Open weightsTrọng số mở开放权重[1],[2]
Good forPhù hợp với适用场景[3],[2]
- Agentic tool use and long-context reasoning.
- Indic-language chat across native script, romanized and code-mixed input.
StrengthsĐiểm mạnh优势[1],[3]
- 105B MoE with 10.3B active parameters and multi-head latent attention.
- Post-trained for tool calling, instruction following and Indian languages.
- Apache 2.0 weights in NVFP4 and BF16.
Known limitsGiới hạn đã biết已知局限[2]
- Reasoning is on by default and reasoning tokens count toward max_tokens.
- The conversations API id has a smaller 32K context and never reasons.
API notesGhi chú APIAPI 说明[2]
- OpenAI-compatible POST /v2/chat/completions; tools and tool_choice supported.
- Set reasoning_effort to none to turn thinking off on sarvam-105b.
Links and versionsLiên kết và phiên bản链接与版本
- AnnouncementBài công bố发布公告
- sarvam.ai
- Model cardThẻ mô hình模型卡
- huggingface.co
- DocsTài liệu文档
- docs.sarvam.ai
- Pricing pageTrang giá价格页
- docs.sarvam.ai
SourcesNguồn来源
- [1]Sarvam-105B-1711 model cardaccessedtruy cập访问于 2026-11-23
- [2]Sarvam-105B API model pageaccessedtruy cập访问于 2026-11-23
- [3]Sarvam-105B-1711 launch postaccessedtruy cập访问于 2026-11-23
Upstreams and pricingUpstream và giá上游与价格
Share cards2 images


AliasesBí danh别名 (1)
sarvam/sarvam-105b-1711
Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.
Across all upstreams
Loading usage…