recursive
Recursive: Flint (free)
recursive/flint-v1.0:free
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
recursive/flint-v1.0:free is Recursive’s open-weight mixture-of-experts model for coding agents. Recursive describes text generation, reasoning, and multi-turn tool use, combining a large total parameter count with a small active-parameter fraction per token. Its developer-reported release evaluations focus on agentic software work. OpenRouter lists mandatory reasoning and a long context configuration for this exact free variant, while the available evidence remains limited to catalog and developer materials.[1][2]
Strengths
- Recursive positions it for agentic software tasks such as investigating codebases, fixing bugs, implementing features, and writing tests.[2]
- The MoE design uses a small active-parameter fraction per token while retaining a much larger total parameter count.[2]
- The model documentation describes reasoning, multi-turn and OpenAI-compatible tool calls, a long context configuration, and an Apache 2.0 checkpoint release.[2]
Limitations
- OpenRouter marks reasoning as mandatory; Recursive cautions that long reasoning can add latency or exhaust the output budget before completion.[1][2]
- The developer warns that code and tool actions may be incorrect, harmful, or unsafe, so testing, review, permissions, and execution boundaries remain necessary.[2]
- The supplied evidence comes only from OpenRouter and Recursive’s own documentation, so independent and workload-specific validation is still needed, including for the chosen checkpoint and runtime.[1][2]
Where to use it
- Consider it for coding agents that inspect repositories, patch defects, implement scoped features, or draft tests.[2]
- It may fit development assistants that need explicit reasoning plus OpenAI-compatible, multi-turn tool calls.[1][2]
- Evaluate it for long-context repository investigation or code-change planning, with accuracy checked at the actual prompt and output lengths.[2]
Sources
- [1] OpenRouter catalog · Recursive: Flint (free)Sources checked: Nov 13, 2026
- [2] Model documentation · Recursive: Flint (free)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...
Specifications
- Model ID
- recursive/flint-v1.0:free
- Canonical ID
- recursive/flint-v1.0-20261021
- Creator
- recursive
- Added to OpenRouter
- 21.10.2026
- Context length
- 262,144
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: mandatory · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Recursivebf16 | 262,144 | $0 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.