context-1 API & Inference Endpoint

Model Details

Base model: gpt-oss-20b
Parameters: 20B (Mixture of Experts)
Training: SFT + RL (CISPO) with a staged curriculum
Precision: BF16 (MXFP4 quantized checkpoint coming soon)

Key Capabilities

Query decomposition: Breaks complex multi-constraint questions into targeted subqueries.
Parallel tool calling: Averages 2.56 tool calls per turn, reducing total turns and end-to-end latency.
Self-editing context: Selectively prunes irrelevant documents mid-search to sustain retrieval quality over long horizons within a bounded context window (0.94 prune accuracy).
Cross-domain generalization: Trained on web, legal, and finance tasks; generalizes to held-out domains and public benchmarks (BrowseComp-Plus, SealQA, FRAMES, HLE).

Important: Agent Harness Required

Context-1 is trained to operate within a specific agent harness that manages tool execution, token budgets, context pruning, and deduplication. The harness is not yet public. Running the model without it will not reproduce the results reported in the technical report.

We plan to release the full agent harness and evaluation code soon. In the meantime, the technical report describes the harness design in detail.

Citation

bibtex

@techreport{bashir2026context1,  title = {Chroma Context-1: Training a Self-Editing Search Agent},  author = {Bashir, Hammad and Hong, Kelly and Jiang, Patrick and Shi, Zhiyi},  year = {2026},  month = {March},  institution = {Chroma},  url = {https://trychroma.com/research/context-1},}

License

Apache 2.0

Model Details

Base model: gpt-oss-20b
Parameters: 20B (Mixture of Experts)
Training: SFT + RL (CISPO) with a staged curriculum
Precision: BF16 (MXFP4 quantized checkpoint coming soon)

Key Capabilities

Query decomposition: Breaks complex multi-constraint questions into targeted subqueries.
Parallel tool calling: Averages 2.56 tool calls per turn, reducing total turns and end-to-end latency.
Self-editing context: Selectively prunes irrelevant documents mid-search to sustain retrieval quality over long horizons within a bounded context window (0.94 prune accuracy).
Cross-domain generalization: Trained on web, legal, and finance tasks; generalizes to held-out domains and public benchmarks (BrowseComp-Plus, SealQA, FRAMES, HLE).

Important: Agent Harness Required

We plan to release the full agent harness and evaluation code soon. In the meantime, the technical report describes the harness design in detail.

Citation

bibtex

@techreport{bashir2026context1,  title = {Chroma Context-1: Training a Self-Editing Search Agent},  author = {Bashir, Hammad and Hong, Kelly and Jiang, Patrick and Shi, Zhiyi},  year = {2026},  month = {March},  institution = {Chroma},  url = {https://trychroma.com/research/context-1},}

License

Apache 2.0

context-1

README

Model Details

Key Capabilities

Important: Agent Harness Required

Citation

License

Explore FriendliAI today

README

Model Details

Key Capabilities

Important: Agent Harness Required

Citation

License